stage(elp): consolidate scattered lang work — full-lexicon vocabulary + profiles

Backfill ELP vocabulary from FULL lexicons (UniMorph + kaikki.org Wiktionary,
real gender/inflections) for 8 languages, 812,894 entries total, in the proven
seed-fn format matching the 18 ancient vocabularies:
  es 72,032 | fr 130,517 | de 144,692 | la 22,590 | it 193,675 | pt 115,772 |
  ro 86,504 | ca 47,112
4 of these (es fr de la) backfill ELP languages that had morphology but no
vocabulary; it/pt/ro/ca are new Romance (need morphology-*.el ports next).
Adds lang_profile_* for all 8 + reproducible generators under tests/lang-gen.
Vocab is runtime seed data (not in build manifest, like the 18 ancients);
seed-fn format validated to compile to C via elc.

.gitea/workflows/ci-dev.yaml

@@ -39,9 +39,9 @@ jobs:
         run: |
           dist/platform/elc-linux-amd64 elc-cli.el > dist/elc-gen2.c
           gcc -O2 \
-            -I runtime \
+            -I el-compiler/runtime \
             dist/elc-gen2.c \
-            runtime/el_runtime.c \
+            el-compiler/runtime/el_runtime.c \
             -lcurl -lssl -lcrypto -lpthread -lm \
             -o dist/platform/elc
           chmod +x dist/platform/elc
@@ -54,9 +54,9 @@ jobs:
           mkdir -p dist/bin
           dist/platform/elc elb.el > dist/elb.c
           gcc -O2 \
-            -I runtime \
+            -I el-compiler/runtime \
             dist/elb.c \
-            runtime/el_runtime.c \
+            el-compiler/runtime/el_runtime.c \
             -lcurl -lssl -lcrypto -lpthread -lm \
             -o dist/bin/elb
           chmod +x dist/bin/elb
@@ -91,7 +91,7 @@ jobs:
       - name: Precompile el_runtime.o
         run: |
           set -euo pipefail
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           gcc -O2 -c -I "$RUNTIME" "$RUNTIME/el_runtime.c" \
             -o /tmp/el_runtime.o
           echo "el_runtime.o compiled"
@@ -100,7 +100,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_core.el > /tmp/el_native_core.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_core.c /tmp/el_runtime.o \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_core
@@ -110,7 +110,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_text.el > /tmp/el_native_text.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_text.c /tmp/el_runtime.o \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_text
@@ -120,7 +120,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_string.el > /tmp/el_native_string.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_string.c /tmp/el_runtime.o \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_string
@@ -130,7 +130,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_math.el > /tmp/el_native_math.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_math.c /tmp/el_runtime.o \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_math
@@ -140,7 +140,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_state.el > /tmp/el_native_state.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_state.c /tmp/el_runtime.o \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_state
@@ -150,7 +150,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_time.el > /tmp/el_native_time.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_time.c /tmp/el_runtime.o \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_time
@@ -160,7 +160,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_json.el > /tmp/el_native_json.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_json.c /tmp/el_runtime.o \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_json
@@ -170,7 +170,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_env.el > /tmp/el_native_env.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_env.c /tmp/el_runtime.o \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_env
@@ -180,7 +180,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_fs.el > /tmp/el_native_fs.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_fs.c /tmp/el_runtime.o \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_fs
@@ -191,7 +191,7 @@ jobs:
         run: |
           ABS_ELB="$(pwd)/dist/bin/elb"
           ABS_ELC="$(pwd)/dist/platform/elc"
-          ABS_RUNTIME="$(pwd)/runtime"
+          ABS_RUNTIME="$(pwd)/el-compiler/runtime"
           ABS_OUT="$(pwd)/dist/bin"
           (cd ../epm && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
           chmod +x dist/bin/epm
@@ -202,7 +202,7 @@ jobs:
         run: |
           ABS_ELB="$(pwd)/dist/bin/elb"
           ABS_ELC="$(pwd)/dist/platform/elc"
-          ABS_RUNTIME="$(pwd)/runtime"
+          ABS_RUNTIME="$(pwd)/el-compiler/runtime"
           ABS_OUT="$(pwd)/dist/bin"
           (cd tools/install && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
           chmod +x dist/bin/el-install
@@ -242,7 +242,7 @@ jobs:
             --project=neuron-785695 \
             --package=el-runtime-c \
             --version="${VERSION}" \
-            --source=runtime/el_runtime.c
+            --source=el-compiler/runtime/el_runtime.c
 
           gcloud artifacts generic upload \
             --repository=foundation-dev \
@@ -250,7 +250,7 @@ jobs:
             --project=neuron-785695 \
             --package=el-runtime-h \
             --version="${VERSION}" \
-            --source=runtime/el_runtime.h
+            --source=el-compiler/runtime/el_runtime.h
 
           gcloud artifacts generic upload \
             --repository=foundation-dev \
@@ -258,7 +258,7 @@ jobs:
             --project=neuron-785695 \
             --package=el-runtime-js \
             --version="${VERSION}" \
-            --source=runtime/el_runtime.js
+            --source=el-compiler/runtime/el_runtime.js
 
           echo "Published El SDK version=${VERSION} to foundation-dev"
           # Keep key alive for the ci-base rebuild step below
@@ -291,9 +291,9 @@ jobs:
           FROM ${BASE}
           COPY dist/platform/elc                 /opt/el/dist/platform/elc
           COPY dist/bin/elb                       /opt/el/dist/bin/elb
-          COPY runtime/el_runtime.c  /opt/el/runtime/el_runtime.c
-          COPY runtime/el_runtime.h  /opt/el/runtime/el_runtime.h
-          COPY runtime/el_runtime.js /opt/el/runtime/el_runtime.js
+          COPY el-compiler/runtime/el_runtime.c  /opt/el/el-compiler/runtime/el_runtime.c
+          COPY el-compiler/runtime/el_runtime.h  /opt/el/el-compiler/runtime/el_runtime.h
+          COPY el-compiler/runtime/el_runtime.js /opt/el/el-compiler/runtime/el_runtime.js
           RUN chmod +x /opt/el/dist/platform/elc /opt/el/dist/bin/elb
           EOF
 

.gitea/workflows/ci-stage.yaml

@@ -46,9 +46,9 @@ jobs:
         run: |
           dist/platform/elc-linux-amd64 elc-cli.el > dist/elc-gen2.c
           gcc -O2 \
-            -I runtime \
+            -I el-compiler/runtime \
             dist/elc-gen2.c \
-            runtime/el_runtime.c \
+            el-compiler/runtime/el_runtime.c \
             -lcurl -lssl -lcrypto -lpthread -lm \
             -o dist/platform/elc
           chmod +x dist/platform/elc
@@ -84,7 +84,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_core.el > /tmp/el_native_core.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_core.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_core
@@ -94,7 +94,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_text.el > /tmp/el_native_text.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_text.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_text
@@ -104,7 +104,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_string.el > /tmp/el_native_string.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_string.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_string
@@ -114,7 +114,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_math.el > /tmp/el_native_math.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_math.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_math
@@ -124,7 +124,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_state.el > /tmp/el_native_state.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_state.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_state
@@ -134,7 +134,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_time.el > /tmp/el_native_time.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_time.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_time
@@ -144,7 +144,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_json.el > /tmp/el_native_json.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_json.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_json
@@ -154,7 +154,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_env.el > /tmp/el_native_env.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_env.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_env
@@ -164,7 +164,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_fs.el > /tmp/el_native_fs.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_fs.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_fs
@@ -176,9 +176,9 @@ jobs:
           mkdir -p dist/bin
           dist/platform/elc elb.el > dist/elb.c
           gcc -O2 \
-            -I runtime \
+            -I el-compiler/runtime \
             dist/elb.c \
-            runtime/el_runtime.c \
+            el-compiler/runtime/el_runtime.c \
             -lcurl -lssl -lcrypto -lpthread -lm \
             -o dist/bin/elb
           chmod +x dist/bin/elb
@@ -189,7 +189,7 @@ jobs:
         run: |
           ABS_ELB="$(pwd)/dist/bin/elb"
           ABS_ELC="$(pwd)/dist/platform/elc"
-          ABS_RUNTIME="$(pwd)/runtime"
+          ABS_RUNTIME="$(pwd)/el-compiler/runtime"
           ABS_OUT="$(pwd)/dist/bin"
           (cd ../epm && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
           chmod +x dist/bin/epm
@@ -200,7 +200,7 @@ jobs:
         run: |
           ABS_ELB="$(pwd)/dist/bin/elb"
           ABS_ELC="$(pwd)/dist/platform/elc"
-          ABS_RUNTIME="$(pwd)/runtime"
+          ABS_RUNTIME="$(pwd)/el-compiler/runtime"
           ABS_OUT="$(pwd)/dist/bin"
           (cd tools/install && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
           chmod +x dist/bin/el-install
@@ -235,7 +235,7 @@ jobs:
             --project=neuron-785695 \
             --package=el-runtime-c \
             --version="${VERSION}" \
-            --source=runtime/el_runtime.c
+            --source=el-compiler/runtime/el_runtime.c
 
           gcloud artifacts generic upload \
             --repository=foundation-stage \
@@ -243,7 +243,7 @@ jobs:
             --project=neuron-785695 \
             --package=el-runtime-h \
             --version="${VERSION}" \
-            --source=runtime/el_runtime.h
+            --source=el-compiler/runtime/el_runtime.h
 
           echo "Published El SDK version=${VERSION} to foundation-stage"
           # Keep key alive for the ci-base rebuild step below
@@ -275,9 +275,9 @@ jobs:
           FROM ${BASE}
           COPY dist/platform/elc                 /opt/el/dist/platform/elc
           COPY dist/bin/elb                       /opt/el/dist/bin/elb
-          COPY runtime/el_runtime.c  /opt/el/runtime/el_runtime.c
-          COPY runtime/el_runtime.h  /opt/el/runtime/el_runtime.h
-          COPY runtime/el_runtime.js /opt/el/runtime/el_runtime.js
+          COPY el-compiler/runtime/el_runtime.c  /opt/el/el-compiler/runtime/el_runtime.c
+          COPY el-compiler/runtime/el_runtime.h  /opt/el/el-compiler/runtime/el_runtime.h
+          COPY el-compiler/runtime/el_runtime.js /opt/el/el-compiler/runtime/el_runtime.js
           RUN chmod +x /opt/el/dist/platform/elc /opt/el/dist/bin/elb
           EOF
 

.gitea/workflows/sdk-release.yaml

@@ -47,9 +47,9 @@ jobs:
           mkdir -p dist/platform
           dist/platform/elc-linux-amd64 elc-cli.el > dist/elc-gen2.c
           gcc -O2 \
-            -I runtime \
+            -I el-compiler/runtime \
             dist/elc-gen2.c \
-            runtime/el_runtime.c \
+            el-compiler/runtime/el_runtime.c \
             -lcurl -lssl -lcrypto -lpthread -lm \
             -o dist/platform/elc
           chmod +x dist/platform/elc
@@ -62,9 +62,9 @@ jobs:
           mkdir -p dist/bin
           dist/platform/elc elb.el > dist/elb.c
           gcc -O2 \
-            -I runtime \
+            -I el-compiler/runtime \
             dist/elb.c \
-            runtime/el_runtime.c \
+            el-compiler/runtime/el_runtime.c \
             -lcurl -lssl -lcrypto -lpthread -lm \
             -o dist/bin/elb
           chmod +x dist/bin/elb
@@ -75,7 +75,7 @@ jobs:
         run: |
           ABS_ELB="$(pwd)/dist/bin/elb"
           ABS_ELC="$(pwd)/dist/platform/elc"
-          ABS_RUNTIME="$(pwd)/runtime"
+          ABS_RUNTIME="$(pwd)/el-compiler/runtime"
           ABS_OUT="$(pwd)/dist/bin"
           (cd ../epm && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
           chmod +x dist/bin/epm
@@ -86,7 +86,7 @@ jobs:
         run: |
           ABS_ELB="$(pwd)/dist/bin/elb"
           ABS_ELC="$(pwd)/dist/platform/elc"
-          ABS_RUNTIME="$(pwd)/runtime"
+          ABS_RUNTIME="$(pwd)/el-compiler/runtime"
           ABS_OUT="$(pwd)/dist/bin"
           (cd tools/install && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
           chmod +x dist/bin/el-install
@@ -121,7 +121,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_core.el > /tmp/el_native_core.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_core.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_core
@@ -131,7 +131,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_text.el > /tmp/el_native_text.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_text.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_text
@@ -141,7 +141,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_string.el > /tmp/el_native_string.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_string.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_string
@@ -151,7 +151,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_math.el > /tmp/el_native_math.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_math.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_math
@@ -161,7 +161,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_state.el > /tmp/el_native_state.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_state.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_state
@@ -171,7 +171,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_time.el > /tmp/el_native_time.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_time.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_time
@@ -181,7 +181,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_json.el > /tmp/el_native_json.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_json.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_json
@@ -191,7 +191,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_env.el > /tmp/el_native_env.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_env.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_env
@@ -201,7 +201,7 @@ jobs:
         run: |
           set -euo pipefail
           ELC="$(pwd)/dist/platform/elc"
-          RUNTIME="$(pwd)/runtime"
+          RUNTIME="$(pwd)/el-compiler/runtime"
           "$ELC" --test tests/native/test_fs.el > /tmp/el_native_fs.c
           gcc -O2 -I "$RUNTIME" /tmp/el_native_fs.c "$RUNTIME/el_runtime.c" \
             -lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_fs
@@ -216,8 +216,8 @@ jobs:
           cp lang/dist/platform/elc          dist/sdk/bin/elc
           cp lang/dist/bin/elb               dist/sdk/bin/elb
           cp lang/dist/bin/epm               dist/sdk/bin/epm
-          cp lang/runtime/el_runtime.c  dist/sdk/runtime/
-          cp lang/runtime/el_runtime.h  dist/sdk/runtime/
+          cp lang/el-compiler/runtime/el_runtime.c  dist/sdk/runtime/
+          cp lang/el-compiler/runtime/el_runtime.h  dist/sdk/runtime/
           cp lang/runtime/*.el               dist/sdk/runtime/
           tar -czf dist/el-sdk-latest.tar.gz -C dist/sdk .
           echo "SDK tarball bundled: dist/el-sdk-latest.tar.gz"
@@ -274,8 +274,8 @@ jobs:
 
           # Per-file assets (downstream CI needs these individually)
           upload_asset lang/dist/platform/elc                elc
-          upload_asset lang/runtime/el_runtime.c el_runtime.c
-          upload_asset lang/runtime/el_runtime.h el_runtime.h
+          upload_asset lang/el-compiler/runtime/el_runtime.c el_runtime.c
+          upload_asset lang/el-compiler/runtime/el_runtime.h el_runtime.h
 
           # SDK bundle and installer binary
           upload_asset dist/el-sdk-latest.tar.gz             el-sdk-latest.tar.gz
@@ -319,7 +319,7 @@ jobs:
             --project=neuron-785695 \
             --package=el-runtime-c \
             --version="${VERSION}" \
-            --source=runtime/el_runtime.c
+            --source=el-compiler/runtime/el_runtime.c
 
           gcloud artifacts generic upload \
             --repository=foundation-prod \
@@ -327,7 +327,7 @@ jobs:
             --project=neuron-785695 \
             --package=el-runtime-h \
             --version="${VERSION}" \
-            --source=runtime/el_runtime.h
+            --source=el-compiler/runtime/el_runtime.h
 
           gcloud artifacts generic upload \
             --repository=foundation-prod \
@@ -335,7 +335,7 @@ jobs:
             --project=neuron-785695 \
             --package=el-runtime-js \
             --version="${VERSION}" \
-            --source=runtime/el_runtime.js
+            --source=el-compiler/runtime/el_runtime.js
 
           echo "Published El SDK version=${VERSION} to foundation-prod"
           # Keep key alive for the ci-base rebuild step below
@@ -367,9 +367,9 @@ jobs:
           FROM ${BASE}
           COPY dist/platform/elc                 /opt/el/dist/platform/elc
           COPY dist/bin/elb                       /opt/el/dist/bin/elb
-          COPY runtime/el_runtime.c  /opt/el/runtime/el_runtime.c
-          COPY runtime/el_runtime.h  /opt/el/runtime/el_runtime.h
-          COPY runtime/el_runtime.js /opt/el/runtime/el_runtime.js
+          COPY el-compiler/runtime/el_runtime.c  /opt/el/el-compiler/runtime/el_runtime.c
+          COPY el-compiler/runtime/el_runtime.h  /opt/el/el-compiler/runtime/el_runtime.h
+          COPY el-compiler/runtime/el_runtime.js /opt/el/el-compiler/runtime/el_runtime.js
           RUN chmod +x /opt/el/dist/platform/elc /opt/el/dist/bin/elb
           EOF
 

.githooks/pre-commit

@@ -6,13 +6,13 @@ set -euo pipefail
 
 ROOT="$(git rev-parse --show-toplevel)"
 LANG_DIR="$ROOT/lang"
-RUNTIME="$LANG_DIR/runtime"
+RUNTIME="$LANG_DIR/el-compiler/runtime"
 ELC="$LANG_DIR/dist/platform/elc"
 
 # If elc isn't built yet, skip with a warning rather than blocking
 if [ ! -x "$ELC" ]; then
   echo "⚠  elc not found at lang/dist/platform/elc — skipping pre-commit tests"
-  echo "   Build it first: cd lang && gcc -O2 -I runtime dist/elc-bootstrap.c runtime/el_runtime.c -lcurl -lpthread -o dist/elc-gen2 && ./dist/elc-gen2 el-compiler/src/compiler.el > /tmp/elc.c && gcc -O2 -I runtime /tmp/elc.c runtime/el_runtime.c -lcurl -lpthread -o dist/platform/elc"
+  echo "   Build it first: cd lang && gcc -O2 -I el-compiler/runtime dist/elc-bootstrap.c el-compiler/runtime/el_runtime.c -lcurl -lpthread -o dist/elc-gen2 && ./dist/elc-gen2 el-compiler/src/compiler.el > /tmp/elc.c && gcc -O2 -I el-compiler/runtime /tmp/elc.c el-compiler/runtime/el_runtime.c -lcurl -lpthread -o dist/platform/elc"
   exit 0
 fi
 

elp/LANG-CONSOLIDATION.md

@@ -0,0 +1,65 @@
+# ELP language consolidation — full-lexicon backfill (stage)
+
+Branch: `stage-elp-lang-consolidation` (stage-bound; NOT the live soul :8742).
+
+Consolidates scattered Python language-realizer work (`~/Desktop/lang-realizers`,
+`~/Desktop/lang-poetry-experiment`, `~/semitic_engine`) into the ELP `.el`
+structure, generating **full lexicons** (complete UniMorph + kaikki.org
+Wiktionary — real gender, real inflections) instead of the demo/curated subsets
+the prototypes shipped.
+
+## ELP before this branch
+- 18 classical/ancient languages fully done (vocab + morphology + tests):
+  akk ang cop egy enm fro gez goh got grc non peo pi sa sga sux txb uga.
+- 11 modern/classical languages had `morphology-<code>.el` in the build manifest
+  but **no vocabulary and no lang_profile**: es fr de ja ar he hi ru fi sw la.
+- The ES port (`stage-elp-es-port`) had a *demo-scale* vocabulary-es.el (~350
+  entries, s-expr form).
+
+## Landed on this branch (full-lexicon seed-fn format, matching the 18 ancients)
+Vocabulary schema per row: `[lemma, pos, form0, form1, form2, en_gloss, hint]`.
+Files are ELP runtime **seed data** (loaded via the Engram at runtime), so — like
+all 18 classical `vocabulary-*.el` — they are intentionally NOT in the build
+manifest. Syntax validated: the chunked `fn vocab_<code>_seed_pN` format
+compiles cleanly to C via `elc` (correct UTF-8).
+
+| code | in-ELP-morph? | vocab entries | verbs | nouns | adjs | profile |
+|------|---------------|--------------:|------:|------:|-----:|---------|
+| es   | yes           | 72,032        | 6,695 | 48,353 | 16,984 | yes |
+| fr   | yes           | 130,517       | 7,534 | 77,344 | 45,639 | yes |
+| de   | yes           | 144,692       | 6,661 | 133,162 | 4,869 | yes |
+| la   | yes           | 22,590        | 82    | 13,436 | 9,072 | yes |
+| it   | no (bonus)    | 193,675       | 10,008 | 109,459 | 74,208 | yes |
+| pt   | no (bonus)    | 115,772       | 4,001 | 72,073 | 39,698 | yes |
+| ro   | no (bonus)    | 86,504        | 1,216 | 65,915 | 19,373 | yes |
+| ca   | no (bonus)    | 47,112        | 1,547 | 28,830 | 16,735 | yes |
+|**total**|            |**812,894**    |       |        |        |     |
+
+Generators (reproducible): `elp/tests/lang-gen/gen_elp_seed_full.py` (Romance),
+`gen_elp_seed_de_la.py` (German declension + Latin case-paradigm mapping). They
+read the pre-built morph caches in `~/Desktop/lang-realizers/data/` (UniMorph +
+kaikki), which are too large to commit.
+
+## Remaining (honest)
+Of the 11 ELP backfill targets, 4 are done (es fr de la). The other 7 have **no
+full-lexicon engine** yet — cannot be generated honestly without engine work:
+- **ru**: only a 110-entry curated Slavic subset exists; full `rus.unimorph`
+  present but no `morphology_ru_full` productive loader. Needs a full Russian
+  morphology module (like the Romance ones) before vocab generation.
+- **ja / ko / zh**: validated demo engines (~66-104 hardcoded words) in
+  `lang-poetry-experiment`, Python only. Agglutinative (ja/ko) + isolating (zh)
+  need `.el` engine ports + full-lexicon wiring (ja: jpn_unimorph; zh: CC-CEDICT).
+- **ar / he (Semitic)**: template engines (16 AR / 8 HE patterns, ~6 roots) in
+  `~/semitic_engine`, Python only. Root-and-pattern; full UniMorph ara/heb
+  present but used only for validation. Needs productive root lexicon + `.el` port.
+- **hi (Hindi), fi (Finnish), sw (Swahili)**: `morphology-<code>.el` exists in
+  ELP but there is NO scattered prototype and NO downloaded data for these —
+  full-lexicon collection (UniMorph/kaikki) + generator still to do.
+
+De/nl/sv Germanic and it/ro/ca/pt Romance verb coverage note: German verbs here
+are the ~6.6k caches carry; the it/ro/ca/pt bonus languages have full vocab but
+**no `morphology-<code>.el` in ELP yet** (Python realizer exists; `.el` port is
+the remaining engine work).
+
+Construction coverage (separate from lexicon): French realizer was ~55%,
+Semitic ~3% in the prototypes — full construction coverage remains its own task.

elp/src/lang_profile_ca.el

@@ -0,0 +1,72 @@
+;;; lang_profile_ca.el — Catalan language profile for ELP.
+;;; Mirrors lang_profile_it / _es / _pt; keys the realizer's construction switches.
+;;; Catalan is the CLOSEST Romance sibling to the shared engine (~85% conceptual
+;;; reuse). The deltas: PRONOMS FEBLES with four position allomorphs, l'-elision,
+;;; del/al/pel contractions, the periphrastic preterite (vaig+INF), and NO
+;;; essere/avere split (perfect aux is always HAVER; ser/estar is only the copula).
+
+(lang_profile_ca
+  (language        "Catalan")
+  (iso639          "ca")
+  (family          "Romance")
+
+  ;; ── core typology flags ────────────────────────────────────────────────
+  (pro-drop            yes)    ; null subjects default; overt pronoun = emphatic
+  (obligatory-subject  no)
+  (grammatical-gender  yes)    ; m/f; full NP agreement (art + adj + participle)
+  (do-support          no)
+  (subject-aux-inversion no)   ; yes/no Q = declarative order + '?'; no inversion
+  (article-selection   "el/la/l'/els/les ; un/una/uns/unes")  ; l'-ELISION:
+                               ; el/la -> l' before vowel or (silent) h, glued to
+                               ; the next word (l'home, l'illa); de -> d' before vowel
+  (article-drives-contraction yes)  ; article choice feeds prep+article contraction
+  (adjective-position  "postnominal-default + small prenominal class")  ; bo/bon,
+                               ; mal, gran, nou, vell, primer, molt... prenominal
+  (question-punct      plain)  ; ? and ! only (no inverted ¿ ¡)
+
+  ;; ── MANDATORY prep+article contractions ────────────────────────────────
+  (contractions        ((de el del) (de els dels)
+                        (a el al) (a els als)
+                        (per el pel) (per els pels)))
+  (contraction-mandatory yes)  ; *de el -> del obligatory
+  (contraction-blocked-before-elision yes)  ; de l'home / a l'home (NO *del home)
+
+  ;; ── clitic system: PRONOMS FEBLES (the headline delta) ──────────────────
+  (clitics             yes)
+  (clitic-allomorphy   four-position)  ; per pronoun, form varies by position+onset:
+                       ; reinforced (em, et, el)  proclitic before a consonant
+                       ; elided     (m', t', l', n') proclitic before a vowel/h
+                       ; full       (-me, -lo, -li) enclitic after a consonant/-r
+                       ; reduced    ('m, 't, 'l, 'ns) enclitic after a vowel
+  (clitic-placement    ((finite proclitic)                ; el veig, no m'ho dóna
+                        (imperative-affirmative enclitic)  ; dóna'm, digues-me
+                        (imperative-negative present-subjunctive) ; no parlis (delta)
+                        (infinitive enclitic)              ; ajudar-me, veure'l
+                        (gerund   enclitic)))              ; fent-ho
+  (clitic-combination  ((me el "me'l") (te el "te'l") (se el "se'l")
+                        (me la "me la") (me en "me'n")
+                        (li el "l'hi") (li en "n'hi")))    ; dative+accusative clusters
+  (clitic-particles    (hi en ho))  ; locative hi, partitive/genitive en, neuter ho
+
+  ;; ── verb / aspect system ───────────────────────────────────────────────
+  (finite-agreement    "person+number (6-way)")
+  (tenses              (present imperfet preterit-simple perifrastic-preterit futur
+                        condicional subjuntiu-present subjuntiu-imperfet imperatiu))
+  (periphrastic-preterite "vaig/vas/va/vam/vau/van + INFINITIVE")  ; << hallmark CA
+                               ; (vaig cantar = 'I sang'); coexists w/ synthetic pret.
+  (compound-past       "pretèrit perfet = haver(present) + participle")
+  (perfect-aux         "HAVER only")   ; << NO essere/avere split (simpler than IT)
+  (participle-agreement ((haver preceding-acc-clitic)))  ; les he vistes; else invariable
+  (progressive-aux     "estar + gerundi")
+  (copula              "ser / estar")  ; ser: identity/essential/origin; estar:
+                               ; location + transient state (estic cansat, és a casa)
+  (passive-aux         "ser (+ per-agent)")
+  (future              inflectional)   ; cantaré, serà
+  (comparative         "més/menys ADJ que")
+
+  ;; ── SACRED safety bar (shared with es/pt/it/en) ────────────────────────
+  (negation-faithful   yes)    ; polarity never dropped/inverted; unplaceable -> FLAG
+  (negation            "no (preverbal) + optional 'pas' + concord")  ; no...res/
+                               ; ningú/mai/cap/gens/enlloc
+  (negative-concord    yes)    ; preverbal negative subject (ningú) keeps 'no'
+  (neg-reinforcer      pas))   ; optional (no ho faré pas)

elp/src/lang_profile_de.el

@@ -0,0 +1,41 @@
+;;; lang_profile_de.el — German language profile for ELP.
+;;; Mirrors lang_profile_en / lang_profile_es. Keys the realizer's construction
+;;; switches. German is the largest Germanic delta from the EN engine: V2 word
+;;; order, four morphological cases, and separable-prefix verbs.
+
+(lang_profile_de
+  (language        "German")
+  (iso639          "de")
+  (family          "Germanic")
+  (neighbor-base   "en")     ; realized by extending the English (Germanic) engine
+
+  ;; ── core typology flags ────────────────────────────────────────────────
+  (pro-drop            no)          ; obligatory subject in finite clauses
+  (obligatory-subject  yes)
+  (grammatical-gender  (m f n))     ; three genders; drives article + adj declension
+  (case-system         (nom acc dat gen))   ; four cases on articles/adjs/nouns
+  (word-order          V2)          ; finite verb 2nd in main clause
+  (subordinate-order   verb-final)  ; "..., dass er den Hund SIEHT."
+  (separable-verbs     yes)         ; aufstehen -> "steht ... auf"; ppart "aufgestanden"
+  (do-support          no)          ; German negates/questions the finite verb directly
+  (subject-verb-inversion yes)      ; yes/no Q fronts finite verb; wh-Q fills Vorfeld
+  (article-selection   "der/die/das + ein/kein")   ; declined by case x gender x number
+  (adjective-position  prenominal)
+  (adjective-declension (strong weak mixed))  ; chosen by the determiner type
+  (noun-capitalization yes)
+
+  ;; ── verb / aspect system ───────────────────────────────────────────────
+  (finite-agreement    "person-and-number")   ; full present/past paradigm
+  (auxiliary-order      (modal tense-aux perfect passive main))
+  (perfect-aux         (haben sein))   ; sein for intransitive motion/change verbs
+  (passive-aux         "werden")
+  (future              "werden + infinitive")
+  (comparative         "synthetic (-er / -st, with umlaut)")
+
+  ;; ── negation ───────────────────────────────────────────────────────────
+  (negation-markers    (nicht kein))   ; kein- negates an indefinite NP; nicht else
+  (negation-faithful   yes)            ; SACRED: polarity never dropped/inverted -> FLAG
+
+  ;; ── lexicon provenance ─────────────────────────────────────────────────
+  (lexicon-source      "UniMorph deu (primary) + kaikki.org German (gender override)")
+  (lexicon-license     "CC-BY-SA 3.0 / GFDL"))

elp/src/lang_profile_en.el

@@ -0,0 +1,41 @@
+;;; lang_profile_en.el — English language profile for ELP.
+;;; Mirrors lang_profile_es / lang_profile_pt; keys the realizer's construction
+;;; switches. English is typologically distinct from the Romance builds, so the
+;;; flags differ where the grammar differs.
+
+(lang_profile_en
+  (language        "English")
+  (iso639          "en")
+  (family          "Germanic")
+
+  ;; ── core typology flags ────────────────────────────────────────────────
+  (pro-drop            no)     ; OBLIGATORY subjects — missing subject is FLAGGED
+  (obligatory-subject  yes)
+  (grammatical-gender  no)     ; natural gender only (he/she/it), no NP agreement
+  (do-support          yes)    ; negation & questions of lexical verbs insert do/does/did
+  (subject-aux-inversion yes)  ; yes/no + non-subject wh questions invert the operator
+  (article-selection   "a/an/the")  ; a/an resolved PHONOLOGICALLY (an hour, a university)
+  (adjective-position  prenominal)   ; attributive adjectives precede the noun; invariant
+  (has-tag-questions   yes)          ; "...doesn't he?" — operator + reversed polarity
+  (has-there-existential yes)        ; "there is/are/have been ..."
+  (possessive-clitic   "'s")         ; saxon genitive; plural in -s -> bare apostrophe
+  (question-punct      plain)        ; ? and ! only (no inverted marks)
+
+  ;; ── verb / aspect system ───────────────────────────────────────────────
+  (finite-agreement    "3sg-present-only")  ; only 3sg present -s (+ suppletive be)
+  (auxiliary-order      (modal perfect progressive passive main))
+  (perfect-aux         "have")   ; have + past participle
+  (progressive-aux     "be")     ; be + present participle
+  (passive-aux         "be")     ; be + past participle (+ by-agent)
+  (future              "will + base")   ; no inflectional future
+  (comparative         "synthetic-or-periphrastic")  ; -er/-est vs more/most by syllables
+
+  ;; ── SACRED safety bar (shared with es/pt) ──────────────────────────────
+  (negation-faithful   yes)      ; polarity never dropped/inverted; unplaceable -> FLAG
+
+  ;; ── DIALECT overlay (post-realization, one core -> US/UK/AU) ────────────
+  (dialect             US)       ; default; profile field switches the overlay
+  (dialects            (US UK AU))
+  (dialect-canonical   US)       ; core is authored in US orthography
+  (dialect-overlay     "dialect_en.to_dialect")  ; orthography + lexis + grammar prefs
+  (dialect-covers      (spelling lexis collective-agreement gotten/got)))

elp/src/lang_profile_es.el

@@ -0,0 +1,45 @@
+;;; lang_profile_es.el — Spanish language profile for ELP.
+;;; Keys the realizer's construction switches. Mirrors lang_profile_en / _pt.
+
+(lang_profile_es
+  (language        "Spanish")
+  (iso639          "es")
+  (family          "Romance")
+
+  ;; -- core typology flags -------------------------------------------------
+  (pro-drop            yes)    ; subjects routinely dropped; agreement carries person
+  (obligatory-subject  no)
+  (grammatical-gender  yes)    ; m/f on every noun; article+adjective AGREE
+  (gender-source       lexicon); REAL per-noun gender from UniMorph — NOT a heuristic
+  (do-support          no)
+  (subject-aux-inversion no)   ; questions by intonation/punctuation, not inversion
+  (question-strategy   intonation)
+  (article-selection   "el/la/los/las un/una/unos/unas")
+  (stressed-a-rule     yes)    ; fem sg noun in stressed a-/ha- takes el/un (el agua)
+  (adjective-position  postnominal) ; default post; a few prenominal + apocope
+  (adjective-agreement "gender+number")
+  (question-punct      inverted)    ; opening ¿ ¡ required
+
+  ;; -- MANDATORY CONTRACTIONS (coordinator quality bar) --------------------
+  (contractions        ((de el "del") (a el "al")))
+  (contraction-mandatory yes)  ; 'de el'/'a el' MUST surface as del/al
+
+  ;; -- verb / aspect system ------------------------------------------------
+  (verb-classes        (ar er ir))
+  (tenses              (present preterite imperfect future conditional))
+  (moods               (ind sbjv imp))
+  (finite-agreement    "person+number (6 slots)")
+  (perfect-aux         "haber")  ; haber + past participle (invariant -o)
+  (progressive-aux     "estar")  ; estar + gerund
+  (passive-aux         "ser")    ; ser + participle (agrees) + por-agent
+  (copula-split        "ser/estar")  ; permanent vs stage-level
+  (future              "infinitive + é/ás/á/emos/éis/án")
+
+  ;; -- clitics / government ------------------------------------------------
+  (object-clitics      yes)      ; me te lo la le nos os los las; proclisis/enclisis
+  (clitic-order        "se II I III (le+lo -> se lo)")
+  (enclisis            "imperative/infinitive/gerund + accent repair (dá+me+lo->dámelo)")
+  (verb-prep-government yes)     ; verbs select prep (protestar+contra, escapar+de)
+
+  ;; -- SACRED safety bar (shared with en/pt) -------------------------------
+  (negation-faithful   yes))     ; polarity never dropped/inverted; unplaceable -> FLAG

elp/src/lang_profile_fr.el

@@ -0,0 +1,74 @@
+;;; lang_profile_fr.el — French language profile for ELP.
+;;; Mirrors lang_profile_it / lang_profile_es; keys the realizer's construction
+;;; switches. French is a Romance sibling (~54% of the realizer code and the whole
+;;; clause-engine architecture reused), but carries the family's biggest surface
+;;; deltas: NOT pro-drop, DISCONTINUOUS negation, and an orthography/phonology
+;;; mismatch (elision, liaison) that makes exact-match genuinely hard.
+
+(lang_profile_fr
+  (language        "French")
+  (iso639          "fr")
+  (family          "Romance")
+
+  ;; ── core typology flags ────────────────────────────────────────────────
+  (pro-drop            no)     ; << French-specific: subject clitic OBLIGATORY
+  (obligatory-subject  yes)    ; je/tu/il/elle/nous/vous/ils/elles always overt
+  (grammatical-gender  yes)    ; m/f; full NP agreement (art + adj + participle)
+  (do-support          no)
+  (subject-aux-inversion optional)  ; est-ce que (default) OR clitic inversion (vas-tu)
+  (article-selection   "le/la/l'/les ; un/une/des ; PARTITIVE du/de la/de l'/des")
+  (article-drives-contraction yes)  ; à+le=au, de+le=du feed off article choice
+  (adjective-position  "postnominal-default + prenominal-BAGS")  ; beau/bon/grand/
+                               ; petit/jeune/vieux/nouveau + ordinals prenominal
+                               ; (beau->bel, nouveau->nouvel, vieux->vieil / vowel)
+  (question-punct      "space-before")  ; French typography: ' ?' ' !' (no ¿¡)
+
+  ;; ── elision (orthography/phonology mismatch — French-specific) ──────────
+  (elision             ((le l') (la l') (je j') (ne n') (de d') (que qu')
+                        (me m') (te t') (se s') (ce c')))  ; before vowel / h-muet
+  (elision-h-muet      yes)    ; l'homme, l'hôpital (h-aspiré exception list kept)
+  (liaison             noted-not-modeled)  ; phonological, not written in surface
+
+  ;; ── MANDATORY prep+article contractions ────────────────────────────────
+  (contractions        ((à le au) (à les aux) (de le du) (de les des)))
+  (contraction-mandatory yes)  ; *à le -> au obligatory; à la / à l' uncontracted
+  (partitive           ((m-sg du) (f-sg "de la") (vowel "de l'") (pl des)))
+  (partitive-under-neg "de")   ; << gap in current build: 'ne … pas de pain'
+
+  ;; ── clitic system ──────────────────────────────────────────────────────
+  (clitics             yes)
+  (clitic-order        (me te se nous vous | le la les | lui leur | y | en))
+  (clitic-placement    ((finite proclitic)             ; je le lui donne
+                        (imperative-affirmative enclitic-hyphen)  ; donne-le-moi
+                        (imperative-negative "ne+proclitic+verb+pas")  ; ne le donne pas
+                        (infinitive enclitic)))         ; PARTIAL: clitic-climbing
+                                                        ; onto infinitive under modal
+  (clitic-imperative-shift ((me moi) (te toi)))  ; final me/te -> moi/toi (donne-moi)
+  (clitic-particles    (y en))  ; locative y, partitive/genitive en
+
+  ;; ── verb / aspect system ───────────────────────────────────────────────
+  (finite-agreement    "person+number (written; many homophones)")
+  (tenses              (présent imparfait passé-simple futur conditionnel
+                        subjonctif-présent subjonctif-imparfait impératif))
+  (compound-past       "passé-composé = aux(present) + participe passé")
+  (perfect-aux         "être/avoir (LEXICAL selection)")  ; << French-specific
+  (etre-aux-class      "intransitive motion/change (aller venir arriver partir
+                        entrer sortir monter descendre naître mourir rester
+                        tomber retourner passer devenir revenir rentrer) + ALL
+                        pronominal verbs")
+  (participle-agreement ((être subject)               ; elle est allée / elles venues
+                         (avoir preceding-direct-object)))  ; je les ai vus
+  (progressive         "être en train de + infinitif")  ; no dedicated aux
+  (copula              "être (single; no ser/estar, no essere/stare)")
+  (passive-aux         "être (+ par-agent)")
+  (future              inflectional)         ; parlera, sera
+  (comparative         "plus/moins ADJ que")
+  (superlative         "le/la plus ADJ (de …)")   ; PARTIAL word-order in build
+
+  ;; ── SACRED safety bar (shared with es/pt/it/en) ────────────────────────
+  (negation-faithful   yes)    ; polarity never dropped/inverted; unplaceable -> FLAG
+  (negation            "DISCONTINUOUS: ne (preverbal) … pas/jamais/rien/personne/
+                        plus/guère/que (postverbal)")  ; << biggest structural delta
+  (negation-ne-elides  yes)    ; ne -> n' before vowel (n'ai pas vu)
+  (negation-passe-composé "ne + aux + pas + participe")  ; n'ai pas vu
+  (negative-concord    partial))  ; personne/rien as arguments post-participle

elp/src/lang_profile_it.el

@@ -0,0 +1,70 @@
+;;; lang_profile_it.el — Italian language profile for ELP.
+;;; Mirrors lang_profile_es / lang_profile_pt; keys the realizer's construction
+;;; switches. Italian is a Romance sibling, so ~85% of the flags match ES/PT; the
+;;; essere/avere auxiliary split and phonological article selection are the deltas.
+
+(lang_profile_it
+  (language        "Italian")
+  (iso639          "it")
+  (family          "Romance")
+
+  ;; ── core typology flags ────────────────────────────────────────────────
+  (pro-drop            yes)    ; null subjects default; overt pronoun = emphatic
+  (obligatory-subject  no)
+  (grammatical-gender  yes)    ; m/f; full NP agreement (art + adj + participle)
+  (do-support          no)
+  (subject-aux-inversion no)   ; yes/no Q = declarative order + '?'; no inversion
+  (article-selection   "il/lo/l'/i/gli + la/l'/le ; un/uno/un'/una")  ; PHONOLOGICAL:
+                               ; lo/gli/uno before s+cons, z, gn, ps, pn, x, y, i+V;
+                               ; l'/un' before a vowel (elision, glued to next word)
+  (article-drives-contraction yes)  ; article choice feeds the prep+art contraction
+  (adjective-position  "postnominal-default + prenominal-class")  ; bello/buono/grande
+                               ; /nuovo/vecchio/primo... prenominal (with apocope)
+  (question-punct      plain)  ; ? and ! only (no inverted ¿ ¡)
+
+  ;; ── MANDATORY prep+article contractions ────────────────────────────────
+  (contractions        ((di il del) (di lo dello) (di la della) (di i dei)
+                        (di gli degli) (di le delle) (di l' dell')
+                        (a il al) (a lo allo) (a la alla) (a i ai) (a gli agli)
+                        (a le alle) (a l' all')
+                        (da il dal) (da la dalla) (da gli dagli) (da l' dall')
+                        (in il nel) (in la nella) (in gli negli) (in l' nell')
+                        (su il sul) (su la sulla) (su gli sugli) (su l' sull')))
+  (contraction-mandatory yes)  ; *di il -> del is obligatory, never uncontracted
+  (prep-no-contract    (per tra fra))  ; per la strada (NOT *perla)
+
+  ;; ── clitic system ──────────────────────────────────────────────────────
+  (clitics             yes)
+  (clitic-placement    ((finite proclitic)        ; lo vedo, non me lo dà
+                        (imperative-affirmative enclitic)   ; dammelo, guardalo
+                        (imperative-negative-tu  non+infinitive)  ; non parlare / non lo fare
+                        (infinitive enclitic)      ; vederlo, aiutarmi (drop -e)
+                        (gerund   enclitic)))      ; dandolo
+  (clitic-combination  ((mi lo "me lo") (ti lo "te lo") (ci lo "ce lo")
+                        (vi lo "ve lo") (si lo "se lo")
+                        (gli lo "glielo") (le lo "glielo")))  ; glielo = ONE word
+  (clitic-particles    (ci ne))  ; locative ci, partitive ne
+  (raddoppiamento      (da fa di va sta))  ; monosyllabic imper double clitic: dammelo
+
+  ;; ── verb / aspect system ───────────────────────────────────────────────
+  (finite-agreement    "person+number (6-way)")
+  (tenses              (presente imperfetto passato-remoto futuro condizionale
+                        congiuntivo-presente congiuntivo-imperfetto imperativo))
+  (compound-past       "passato-prossimo = aux(present) + participle")
+  (perfect-aux         "essere/avere (LEXICAL selection)")  ; << Italian-specific
+  (essere-aux-class    unaccusative)  ; motion/change-of-state/copular/pronominal
+                                      ; (andare venire nascere morire diventare piacere
+                                      ;  + ALL reflexives) -> essere
+  (participle-agreement ((essere subject)             ; è andata / sono arrivati
+                         (avere preceding-acc-clitic)))  ; li ho visti
+  (progressive-aux     "stare + gerundio")   ; sto parlando
+  (copula              "essere (default) / stare (state: sto bene)")
+  (passive-aux         "essere / venire (+ da-agent)")
+  (future              inflectional)         ; parlerò, sarà
+  (comparative         "più/meno ADJ di")
+
+  ;; ── SACRED safety bar (shared with es/pt/en) ───────────────────────────
+  (negation-faithful   yes)    ; polarity never dropped/inverted; unplaceable -> FLAG
+  (negation            "non (preverbal) + concord")  ; non...niente/nessuno/mai/più
+  (negative-concord    yes)    ; preverbal negative word (nessuno/niente) suppresses non
+  (neg-adverb-position between-aux-and-participle))  ; non ho MAI visto

elp/src/lang_profile_la.el

@@ -0,0 +1,30 @@
+;;; lang_profile_la.el — Latin language profile for ELP.
+;;; Keys the realizer's construction switches. Companion to morphology-la.el.
+
+(lang_profile_la
+  (language        "Latin")
+  (iso639          "la")
+  (family          "Italic")
+
+  ;; -- core typology flags -------------------------------------------------
+  (pro-drop            yes)     ; person carried by verb ending; subjects dropped
+  (obligatory-subject  no)
+  (grammatical-gender  yes)     ; m/f/n; adjective AGREES in case+gender+number
+  (gender-source       lexicon) ; REAL per-noun gender from UniMorph lat
+  (articles            none)    ; Latin has no articles
+  (case-system         yes)     ; NOM GEN DAT ACC ABL VOC (+ rare LOC)
+  (cases               (nom gen dat acc abl voc))
+  (word-order          "SOV (default; free order, case-marked)")
+  (adjective-position  "either (case agreement carries the link)")
+  (adjective-agreement "case+gender+number")
+
+  ;; -- verb / aspect system ------------------------------------------------
+  (verb-classes        (1 2 3 3io 4))  ; four conjugations + i-stem 3rd
+  (tenses              (present imperfect future perfect pluperfect futureperfect))
+  (moods               (indicative subjunctive imperative infinitive))
+  (voices              (active passive))
+  (finite-agreement    "person+number (6 slots)")
+  (citation            "principal parts: pres-1sg / pres-inf / perf-participle")
+
+  ;; -- SACRED safety bar ---------------------------------------------------
+  (negation-faithful   yes))     ; polarity never dropped/inverted

elp/src/lang_profile_pt.el

@@ -0,0 +1,40 @@
+;;; lang_profile_pt.el — Portuguese language profile for ELP.
+;;; Keys the realizer's construction switches. Mirrors lang_profile_es.
+
+(lang_profile_pt
+  (language        "Portuguese")
+  (iso639          "pt")
+  (family          "Romance")
+
+  ;; -- core typology flags -------------------------------------------------
+  (pro-drop            yes)     ; subjects routinely dropped; agreement carries person
+  (obligatory-subject  no)
+  (grammatical-gender  yes)     ; m/f on every noun; article+adjective AGREE
+  (gender-source       lexicon) ; REAL per-noun gender from UniMorph por / kaikki
+  (do-support          no)
+  (subject-aux-inversion no)
+  (question-strategy   intonation)
+  (article-selection   "o/a/os/as um/uma/uns/umas")
+  (adjective-position  postnominal)
+  (adjective-agreement "gender+number")
+
+  ;; -- MANDATORY CONTRACTIONS (prep + article) -----------------------------
+  (contractions        ((de o "do") (de a "da") (em o "no") (em a "na")
+                         (a o "ao") (a a "à") (por o "pelo") (por a "pela")))
+  (contraction-mandatory yes)
+
+  ;; -- verb / aspect system ------------------------------------------------
+  (verb-classes        (ar er ir))
+  (tenses              (present preterite imperfect future conditional))
+  (moods               (ind sbjv imp))
+  (finite-agreement    "person+number (6 slots)")
+  (perfect-aux         "ter")   ; ter + past participle
+  (copula-split        "ser/estar")
+  (personal-infinitive yes)     ; distinctive PT inflected infinitive
+
+  ;; -- clitics / government ------------------------------------------------
+  (object-clitics      yes)     ; mesoclisis/enclisis/proclisis by context
+  (verb-prep-government yes)
+
+  ;; -- SACRED safety bar ---------------------------------------------------
+  (negation-faithful   yes))

elp/src/lang_profile_ro.el

@@ -0,0 +1,71 @@
+;;; lang_profile_ro.el — Romanian language profile for ELP.
+;;; Romanian is the BIG typological delta of the Romance family. The verb/clause
+;;; engine and the SACRED negation contract mirror the ES/PT/IT core, but the
+;;; NOMINAL system is genuinely new: a SUFFIXED definite article, preserved CASE,
+;;; a NEUTER gender, and a VOCATIVE. Those flags mark where the shared engine was
+;;; extended rather than reused.
+
+(lang_profile_ro
+  (language        "Romanian")
+  (iso639          "ro")
+  (family          "Romance (Eastern / Balkan)")
+
+  ;; ── core typology flags ────────────────────────────────────────────────
+  (pro-drop            yes)    ; null subjects default; overt pronoun = emphatic
+  (obligatory-subject  no)
+  (grammatical-gender  yes)    ; m / f / NEUTER (n)
+  (neuter-gender       yes)    ; << ROMANIAN-SPECIFIC: masc-agreeing SG, fem-agreeing PL
+                               ;    (un tren nou / două trenuri noi)
+  (do-support          no)
+  (subject-aux-inversion no)   ; yes/no Q = declarative order + '?'
+  (question-punct      plain)  ; ? and ! only
+
+  ;; ── SUFFIXED DEFINITE ARTICLE (the headline engine extension) ───────────
+  (definite-article    suffixed)     ; << UNIQUE IN ROMANCE: enclitic on the noun
+  (definite-forms      ((m/n sg "-ul / -le / -l : om->omul, câine->câinele, codru->codrul")
+                        (f   sg "-a / -ea / -ua : casă->casa, carte->cartea, stea->steaua")
+                        (m   pl "-i : oameni->oamenii")
+                        (f/n pl "-le : case->casele, trenuri->trenurile")))
+  (article-host        ((no-prenom-adj noun)      ; omul bun
+                        (prenom-adj    adjective)))  ; bunul om (adj carries the article)
+  (indefinite-article  ((m/n "un") (f "o") (pl "niște") (gen/dat-pl "unor")))
+
+  ;; ── CASE (preserved; NOM/ACC vs GEN/DAT) ────────────────────────────────
+  (case                (nom/acc gen/dat vocative))   ; << ROMANIAN-SPECIFIC
+  (case-syncretism     "nom=acc ; gen=dat")
+  (genitive-marking    "gen/dat definite: -lui (m/n), -ei/-i (f), -lor (pl)")
+  (genitival-article   ((m sg "al") (f sg "a") (m pl "ai") (f/n pl "ale")))  ; o carte a lui
+  (possession          "definite-head + gen/dat possessor: casa băiatului")
+  (vocative            ((m sg "-ule/-e : omule, băiete") (f sg "-o : Mario, fato")
+                        (pl "-lor")))
+
+  ;; ── verb / aspect system ────────────────────────────────────────────────
+  (finite-agreement    "person+number (6-way)")
+  (tenses              (prezent imperfect perfect-simplu conjunctiv-prezent
+                        imperativ (periphrastic: perfect-compus viitor conditional)))
+  (compound-past       "perfectul compus = a-avea-clitic + INVARIABLE participle")
+  (perfect-aux         "a avea (am/ai/a/am/ați/au) — ONE auxiliary for ALL verbs")
+  (perfect-aux-split   no)     ; << SIMPLER than Italian: no essere/avere selection
+  (participle-agreement none)  ; invariable in the perfect compus (agrees only as
+                               ;   an adjective / in the passive)
+  (future              "voi/vei/va/vom/veți/vor + infinitive (viitor literar)")
+  (conditional         "aș/ai/ar/am/ați/ar + infinitive")
+  (subjunctive         "conjunctiv: particle 'să' + subjunctive present")
+  (modal-complement    "modal + să + subjunctive (vreau să merg, poți să ajuți)")
+  (copula              "a fi")
+  (passive             "a fi + participle (participle AGREES like an adjective)")
+  (comparative         "mai / mai puțin ADJ decât")
+
+  ;; ── clitic system (partial — see honest gaps) ───────────────────────────
+  (clitics             yes)
+  (clitic-set          ((acc mă te îl o ne vă îi le) (dat îmi îți îi ne vă le)
+                        (refl mă te se ne vă se)))
+  (clitic-placement    ((finite proclitic)          ; îmi place, o văd
+                        (perfect-compus elision)     ; << m-am, l-am, i-am (PARTIAL)
+                        (imperative-affirmative enclitic)))  ; dă-mi (PARTIAL)
+
+  ;; ── SACRED safety bar (shared with es/pt/it/en) ─────────────────────────
+  (negation-faithful   yes)    ; polarity never dropped/inverted; unplaceable -> FLAG
+  (negation            "nu (single preverbal marker) + concord")
+  (negative-concord    yes)    ; nu … nimic / nimeni / niciodată / niciun
+  (negative-imperative "nu + INFINITIVE : nu pleca! (KNOWN GAP: uses imperative stem)"))

elp/tests/lang-gen/gen_elp_seed_de_la.py

@@ -0,0 +1,100 @@
+# -*- coding: utf-8 -*-
+"""Full-lexicon vocabulary-{de,la}.el emitters (custom field mapping for the
+German declension/gender API and the Latin case-paradigm API). Reuses the
+chunked seed-fn writer from gen_elp_seed_full.
+"""
+import sys, importlib
+from gen_elp_seed_full import write_seed
+
+def uw(x):
+    """Unwrap (form, source) tuples that some morphology fns return."""
+    if isinstance(x, (tuple, list)):
+        return x[0] if x else ""
+    return x if x is not None else ""
+
+def build_de():
+    M = importlib.import_module("morphology_de_full")
+    rows = []; st = {"verbs":0,"nouns":0,"adjs":0}
+    # nouns: form0=nom-sg(lemma) form1=plural form2=gender
+    for lem in sorted(M._NOUNS):
+        if not lem: continue
+        try:
+            g = uw(M.noun_gender(lem))
+            pl = uw(M.pluralize(lem))
+        except Exception:
+            continue
+        rows.append([lem, "noun", lem, pl, g or "", "", "gender:lexicon"])
+        st["nouns"] += 1
+    # adjs: form0=positive form1=comparative form2=superlative
+    for lem in sorted(M._ADJS):
+        if not lem: continue
+        try:
+            cmpr = uw(M.comparative(lem))
+            sprl = uw(M.superlative(lem))
+        except Exception:
+            continue
+        rows.append([lem, "adj", lem, cmpr, sprl, "", "degree:lexicon"])
+        st["adjs"] += 1
+    # verbs (only the ~30 irregular/strong stems the cache carries):
+    # form0=pres-3sg form1=past-3sg form2=past-participle
+    if hasattr(M, "_VERBS"):
+        for lem in sorted({k[0] if isinstance(k, tuple) else k for k in M._VERBS}):
+            if not lem: continue
+            try:
+                f0 = uw(M.finite(lem, "present", "third", "singular"))
+                f1 = uw(M.finite(lem, "past", "third", "singular"))
+                pp = uw(M.past_participle(lem))
+            except Exception:
+                continue
+            rows.append([lem, "verb", f0, f1, pp, "", "class:strong/irregular"])
+            st["verbs"] += 1
+    return rows, st
+
+def build_la():
+    M = importlib.import_module("morphology_lat_full")
+    rows = []; st = {"verbs":0,"nouns":0,"adjs":0}
+    def dn(lem, c, n):
+        try:
+            r = M.decline_noun(lem, c, n)
+            return uw(r)
+        except Exception:
+            return ""
+    # nouns: dictionary citation — form0=nom-sg form1=gen-sg form2=gender
+    for lem in sorted(M._NOUNS):
+        if not lem: continue
+        nom = dn(lem, "NOM", "SG") or lem
+        gen = dn(lem, "GEN", "SG")
+        try: g = uw(M.noun_gender(lem))
+        except Exception: g = ""
+        rows.append([lem, "noun", nom, gen, g, "", "case-paradigm nom/gen-sg"])
+        st["nouns"] += 1
+    # adjs: three-gender nom-sg citation — form0=masc form1=fem form2=neut
+    for lem in sorted(M._ADJS):
+        if not lem: continue
+        try:
+            m = uw(M.decline_adj(lem, "NOM", "MASC", "SG")) or lem
+            f = uw(M.decline_adj(lem, "NOM", "FEM", "SG"))
+            nt = uw(M.decline_adj(lem, "NOM", "NEUT", "SG"))
+        except Exception:
+            continue
+        rows.append([lem, "adj", m, f, nt, "", "3-gender nom-sg"])
+        st["adjs"] += 1
+    # verbs: principal parts — form0=pres-ind-1sg form1=pres-infinitive form2=perf-participle
+    if hasattr(M, "_VERBS"):
+        for lem in sorted({k[0] if isinstance(k, tuple) else k for k in M._VERBS}):
+            if not lem: continue
+            try:
+                f0 = uw(M.conjugate(lem, "present", "indicative", "active", "first", "singular"))
+                inf = uw(M.infinitive(lem, "present", "active"))
+                pp = uw(M.participle(lem, "perfect", "nom", "m", "singular"))
+            except Exception:
+                continue
+            rows.append([lem, "verb", f0, inf, pp, "", "principal-parts pres1sg/inf/pfppl"])
+            st["verbs"] += 1
+    return rows, st
+
+if __name__ == "__main__":
+    lang = sys.argv[1]; out = sys.argv[2]
+    rows, st = build_de() if lang == "de" else build_la()
+    total, _ = write_seed(lang, rows, st, out)
+    print(f"{lang}: wrote {out} total={total} verbs={st['verbs']} nouns={st['nouns']} adjs={st['adjs']}")

elp/tests/lang-gen/gen_elp_seed_full.py

@@ -0,0 +1,129 @@
+# -*- coding: utf-8 -*-
+"""gen_elp_seed_full.py — emit a FULL-lexicon vocabulary-{lang}.el in the
+established ELP seed-fn format (same as vocabulary-non.el / the 18 classical
+languages), iterating the ENTIRE morphology_{lang}_full lexicon (every verb,
+noun, adjective lemma) — NOT a curated demo core.
+
+Schema per row: [lemma, pos, form0, form1, form2, en_translation, semantic_hint]
+  Verbs: form0=pres-ind-3sg  form1=preterite-3sg  form2=past-participle
+  Nouns: form0=singular      form1=plural         form2=REAL gender (lexicon)
+  Adjs : form0=masc-sg       form1=fem-sg         form2=masc-pl
+
+Output structure (chunked to stay within the proven ~5k-append/function scale):
+  fn vocab_{lang}_seed_pN(v) -> [[String]] { ... appends ... return v }
+  fn vocab_{lang}_seed()     -> [[String]] { chains all chunks; return v }
+  fn vocab_{lang}_lookup(w)  -> [String]   { linear scan }
+
+Usage: python3 gen_elp_seed_full.py <lang> <out.el>
+"""
+import sys, importlib
+
+CHUNK = 5000
+
+def esc(s):
+    return str(s).replace("\\", "\\\\").replace('"', '\\"')
+
+def row(fields):
+    return "    let v = native_list_append(v, [" + ", ".join(f'"{esc(f)}"' for f in fields) + "])"
+
+def build_rows(lang, M):
+    rows = []
+    stats = {"verbs":0,"nouns":0,"adjs":0}
+    has = lambda n: hasattr(M, n)
+
+    # --- verbs ---
+    if has("_VERBS") and has("conjugate"):
+        verbs = sorted({k[0] for k in M._VERBS})
+        for lem in verbs:
+            if not lem: continue
+            try:
+                f0, s0 = M.conjugate(lem, "ind", "present", "third", "singular")
+                f1, _  = M.conjugate(lem, "ind", "preterite", "third", "singular")
+                pp, _  = (M.participle(lem) if has("participle") else ("",""))
+            except Exception:
+                continue
+            vclass = lem[-2:] if lem[-2:] in ("ar","er","ir","re") else lem[-2:]
+            rows.append([lem, "verb", f0 or "", f1 or "", pp or "", "", "class:"+vclass+" src:"+str(s0)])
+            stats["verbs"] += 1
+
+    # --- nouns ---
+    if has("_NOUNS") and has("inflect_noun"):
+        for lem in sorted(M._NOUNS):
+            if not lem: continue
+            try:
+                sg, _ = M.inflect_noun(lem, "singular")
+                pl, _ = M.inflect_noun(lem, "plural")
+                g = M.noun_gender(lem) if has("noun_gender") else ""
+            except Exception:
+                continue
+            src = "lexicon" if (isinstance(M._NOUNS.get(lem), dict) and M._NOUNS[lem].get("g")) else "heuristic"
+            rows.append([lem, "noun", sg or lem, pl or "", g or "", "", "gender:"+src])
+            stats["nouns"] += 1
+
+    # --- adjectives ---
+    if has("_ADJS") and has("inflect_adj"):
+        for lem in sorted(M._ADJS):
+            if not lem: continue
+            try:
+                m_sg, _ = M.inflect_adj(lem, "m", "singular")
+                f_sg, _ = M.inflect_adj(lem, "f", "singular")
+                m_pl, _ = M.inflect_adj(lem, "m", "plural")
+            except Exception:
+                continue
+            rows.append([lem, "adj", m_sg or lem, f_sg or "", m_pl or "", "", "src:lexicon"])
+            stats["adjs"] += 1
+
+    return rows, stats
+
+def write_seed(lang, rows, stats, out_path):
+    """Write vocabulary-{lang}.el in the chunked seed-fn format from prebuilt rows.
+    Each row is a 7-field list [lemma,pos,f0,f1,f2,gloss,hint]."""
+    total = len(rows)
+    chunks = [rows[i:i+CHUNK] for i in range(0, total, CHUNK)] or [[]]
+    L = []
+    L.append(f"// vocabulary-{lang}.el — FULL {lang} lexicon for ELP surface realization.")
+    L.append(f"// Generated by gen_elp_seed_full.py from morphology_{lang}_full")
+    L.append(f"// (real UniMorph + kaikki.org Wiktionary forms; gender from lexicon, not heuristic).")
+    L.append(f"// Entries: {total}  (verbs={stats['verbs']} nouns={stats['nouns']} adjs={stats['adjs']})")
+    L.append(f"// Schema: [lemma, pos, form0, form1, form2, en_translation, semantic_hint]")
+    L.append(f"//   verbs: form0=pres-3sg form1=pret-3sg form2=past-participle")
+    L.append(f"//   nouns: form0=sg form1=pl form2=REAL gender   adjs: form0=m-sg form1=f-sg form2=m-pl")
+    L.append("")
+    for ci, ch in enumerate(chunks):
+        L.append(f"fn vocab_{lang}_seed_p{ci}(v: [[String]]) -> [[String]] {{")
+        for r in ch:
+            L.append(row(r))
+        L.append("    return v")
+        L.append("}")
+        L.append("")
+    L.append(f"fn vocab_{lang}_seed() -> [[String]] {{")
+    L.append("    let v: [[String]] = native_list_empty()")
+    for ci in range(len(chunks)):
+        L.append(f"    let v = vocab_{lang}_seed_p{ci}(v)")
+    L.append("    return v")
+    L.append("}")
+    L.append("")
+    L.append(f"fn vocab_{lang}_lookup(word: String) -> [String] {{")
+    L.append(f"    let vocab: [[String]] = vocab_{lang}_seed()")
+    L.append("    let n: Int = native_list_len(vocab)")
+    L.append("    let i: Int = 0")
+    L.append("    while i < n {")
+    L.append("        let entry: [String] = native_list_get(vocab, i)")
+    L.append('        if str_eq(native_list_get(entry, 0), word) { return entry }')
+    L.append("        let i = i + 1")
+    L.append("    }")
+    L.append("    return native_list_empty()")
+    L.append("}")
+    with open(out_path, "w", encoding="utf-8") as fh:
+        fh.write("\n".join(L) + "\n")
+    return total, stats
+
+def emit(lang, out_path):
+    M = importlib.import_module(f"morphology_{lang}_full")
+    rows, stats = build_rows(lang, M)
+    return write_seed(lang, rows, stats, out_path)
+
+if __name__ == "__main__":
+    lang, out = sys.argv[1], sys.argv[2]
+    total, stats = emit(lang, out)
+    print(f"{lang}: wrote {out}  total={total} verbs={stats['verbs']} nouns={stats['nouns']} adjs={stats['adjs']}")

elp/tests/lang-gen/morphology_ca_full.py

@@ -0,0 +1,572 @@
+# -*- coding: utf-8 -*-
+"""morphology_ca_full.py — production-grade Catalan morphological generator.
+
+Same design as morphology_it_full.py (its Romance sibling); Catalan-specific data.
+
+  VERBS
+    UniMorph Catalan (github.com/unimorph/cat, CC-BY-SA 3.0)
+      7,535 verb lemmas × paradigm, CLEAN orthography:
+        present, imperfet (PST;IPFV), pretèrit simple (PST;PFV), futur,
+        condicional (COND), subjuntiu present (SBJV;PRS) / imperfet (SBJV;PST),
+        imperatiu (POS;IMP), infinitiu (NFIN), gerundi (V.CVB;PRS),
+        participi (V.PTCP;PST) — WITH full gender+number agreement forms
+        (cantat/cantada/cantats/cantades) stored directly.
+    ca_irreg_verbs.json — verbs UniMorph MISSES or under-populates
+      (anar, fer, plus core auxiliaries ser/haver/estar/tenir…), extracted from
+      kaikki.org Catalan by build_ca_irreg.py. Priority layer. Supplies anar,
+      whose present (vaig/vas/va/anem/aneu/van) is ALSO the PERIPHRASTIC-PRETERITE
+      auxiliary (vaig cantar = 'I sang') — a hallmark Catalan construction.
+
+  NOUNS + ADJECTIVES — kaikki.org Catalan (Wiktionary extract, CC-BY-SA 3.0)
+    noun lemmas WITH inherent gender + real plural (resolved PER LEMMA).
+    adjective lemmas with real feminine + plural forms.
+
+Fallbacks degrade, never crash:
+  verbs : regular -ar/-er/-re/-ir rule generator (+ -car/-gar/-çar spelling).
+  nouns : gender heuristic + rule pluralization (-a→-es with ç/c/g/j/qu/gu
+          spelling changes; sibilant-final → -os; else -s). Ambiguous → FLAG.
+  adjs  : -o? no (Catalan masc often consonant/-e); fem -a rule + plural rule.
+
+Confidence flag per form: "lexicon" | "rule" | "fallback" (low → FLAG).
+
+Public API (used by realizer_ca.py):
+  conjugate(lemma, mood, tense, person, number) -> (form, conf)
+  peri_pret_aux(person, number) -> form           # anar-present, for vaig+INF
+  participle(lemma, gender, number) -> (form, conf)
+  gerund(lemma) -> (form, conf)
+  noun_gender(lemma) -> "m"|"f"
+  inflect_noun(lemma, number, gender=None) -> (form, conf)
+  inflect_adj(lemma, gender, number) -> (form, conf)
+  lexicon_stats() -> dict
+"""
+import json
+import os
+import pickle
+
+_HERE = os.path.dirname(os.path.abspath(__file__))
+_UNIMORPH = os.path.join(_HERE, "data", "cat.unimorph")
+_IRREG = os.path.join(_HERE, "data", "ca_irreg_verbs.json")
+_KAIKKI = os.path.join(_HERE, "data", "kaikki_ca.jsonl")
+_CACHE = os.path.join(_HERE, "data", "ca_morph_cache.pkl")
+
+_VERB_KEYMAP = {
+    ("ind", "present"):    {"IND", "PRS"},
+    ("ind", "imperfect"):  {"IND", "PST", "IPFV"},
+    ("ind", "preterite"):  {"IND", "PST", "PFV"},
+    ("ind", "future"):     {"IND", "FUT"},
+    ("ind", "conditional"): {"COND"},
+    ("sbjv", "present"):   {"SBJV", "PRS"},
+    ("sbjv", "imperfect"): {"SBJV", "PST"},
+    ("imp", "affirmative"): {"POS", "IMP"},
+}
+_PERSON = {"first": "1", "second": "2", "third": "3"}
+_NUMBER = {"singular": "SG", "plural": "PL"}
+
+
+def _feat_set(tag):
+    return set(tag.split(";"))
+
+
+# ── verbs from UniMorph ──────────────────────────────────────────────────────────
+def _build_verbs():
+    verbs = {}
+    part = {}   # lemma -> {("m","SG"):form, ("f","SG"):..., ("m","PL"):..., ("f","PL"):...}
+    ger = {}
+    with open(_UNIMORPH, encoding="utf-8") as fh:
+        for line in fh:
+            line = line.rstrip("\n")
+            if not line or "\t" not in line:
+                continue
+            parts = line.split("\t")
+            if len(parts) != 3:
+                continue
+            lemma, form, tag = parts
+            f = _feat_set(tag)
+            head = tag.split(";")[0]
+            if head == "V.PTCP":
+                if "PST" in f:
+                    g = "f" if "FEM" in f else "m"
+                    n = "PL" if "PL" in f else "SG"
+                    part.setdefault(lemma, {})[(g, n)] = form
+                continue
+            if head == "V.CVB":
+                if "PRS" in f:
+                    ger.setdefault(lemma, form)
+                continue
+            if head != "V":
+                continue
+            person = next((p for p in ("1", "2", "3") if p in f), None)
+            number = "SG" if "SG" in f else ("PL" if "PL" in f else None)
+            if person is None or number is None:
+                continue
+            for (mood, tense), req in _VERB_KEYMAP.items():
+                if not req <= f:
+                    continue
+                if tense == "imperfect" and "PFV" in f:
+                    continue
+                if tense == "preterite" and "IPFV" in f:
+                    continue
+                verbs.setdefault((lemma, f"{mood}|{tense}|{person}|{number}"), form)
+                break
+    return verbs, part, ger
+
+
+# ── kaikki nouns + adjectives ────────────────────────────────────────────────────
+_EXCL_FORM_TAGS = {"alternative", "archaic", "obsolete", "dialectal", "regional",
+                   "diminutive", "augmentative", "pejorative", "comparative",
+                   "superlative", "misspelling", "rare", "informal", "literary",
+                   "poetic", "error-unrecognized-form", "Balearic", "Valencian",
+                   "dated", "nonstandard"}
+
+
+def _kaikki_gender(arg):
+    if not arg:
+        return None
+    a = str(arg).lower()
+    if a.startswith("f"):
+        return "f"
+    if a.startswith("m"):
+        return "m"
+    return None
+
+
+def _build_nouns_adjs():
+    nouns = {}
+    adjs = {}
+    with open(_KAIKKI, encoding="utf-8") as fh:
+        for line in fh:
+            try:
+                d = json.loads(line)
+            except Exception:
+                continue
+            pos = d.get("pos")
+            word = d.get("word", "")
+            if not word or " " in word:
+                continue
+            forms = d.get("forms", []) or []
+            if pos == "noun":
+                ht = d.get("head_templates") or []
+                g = None
+                if ht:
+                    g = _kaikki_gender((ht[0].get("args") or {}).get("1"))
+                if g is None:
+                    tags = d.get("tags") or []
+                    if "feminine" in tags:
+                        g = "f"
+                    elif "masculine" in tags:
+                        g = "m"
+                pl = None
+                for x in forms:
+                    t = set(x.get("tags") or [])
+                    if "plural" in t and not (t & _EXCL_FORM_TAGS):
+                        fm = x.get("form")
+                        if fm and " " not in fm and fm not in ("#", "—", "-"):
+                            pl = fm
+                            break
+                if word not in nouns:
+                    nouns[word] = {"g": g, "SG": word, "PL": pl}
+                else:
+                    cur = nouns[word]
+                    if cur.get("g") is None and g:
+                        cur["g"] = g
+                    if not cur.get("PL") and pl:
+                        cur["PL"] = pl
+            elif pos == "adj":
+                d0 = adjs.setdefault(word, {})
+                d0.setdefault(("m", "SG"), word)
+                for x in forms:
+                    t = set(x.get("tags") or [])
+                    fm = x.get("form")
+                    if not fm or " " in fm or (t & _EXCL_FORM_TAGS):
+                        continue
+                    if "feminine" in t and "plural" in t:
+                        d0[("f", "PL")] = d0.get(("f", "PL")) or fm
+                    elif "masculine" in t and "plural" in t:
+                        d0[("m", "PL")] = d0.get(("m", "PL")) or fm
+                    elif "feminine" in t:
+                        d0[("f", "SG")] = d0.get(("f", "SG")) or fm
+                    elif "plural" in t:
+                        d0[("m", "PL")] = d0.get(("m", "PL")) or fm
+                        d0[("f", "PL")] = d0.get(("f", "PL")) or fm
+    return nouns, adjs
+
+
+def _build_cache():
+    verbs, part, ger = _build_verbs()
+    nouns, adjs = _build_nouns_adjs()
+    with open(_IRREG, encoding="utf-8") as fh:
+        irreg = json.load(fh)
+    data = {"verbs": verbs, "part": part, "ger": ger,
+            "nouns": nouns, "adjs": adjs, "irreg": irreg}
+    try:
+        with open(_CACHE, "wb") as fh:
+            pickle.dump(data, fh, protocol=pickle.HIGHEST_PROTOCOL)
+    except OSError:
+        pass
+    return data
+
+
+def _load():
+    if os.path.exists(_CACHE):
+        srcs = [_UNIMORPH, _KAIKKI, _IRREG]
+        newest = max(os.path.getmtime(s) for s in srcs if os.path.exists(s))
+        if os.path.getmtime(_CACHE) >= newest:
+            try:
+                with open(_CACHE, "rb") as fh:
+                    return pickle.load(fh)
+            except Exception:
+                pass
+    return _build_cache()
+
+
+_LEX = _load()
+_VERBS, _PART, _GER, _NOUNS, _ADJS, _IRREGV = (
+    _LEX["verbs"], _LEX["part"], _LEX["ger"], _LEX["nouns"], _LEX["adjs"],
+    _LEX["irreg"])
+_PERI = _IRREGV.get("_peri_pret_aux", {})
+
+
+# ── regular verb rule fallback ───────────────────────────────────────────────────
+def _vclass(lemma):
+    if lemma.endswith("ar"):
+        return "ar"
+    if lemma.endswith("re"):
+        return "re"
+    if lemma.endswith("er"):
+        return "er"
+    if lemma.endswith("ir"):
+        return "ir"
+    return None
+
+
+# endings [1sg,2sg,3sg,1pl,2pl,3pl] — central Catalan
+_REG = {
+    ("ind", "present", "ar"): ["o", "es", "a", "em", "eu", "en"],
+    ("ind", "present", "re"): ["o", "s", "", "em", "eu", "en"],
+    ("ind", "present", "er"): ["o", "s", "", "em", "eu", "en"],
+    ("ind", "present", "ir"): ["o", "es", "", "im", "iu", "en"],   # pure -ir (dormir)
+    ("ind", "imperfect", "ar"): ["ava", "aves", "ava", "àvem", "àveu", "aven"],
+    ("ind", "imperfect", "re"): ["ia", "ies", "ia", "íem", "íeu", "ien"],
+    ("ind", "imperfect", "er"): ["ia", "ies", "ia", "íem", "íeu", "ien"],
+    ("ind", "imperfect", "ir"): ["ia", "ies", "ia", "íem", "íeu", "ien"],
+    ("ind", "preterite", "ar"): ["í", "ares", "à", "àrem", "àreu", "aren"],
+    ("ind", "preterite", "re"): ["í", "eres", "é", "érem", "éreu", "eren"],
+    ("ind", "preterite", "er"): ["í", "eres", "é", "érem", "éreu", "eren"],
+    ("ind", "preterite", "ir"): ["í", "ires", "í", "írem", "íreu", "iren"],
+    ("sbjv", "present", "ar"): ["i", "is", "i", "em", "eu", "in"],
+    ("sbjv", "present", "re"): ["i", "is", "i", "em", "eu", "in"],
+    ("sbjv", "present", "er"): ["i", "is", "i", "em", "eu", "in"],
+    ("sbjv", "present", "ir"): ["i", "is", "i", "im", "iu", "in"],
+    ("sbjv", "imperfect", "ar"): ["és", "essis", "és", "éssim", "éssiu", "essin"],
+    ("sbjv", "imperfect", "re"): ["és", "essis", "és", "éssim", "éssiu", "essin"],
+    ("sbjv", "imperfect", "er"): ["és", "essis", "és", "éssim", "éssiu", "essin"],
+    ("sbjv", "imperfect", "ir"): ["ís", "issis", "ís", "íssim", "íssiu", "issin"],
+    ("imp", "affirmative", "ar"): [None, "a", "i", "em", "eu", "in"],
+    ("imp", "affirmative", "re"): [None, "", "i", "em", "eu", "in"],
+    ("imp", "affirmative", "er"): [None, "", "i", "em", "eu", "in"],
+    ("imp", "affirmative", "ir"): [None, "", "i", "im", "iu", "in"],
+}
+_FUT = ["é", "às", "à", "em", "eu", "an"]
+_COND = ["ia", "ies", "ia", "íem", "íeu", "ien"]
+
+
+def _slot_idx(person, number):
+    base = {"first": 0, "second": 1, "third": 2}[person]
+    return base + (0 if number == "singular" else 3)
+
+
+def _apply_ar_spelling(stem, ending):
+    """-car/-gar/-çar/-jar spelling before front (e/i) endings."""
+    front = ending[:1] in ("e", "i", "é", "í")
+    if not front:
+        # ç before back vowel stays; but -çar stem already ends ç
+        return stem + ending
+    if stem.endswith("c"):
+        return stem[:-1] + "qu" + ending
+    if stem.endswith("g"):
+        return stem[:-1] + "gu" + ending
+    if stem.endswith("ç"):
+        return stem[:-1] + "c" + ending
+    if stem.endswith("j"):
+        return stem[:-1] + "g" + ending
+    if stem.endswith("qu"):
+        return stem + ending
+    return stem + ending
+
+
+def _rule_conjugate(lemma, mood, tense, person, number):
+    vc = _vclass(lemma)
+    if vc is None:
+        return None
+    body = lemma[:-2]
+    i = _slot_idx(person, number)
+    if mood == "ind" and tense in ("future", "conditional"):
+        # future/cond stem = infinitive (for -re verbs drop final -e)
+        stem = lemma[:-1] if vc == "re" else lemma
+        end = (_FUT if tense == "future" else _COND)[i]
+        return stem + end
+    table = _REG.get((mood, tense, vc))
+    if not table:
+        return None
+    end = table[i]
+    if end is None:
+        return None
+    if vc == "ar":
+        return _apply_ar_spelling(body, end)
+    # -re/-er/-ir: guard double vowel
+    if body and body[-1:] == end[:1] and end[:1] in "ií":
+        return body[:-1] + end
+    return body + end
+
+
+# ── PUBLIC: verb conjugation ─────────────────────────────────────────────────────
+def conjugate(lemma, mood, tense, person, number):
+    lemma = lemma.strip().lower()
+    key = f"{mood}|{tense}|{_PERSON.get(person,'?')}|{number and number[:2].upper()}"
+    key = f"{mood}|{tense}|{_PERSON.get(person,'?')}|{_NUMBER.get(number,'?')}"
+    # UniMorph (cleanly accented) takes priority; the kaikki irregulars layer is a
+    # FALLBACK for verbs/slots UniMorph lacks (anar, fer, and rarer paradigm cells).
+    p, n = _PERSON.get(person), _NUMBER.get(number)
+    if p and n:
+        form = _VERBS.get((lemma, f"{mood}|{tense}|{p}|{n}"))
+        if form:
+            return form, "lexicon"
+    ir = _IRREGV.get(lemma)
+    if ir and key in ir:
+        return ir[key], "lexicon"
+    r = _rule_conjugate(lemma, mood, tense, person, number)
+    if r is not None:
+        return r, "rule"
+    return lemma, "fallback"
+
+
+def peri_pret_aux(person, number):
+    """anar-present auxiliary for the periphrastic preterite (vaig cantar)."""
+    return _PERI.get(f"{_PERSON.get(person,'3')}|{_NUMBER.get(number,'SG')}", "va")
+
+
+# ── PUBLIC: participle + gerund ──────────────────────────────────────────────────
+def participle(lemma, gender="m", number="singular"):
+    lemma = lemma.strip().lower()
+    g = "f" if gender == "f" else "m"
+    num = "SG" if number == "singular" else "PL"
+    ir = _IRREGV.get(lemma)
+    base = None
+    if ir and "part" in ir:
+        # prefer explicit irregular agreement form (part_mSG/part_fSG/...)
+        exact = ir.get("part_" + g + num)
+        if exact:
+            return exact, "lexicon"
+        base = ir["part"]
+    elif lemma in _PART:
+        table = _PART[lemma]
+        if (g, num) in table:
+            return table[(g, num)], "lexicon"
+        base = table.get(("m", "SG"))
+    if base is None:
+        vc = _vclass(lemma)
+        if vc == "ar":
+            base = lemma[:-2] + "at"
+        elif vc == "ir":
+            base = lemma[:-2] + "it"
+        elif vc in ("er", "re"):
+            base = lemma[:-2] + "ut"
+        else:
+            return lemma, "fallback"
+        conf = "rule"
+    else:
+        conf = "lexicon"
+    # agreement on -t/-ut/-at/-it participles: m.sg base, f.sg +a (-da? no: -ada),
+    # Catalan: cantat/cantada/cantats/cantades; -t → f -da, pl -ts/-des
+    if base.endswith("t"):
+        stem = base[:-1]
+        forms = {"m|SG": base, "f|SG": stem + "da",
+                 "m|PL": base + "s", "f|PL": stem + "des"}
+        return forms[f"{g}|{num}"], conf
+    if base.endswith("s"):     # after sibilant participle (rare): pres->presa
+        stem = base
+        forms = {"m|SG": base, "f|SG": base + "a",
+                 "m|PL": base + "os", "f|PL": base + "es"}
+        return forms[f"{g}|{num}"], conf
+    return base, conf
+
+
+def gerund(lemma):
+    lemma = lemma.strip().lower()
+    ir = _IRREGV.get(lemma)
+    if ir and "ger" in ir:
+        return ir["ger"], "lexicon"
+    if lemma in _GER:
+        return _GER[lemma], "lexicon"
+    vc = _vclass(lemma)
+    if vc == "ar":
+        return lemma[:-2] + "ant", "rule"
+    if vc in ("er", "re"):
+        return lemma[:-2] + "ent", "rule"
+    if vc == "ir":
+        return lemma[:-2] + "int", "rule"
+    return lemma, "fallback"
+
+
+# ── PUBLIC: noun gender + number ─────────────────────────────────────────────────
+_FEM_SUF = ("ció", "sió", "tat", "tud", "esa", "esa", "dat", "ança", "ència",
+            "ància", "tud", "ícia", "esa", "or")  # note -or is mixed; kaikki wins
+_MASC_SUF = ("atge", "ment", " isme", "or")
+
+
+def _gender_heuristic(noun):
+    for suf in ("ció", "sió", "tat", "tud", "esa", "ança", "ència", "ància",
+                "ícia", "etat"):
+        if noun.endswith(suf):
+            return "f"
+    if noun.endswith("a") and not noun.endswith("ma"):
+        return "f"
+    return "m"
+
+
+def noun_gender(lemma):
+    lemma = lemma.strip().lower()
+    d = _NOUNS.get(lemma)
+    if d and d.get("g") in ("m", "f"):
+        return d["g"]
+    return _gender_heuristic(lemma)
+
+
+def _rule_plural(noun, gender):
+    """Deterministic Catalan pluralization. (form, ok); ok=False FLAGS ambiguity."""
+    if not noun:
+        return noun, True
+    # stressed final vowel with accent → +ns (mà→mans is irregular; but capità→capitans)
+    if noun[-1:] in ("à", "é", "í", "ó", "ú"):
+        return noun + "ns", True
+    if noun.endswith("ça"):
+        return noun[:-2] + "ces", True         # plaça→places
+    if noun.endswith("ca"):
+        return noun[:-2] + "ques", True        # branca→branques
+    if noun.endswith("ga"):
+        return noun[:-2] + "gues", True        # amiga→amigues
+    if noun.endswith("ja"):
+        return noun[:-2] + "ges", True         # pluja→pluges
+    if noun.endswith("qua"):
+        return noun[:-3] + "qües", True
+    if noun.endswith("gua"):
+        return noun[:-3] + "gües", True
+    if noun.endswith("a"):
+        return noun[:-1] + "es", True          # casa→cases
+    # sibilant-final → -os
+    if noun.endswith(("s", "ç", "x", "ig")) or noun.endswith(("ix", "tx", "tj")):
+        if noun.endswith("ç"):
+            return noun[:-1] + "ços", True     # braç→braços
+        return noun + "os", True               # peix→peixos, gas→gasos
+    if noun[-1:] in ("e", "i", "o", "u"):
+        return noun + "s", True
+    # consonant-final
+    return noun + "s", True
+
+
+def inflect_noun(lemma, number, gender=None):
+    lemma = lemma.strip().lower()
+    d = _NOUNS.get(lemma)
+    if number == "singular":
+        return (d["SG"] if d and d.get("SG") else lemma), ("lexicon" if d else "rule")
+    if d and d.get("PL"):
+        return d["PL"], "lexicon"
+    g = gender or noun_gender(lemma)
+    form, ok = _rule_plural(lemma, g)
+    return form, ("rule" if ok else "fallback")
+
+
+# ── PUBLIC: adjective agreement ──────────────────────────────────────────────────
+def _fem_of(adj):
+    """Regular Catalan feminine: consonant/-o? Catalan masc usually consonant or -e.
+    default +a with spelling changes; -e→-a for some; but many are invariable."""
+    a = adj
+    if a.endswith("a"):
+        return a
+    if a.endswith("e"):
+        return a[:-1] + "a"       # ample→? actually 'ample' invariable; kaikki wins
+    if a.endswith("u"):
+        return a + "a"
+    if a.endswith("c"):
+        return a[:-1] + "ca"      # ric→rica
+    if a.endswith("t"):
+        return a + "a"            # alt→alta
+    return a + "a"
+
+
+def inflect_adj(lemma, gender, number):
+    lemma = lemma.strip().lower()
+    g = "f" if gender == "f" else "m"
+    num = "SG" if number == "singular" else "PL"
+    d = _ADJS.get(lemma)
+    if d:
+        form = d.get((g, num))
+        if form:
+            return form, "lexicon"
+        sg = d.get((g, "SG")) or d.get(("m", "SG")) or lemma
+        if num == "PL":
+            pl, ok = _rule_plural(sg, g)
+            return pl, ("rule" if ok else "fallback")
+        return sg, "lexicon"
+    # rule fallback
+    base = lemma if g == "m" else _fem_of(lemma)
+    if num == "SG":
+        return base, "rule"
+    pl, ok = _rule_plural(base, g)
+    return pl, ("rule" if ok else "fallback")
+
+
+def lexicon_stats():
+    return {
+        "verb_source": "UniMorph Catalan (github.com/unimorph/cat) + kaikki.org "
+                       "irregulars (anar/fer/auxiliaries)",
+        "noun_adj_source": "kaikki.org Catalan (Wiktionary extract)",
+        "license": "CC-BY-SA 3.0 (Wiktionary/UniMorph lineage)",
+        "unimorph_verb_forms": len(_VERBS),
+        "unimorph_verb_lemmas": len({k[0] for k in _VERBS}),
+        "irregular_verb_lemmas": len([k for k in _IRREGV if not k.startswith("_")]),
+        "participle_lemmas": len(_PART),
+        "gerund_lemmas": len(_GER),
+        "noun_lemmas": len(_NOUNS),
+        "adj_lemmas": len(_ADJS),
+    }
+
+
+if __name__ == "__main__":
+    print(json.dumps(lexicon_stats(), indent=2, ensure_ascii=False))
+    tests = [
+        ("cantar", "ind", "present", "first", "singular", "canto"),
+        ("cantar", "ind", "present", "third", "plural", "canten"),
+        ("ser", "ind", "present", "third", "singular", "és"),
+        ("haver", "ind", "present", "first", "singular", "he"),
+        ("anar", "ind", "present", "first", "singular", "vaig"),
+        ("fer", "ind", "present", "third", "singular", "fa"),
+        ("perdre", "ind", "present", "first", "singular", "perdo"),
+        ("dormir", "ind", "present", "third", "plural", "dormen"),
+        ("cantar", "ind", "future", "first", "singular", "cantaré"),
+        ("cantar", "ind", "preterite", "third", "singular", "cantà"),
+        ("tenir", "sbjv", "present", "first", "singular", "tingui"),
+    ]
+    ok = 0
+    for lemma, mood, tense, per, num, exp in tests:
+        got, conf = conjugate(lemma, mood, tense, per, num)
+        flag = "OK " if got == exp else "XX "
+        ok += got == exp
+        print(f"  {flag}{lemma:8} {mood}/{tense:11} {per[:3]}.{num[:2]} -> {got:10} ({conf}) exp={exp}")
+    print(f"verb tests {ok}/{len(tests)}")
+    print("  peri-pret anar: 1sg=", peri_pret_aux("first", "singular"),
+          "3pl=", peri_pret_aux("third", "plural"))
+    print("  gender casa=", noun_gender("casa"), "home=", noun_gender("home"),
+          "cavall=", noun_gender("cavall"), "cançó=", noun_gender("cançó"))
+    print("  plural casa->", inflect_noun("casa", "plural"),
+          "| plaça->", inflect_noun("plaça", "plural"),
+          "| peix->", inflect_noun("peix", "plural"),
+          "| braç->", inflect_noun("braç", "plural"),
+          "| home->", inflect_noun("home", "plural"))
+    print("  adj: alt/f/sg->", inflect_adj("alt", "f", "singular"),
+          "| bonic/f/pl->", inflect_adj("bonic", "f", "plural"),
+          "| vermell/f/sg->", inflect_adj("vermell", "f", "singular"))
+    print("  part: cantar/f/sg->", participle("cantar", "f", "singular"),
+          "| veure/f/pl->", participle("veure", "f", "plural"),
+          "| fer/m/sg->", participle("fer", "m", "singular"))
+    print("  ger: fer->", gerund("fer"), "| cantar->", gerund("cantar"))

elp/tests/lang-gen/morphology_de_full.py

@@ -0,0 +1,423 @@
+# -*- coding: utf-8 -*-
+"""morphology_de_full.py — production German morphological generator.
+
+Real data, no toy tables:
+
+  PRIMARY — UniMorph German (github.com/unimorph/deu, CC-BY-SA 3.0).
+    ~219k noun forms, ~199k verb forms. Supplies:
+      nouns : gender (MASC/FEM/NEUT) + case×number paradigm
+              (N;NOM/ACC/DAT/GEN; MASC/FEM/NEUT; SG/PL) — the genitive -(e)s,
+              dative-plural -n and the five plural classes are REAL forms, not
+              guessed.
+      verbs : full finite paradigm IND;{SG,PL};{1,2,3};{PRS,PST}, the past
+              participle (V.PTCP;PST, incl. reattached separable prefix
+              'zugefügt'), and — crucially for V2 — the SEPARATED finite form
+              UniMorph records directly ('füge zu', 'steht auf').
+      adjs  : comparative / superlative (ADJ;CMPR, ADJ;SPRL).
+
+  SECONDARY — kaikki.org German (Wiktionary, CC-BY-SA/GFDL). Gap-fills noun
+    gender + plural where UniMorph is thin. Never overrides UniMorph.
+
+Rule fallbacks (flagged 'rule'/'fallback') for lemmas absent from both lexicons:
+  present  : -e/-st/-t/-en/-t/-en with e-epenthesis after -t/-d/-chn stems
+  plural   : gender heuristic (fem -> -(e)n, else -e / umlaut left to lexicon)
+  ppart    : weak ge-…-t
+Adjective ENDINGS are rule-computed by the realizer (regular closed table);
+this module only supplies the comparative/superlative STEM.
+
+Perfect auxiliary (haben vs sein): sein for a curated set of intransitive
+motion / change-of-state verbs (real German lexical property), else haben.
+
+Public API:
+  noun_gender(lemma) -> 'm'|'f'|'n'
+  decline_noun(lemma, case, number) -> (form, conf)
+  pluralize(lemma) -> (form, conf)
+  finite(lemma, tense, person, number) -> (form, conf)      # may contain ' prefix'
+  nonfinite(lemma, req) -> (form, conf)   # req: 'inf'|'ppart'
+  past_participle(lemma) -> (form, conf)
+  separable_prefix(lemma) -> str|None
+  perfect_aux(lemma) -> 'haben'|'sein'
+  comparative(lemma)/superlative(lemma) -> (stem, conf)
+  lexicon_stats() -> dict
+"""
+import json
+import os
+import pickle
+
+_HERE = os.path.dirname(os.path.abspath(__file__))
+_UNIMORPH = os.path.join(_HERE, "data", "deu.unimorph")
+_KAIKKI = os.path.join(_HERE, "data", "kaikki_de.jsonl")
+_CACHE = os.path.join(_HERE, "data", "de_morph_cache.pkl")
+
+_GENDER = {"MASC": "m", "FEM": "f", "NEUT": "n"}
+
+# intransitive motion / change-of-state verbs that take SEIN in the perfect
+_SEIN = {"gehen", "kommen", "fahren", "laufen", "rennen", "reisen", "fallen",
+         "steigen", "sinken", "wachsen", "sterben", "geschehen", "passieren",
+         "werden", "bleiben", "sein", "aufstehen", "einschlafen", "aufwachen",
+         "ankommen", "abfahren", "aufsteigen", "erscheinen", "verschwinden",
+         "fliegen", "schwimmen", "springen", "begegnen", "folgen", "gelingen",
+         "wandern", "ziehen", "flüchten", "eintreten", "einsteigen", "aussteigen"}
+
+
+# hardcoded high-frequency irregular / auxiliary / modal paradigms (closed class,
+# verified) — consulted before the lexicon so aux+modal chains are always correct.
+_CORE = {
+    "sein": {"prs": {("first", "singular"): "bin", ("second", "singular"): "bist",
+                     ("third", "singular"): "ist", ("first", "plural"): "sind",
+                     ("second", "plural"): "seid", ("third", "plural"): "sind"},
+             "pst": {("first", "singular"): "war", ("second", "singular"): "warst",
+                     ("third", "singular"): "war", ("first", "plural"): "waren",
+                     ("second", "plural"): "wart", ("third", "plural"): "waren"},
+             "ppart": "gewesen"},
+    "haben": {"prs": {("first", "singular"): "habe", ("second", "singular"): "hast",
+                      ("third", "singular"): "hat", ("first", "plural"): "haben",
+                      ("second", "plural"): "habt", ("third", "plural"): "haben"},
+              "pst": {("first", "singular"): "hatte", ("second", "singular"): "hattest",
+                      ("third", "singular"): "hatte", ("first", "plural"): "hatten",
+                      ("second", "plural"): "hattet", ("third", "plural"): "hatten"},
+              "ppart": "gehabt"},
+    "werden": {"prs": {("first", "singular"): "werde", ("second", "singular"): "wirst",
+                       ("third", "singular"): "wird", ("first", "plural"): "werden",
+                       ("second", "plural"): "werdet", ("third", "plural"): "werden"},
+               "pst": {("first", "singular"): "wurde", ("second", "singular"): "wurdest",
+                       ("third", "singular"): "wurde", ("first", "plural"): "wurden",
+                       ("second", "plural"): "wurdet", ("third", "plural"): "wurden"},
+               "ppart": "geworden"},
+}
+_MODAL_PRS = {
+    "können": ("kann", "kannst", "kann", "können", "könnt", "können"),
+    "müssen": ("muss", "musst", "muss", "müssen", "müsst", "müssen"),
+    "wollen": ("will", "willst", "will", "wollen", "wollt", "wollen"),
+    "sollen": ("soll", "sollst", "soll", "sollen", "sollt", "sollen"),
+    "dürfen": ("darf", "darfst", "darf", "dürfen", "dürft", "dürfen"),
+    "mögen": ("mag", "magst", "mag", "mögen", "mögt", "mögen"),
+}
+_MODAL_PST = {
+    "können": ("konnte", "konntest", "konnte", "konnten", "konntet", "konnten"),
+    "müssen": ("musste", "musstest", "musste", "mussten", "musstet", "mussten"),
+    "wollen": ("wollte", "wolltest", "wollte", "wollten", "wolltet", "wollten"),
+    "sollen": ("sollte", "solltest", "sollte", "sollten", "solltet", "sollten"),
+    "dürfen": ("durfte", "durftest", "durfte", "durften", "durftet", "durften"),
+    "mögen": ("mochte", "mochtest", "mochte", "mochten", "mochtet", "mochten"),
+}
+_PN_ORDER = [("first", "singular"), ("second", "singular"), ("third", "singular"),
+             ("first", "plural"), ("second", "plural"), ("third", "plural")]
+_MODAL_PPART = {"können": "gekonnt", "müssen": "gemusst", "wollen": "gewollt",
+                "sollen": "gesollt", "dürfen": "gedurft", "mögen": "gemocht"}
+for _m, _forms in _MODAL_PRS.items():
+    _CORE[_m] = {"prs": dict(zip(_PN_ORDER, _forms)),
+                 "pst": dict(zip(_PN_ORDER, _MODAL_PST[_m])),
+                 "ppart": _MODAL_PPART[_m]}
+
+
+def _person_num(tags):
+    p = n = None
+    for t in tags:
+        if t in ("1", "2", "3"):
+            p = {"1": "first", "2": "second", "3": "third"}[t]
+        elif t == "SG":
+            n = "singular"
+        elif t == "PL":
+            n = "plural"
+    return p, n
+
+
+def _build_from_unimorph():
+    nouns, verbs, adjs = {}, {}, {}
+    if not os.path.exists(_UNIMORPH):
+        return nouns, verbs, adjs
+    with open(_UNIMORPH, encoding="utf-8") as fh:
+        for line in fh:
+            line = line.rstrip("\n")
+            if not line or "\t" not in line:
+                continue
+            parts = line.split("\t")
+            if len(parts) != 3:
+                continue
+            lemma, form, tagstr = parts
+            tags = tagstr.split(";")
+            head = tags[0]
+            tset = set(tags)
+            if head == "N":
+                rec = nouns.setdefault(lemma, {"g": None, "cases": {}, "pl": None})
+                g = next((_GENDER[t] for t in tags if t in _GENDER), None)
+                if g and not rec["g"]:
+                    rec["g"] = g
+                case = next((t for t in tags if t in ("NOM", "ACC", "DAT", "GEN")), None)
+                num = "plural" if "PL" in tset else ("singular" if "SG" in tset else None)
+                if case and num:
+                    rec["cases"].setdefault((case, num), form)
+                    if case == "NOM" and num == "plural" and not rec["pl"]:
+                        rec["pl"] = form
+            elif head.startswith("V"):
+                rec = verbs.setdefault(lemma, {"prs": {}, "pst": {}, "ppart": None})
+                if "PTCP" in head and "PST" in tset:
+                    rec["ppart"] = rec["ppart"] or form
+                elif "IND" in tset and ("PRS" in tset or "PST" in tset):
+                    p, n = _person_num(tags)
+                    if p and n:
+                        slot = "prs" if "PRS" in tset else "pst"
+                        rec[slot].setdefault((p, n), form)
+            elif head == "ADJ":
+                rec = adjs.setdefault(lemma, {})
+                if "CMPR" in tset:
+                    rec.setdefault("cmpr", form.replace("am ", "").strip())
+                elif "SPRL" in tset:
+                    rec.setdefault("sprl", form.replace("am ", "").replace("sten", "st")
+                                   if form.endswith("sten") else form.replace("am ", ""))
+    return nouns, verbs, adjs
+
+
+def _build_from_kaikki(nouns):
+    """Gap-fill noun gender + plural from kaikki German."""
+    if not os.path.exists(_KAIKKI):
+        return
+    _g = {"masculine": "m", "feminine": "f", "neuter": "n", "m": "m", "f": "f", "n": "n"}
+    with open(_KAIKKI, encoding="utf-8") as fh:
+        for line in fh:
+            try:
+                d = json.loads(line)
+            except Exception:
+                continue
+            if d.get("pos") != "noun":
+                continue
+            w = d.get("word", "")
+            if not w or not w[0].isalpha() or " " in w:
+                continue
+            rec = nouns.setdefault(w, {"g": None, "cases": {}, "pl": None})
+            # GENDER: Wiktionary gender is hand-curated and OVERRIDES UniMorph's
+            # auto-tagged gender, which has known errors (e.g. UniMorph deu mis-
+            # records Zeit=MASC, Wagen=NEUT; Wiktionary has f, m correctly).
+            for h in d.get("head_templates", []) or []:
+                a = h.get("args", {}) or {}
+                raw = a.get("1") or a.get("g") or ""
+                code = str(raw).split(",")[0].strip().lower()
+                if code in _g:
+                    rec["g"] = _g[code]
+                    break
+            if not rec["pl"]:
+                for f in d.get("forms", []) or []:
+                    t = set(f.get("tags", []) or [])
+                    if "plural" in t and f.get("form") and "genitive" not in t:
+                        rec["pl"] = f["form"]
+                        break
+
+
+def _build_cache():
+    nouns, verbs, adjs = _build_from_unimorph()
+    _build_from_kaikki(nouns)
+    data = {"nouns": nouns, "verbs": verbs, "adjs": adjs}
+    try:
+        with open(_CACHE, "wb") as fh:
+            pickle.dump(data, fh, protocol=pickle.HIGHEST_PROTOCOL)
+    except OSError:
+        pass
+    return data
+
+
+def _load():
+    if os.path.exists(_CACHE):
+        srcs = [p for p in (_UNIMORPH, _KAIKKI) if os.path.exists(p)]
+        newest = max((os.path.getmtime(p) for p in srcs), default=0)
+        if os.path.getmtime(_CACHE) >= newest:
+            try:
+                with open(_CACHE, "rb") as fh:
+                    return pickle.load(fh)
+            except Exception:
+                pass
+    return _build_cache()
+
+
+_LEX = _load()
+_NOUNS, _VERBS, _ADJS = _LEX["nouns"], _LEX["verbs"], _LEX["adjs"]
+
+
+# ── nouns ────────────────────────────────────────────────────────────────────────
+def noun_gender(lemma):
+    rec = _NOUNS.get(lemma) or _NOUNS.get(lemma.capitalize())
+    if rec and rec.get("g"):
+        return rec["g"]
+    # last-resort rule: -ung/-heit/-keit/-schaft/-tät/-ion -> f ; -chen/-lein -> n
+    low = lemma.lower()
+    if low.endswith(("ung", "heit", "keit", "schaft", "tät", "ion", "ik", "ei")):
+        return "f"
+    if low.endswith(("chen", "lein", "ment", "um")):
+        return "n"
+    return "m"
+
+
+def pluralize(lemma):
+    rec = _NOUNS.get(lemma) or _NOUNS.get(lemma.capitalize())
+    if rec and rec.get("pl"):
+        return rec["pl"], "lexicon"
+    g = noun_gender(lemma)
+    if g == "f":
+        return (lemma + "en" if not lemma.endswith("e") else lemma + "n"), "rule"
+    return (lemma if lemma.endswith(("er", "en", "el")) else lemma + "e"), "rule"
+
+
+def decline_noun(lemma, case, number):
+    """case in NOM/ACC/DAT/GEN, number in singular/plural."""
+    rec = _NOUNS.get(lemma) or _NOUNS.get(lemma.capitalize())
+    if case == "DAT" and number == "singular":
+        # modern German drops the archaic dative -e ('dem Kinde' -> 'dem Kind');
+        # the article carries the case. Keep bare nominative form.
+        base = (rec or {}).get("cases", {}).get(("NOM", "singular")) or lemma
+        return base, ("lexicon" if rec else "rule")
+    if rec and rec.get("cases", {}).get((case, number)):
+        return rec["cases"][(case, number)], "lexicon"
+    if number == "plural":
+        pl, c = pluralize(lemma)
+        if case == "DAT" and not pl.endswith("n") and not pl.endswith("s"):
+            return pl + "n", c            # dative plural -n
+        return pl, c
+    # singular
+    g = noun_gender(lemma)
+    if case == "GEN" and g in ("m", "n"):
+        return (lemma + "es" if lemma.endswith(("s", "ß", "z", "x")) else lemma + "s"), "rule"
+    return lemma, "lexicon" if rec else "rule"
+
+
+# ── verbs ──────────────────────────────────────────────────────────────────────--
+_PRS_ENDINGS = {("first", "singular"): "e", ("second", "singular"): "st",
+                ("third", "singular"): "t", ("first", "plural"): "en",
+                ("second", "plural"): "t", ("third", "plural"): "en"}
+
+
+def _stem(lemma):
+    if lemma.endswith("en"):
+        return lemma[:-2]
+    if lemma.endswith("n"):
+        return lemma[:-1]
+    return lemma
+
+
+def separable_prefix(lemma):
+    """Return the separable prefix if the lemma is a separable-prefix verb."""
+    rec = _VERBS.get(lemma)
+    if rec:
+        for (_p, _n), form in rec.get("prs", {}).items():
+            if " " in form:
+                return form.rsplit(" ", 1)[1]
+    _SEP = ("auf", "aus", "ab", "an", "ein", "mit", "nach", "vor", "zu", "zurück",
+            "weg", "hin", "her", "los", "bei", "fest", "fort", "um", "zusammen")
+    _INSEP = ("be", "ge", "er", "ver", "zer", "ent", "emp", "miss")
+    for p in sorted(_SEP, key=len, reverse=True):
+        if lemma.startswith(p) and len(lemma) > len(p) + 2 \
+                and not lemma.startswith(_INSEP):
+            return p
+    return None
+
+
+def finite(lemma, tense, person, number):
+    """Present/past finite. For separable verbs the returned string is the
+    UniMorph SEPARATED form 'stem prefix' (realizer places prefix per V2)."""
+    slot = "prs" if tense == "present" else "pst"
+    if lemma in _CORE and _CORE[lemma].get(slot, {}).get((person, number)):
+        return _CORE[lemma][slot][(person, number)], "lexicon"
+    rec = _VERBS.get(lemma)
+    if rec and rec.get(slot, {}).get((person, number)):
+        return rec[slot][(person, number)], "lexicon"
+    # rule fallback (present only reliable; past weak -te)
+    stem = _stem(lemma)
+    pref = separable_prefix(lemma)
+    if pref:
+        stem = _stem(lemma[len(pref):])
+    if tense == "present":
+        end = _PRS_ENDINGS[(person, number)]
+        if stem.endswith(("t", "d", "chn", "ffn", "gn")) and end in ("st", "t"):
+            end = "e" + end
+        form = stem + end
+    else:
+        form = stem + ("ete" if stem.endswith(("t", "d")) else "te")
+        if (person, number) == ("second", "singular"):
+            form += "st"
+        elif number == "plural" and person != "second":
+            form += "n"
+        elif (person, number) == ("second", "plural"):
+            form += "t"
+    if pref:
+        return f"{form} {pref}", "rule"
+    return form, "rule"
+
+
+def _weak_t(stem):
+    return stem + ("et" if stem.endswith(("t", "d", "chn", "ffn", "gn")) else "t")
+
+
+def past_participle(lemma):
+    if lemma in _CORE:
+        return _CORE[lemma]["ppart"], "lexicon"
+    rec = _VERBS.get(lemma)
+    if rec and rec.get("ppart"):
+        return rec["ppart"], "lexicon"
+    stem = _stem(lemma)
+    pref = separable_prefix(lemma)
+    _INSEP = ("be", "ge", "er", "ver", "zer", "ent", "emp", "miss")
+    if pref:
+        inner = _stem(lemma[len(pref):])
+        return pref + "ge" + _weak_t(inner), "rule"
+    if lemma.startswith(_INSEP):
+        return _weak_t(stem), "rule"
+    return "ge" + _weak_t(stem), "rule"
+
+
+def nonfinite(lemma, req):
+    if req == "ppart":
+        return past_participle(lemma)
+    return lemma, "lexicon" if lemma in _VERBS else "rule"   # infinitive
+
+
+def perfect_aux(lemma):
+    return "sein" if lemma in _SEIN else "haben"
+
+
+# ── adjectives ────────────────────────────────────────────────────────────────---
+_ADJ_IRREG_SPRL = {"gut": "best", "groß": "größt", "hoch": "höchst",
+                   "nah": "nächst", "viel": "meist", "gern": "liebst"}
+
+
+def comparative(lemma):
+    rec = _ADJS.get(lemma)
+    if rec and rec.get("cmpr"):
+        return rec["cmpr"], "lexicon"
+    return lemma + "er", "rule"
+
+
+def superlative(lemma):
+    """Return the bare superlative STEM (realizer adds 'am ...en' or '-e' ending)."""
+    if lemma in _ADJ_IRREG_SPRL:
+        return _ADJ_IRREG_SPRL[lemma], "lexicon"
+    # derive from the comparative so umlaut is carried (alt->älter->ältest)
+    cmpr, cconf = comparative(lemma)
+    base = cmpr[:-2] if cmpr.endswith("er") else lemma
+    end = "est" if base.endswith(("t", "d", "s", "ß", "z", "sch")) else "st"
+    return base + end, cconf
+
+
+def lexicon_stats():
+    return {
+        "source": "UniMorph deu (primary) + kaikki.org German (gap-fill gender/plural)",
+        "license": "CC-BY-SA 3.0 (UniMorph); CC-BY-SA/GFDL (Wiktionary)",
+        "noun_lemmas": len(_NOUNS),
+        "nouns_with_gender": sum(1 for v in _NOUNS.values() if v.get("g")),
+        "nouns_with_plural": sum(1 for v in _NOUNS.values() if v.get("pl")),
+        "verb_lemmas": len(_VERBS),
+        "verbs_with_ppart": sum(1 for v in _VERBS.values() if v.get("ppart")),
+        "adj_lemmas": len(_ADJS),
+    }
+
+
+if __name__ == "__main__":
+    print(json.dumps(lexicon_stats(), indent=2, ensure_ascii=False))
+    for w in ("Hund", "Frau", "Kind", "Mann", "Buch", "Blume"):
+        print(f"  {w}: gender={noun_gender(w)} pl={pluralize(w)} "
+              f"gen.sg={decline_noun(w, 'GEN', 'singular')} "
+              f"dat.pl={decline_noun(w, 'DAT', 'plural')}")
+    for v in ("machen", "gehen", "aufstehen", "sein", "haben", "arbeiten"):
+        print(f"  {v}: 3sg.prs={finite(v, 'present', 'third', 'singular')} "
+              f"3sg.pst={finite(v, 'past', 'third', 'singular')} "
+              f"ppart={past_participle(v)} aux={perfect_aux(v)} sep={separable_prefix(v)}")
+    for a in ("schnell", "gut", "groß", "alt"):
+        print(f"  {a}: cmpr={comparative(a)} sprl={superlative(a)}")

elp/tests/lang-gen/morphology_es_full.py

@@ -0,0 +1,562 @@
+"""morphology_es_full.py — production-grade Spanish morphological generator.
+
+NOT a toy. Backed by a real, broad, licensed lexicon:
+
+    UniMorph Spanish  (github.com/unimorph/spa, CC-BY-SA 3.0, Wiktionary-derived)
+    1,196,245 inflected forms:
+      6,695 verb lemmas   — full paradigms: indicative (present/preterite/
+                            imperfect/future), conditional, present & imperfect
+                            subjunctive, affirmative imperative, formal/informal
+      48,353 noun lemmas  — WITH inherent gender (N;FEM/MASC;SG/PL)
+      16,984 adj lemmas   — gender + number paradigms
+
+Fallbacks (so we degrade, never crash, on out-of-vocabulary input):
+  - verbs : mlconjug3 (ML paradigm model, conjugates ANY Spanish verb) then a
+            hand-rolled regular-ending generator
+  - nouns : gender heuristic (endings) + regular pluralization
+  - adjs  : -o/-a gender rule + regular pluralization
+
+Every generated form carries a CONFIDENCE flag:
+  "lexicon"   form came straight from UniMorph            (trust: high)
+  "model"     form came from mlconjug3                    (trust: high)
+  "rule"      form came from a deterministic rule         (trust: medium)
+  "fallback"  we could not inflect; returned lemma as-is  (trust: low → FLAG)
+
+Public API (used by realizer_es.py):
+  conjugate(lemma, mood, tense, person, number, formality="informal") -> (form, conf)
+  participle(lemma) -> (form, conf)      # past participle (compound tenses)
+  gerund(lemma) -> (form, conf)
+  noun_gender(lemma) -> "m"|"f"
+  inflect_noun(lemma, number) -> (form, conf)
+  inflect_adj(lemma, gender, number) -> (form, conf)
+  attach_enclitics(verb_form, clitics) -> str     # accent-correct enclisis
+  lexicon_stats() -> dict
+"""
+import os
+import pickle
+import unicodedata
+
+_HERE = os.path.dirname(os.path.abspath(__file__))
+_UNIMORPH = os.path.join(_HERE, "data", "spa.unimorph")
+_CACHE = os.path.join(_HERE, "data", "es_morph_cache.pkl")
+
+# ── canonical feature keys the realizer speaks, mapped to UniMorph tags ─────────
+# mood/tense pair -> the UniMorph feature substring that identifies it
+_VERB_KEYMAP = {
+    ("ind", "present"):    ("IND", "PRS", None),
+    ("ind", "preterite"):  ("IND", "PST", "PFV"),
+    ("ind", "imperfect"):  ("IND", "PST", "IPFV"),
+    ("ind", "future"):     ("IND", "FUT", None),
+    ("ind", "conditional"):("COND", None, None),
+    ("sbjv", "present"):   ("SBJV", "PRS", None),
+    ("sbjv", "imperfect"): ("SBJV", "PST", "LGSPEC1"),  # -ra form
+    ("imp", "present"):    ("POS", "IMP", None),
+}
+_PERSON = {"first": "1", "second": "2", "third": "3"}
+_NUMBER = {"singular": "SG", "plural": "PL"}
+
+
+# ── build / load the compact lexicon ───────────────────────────────────────────
+def _feat_set(tag):
+    return set(tag.split(";"))
+
+
+def _build_cache():
+    verbs = {}     # (lemma, canonkey) -> form   canonkey e.g. "ind|present|1|SG|infm"
+    nouns = {}     # lemma -> {"g": "m"/"f", "SG": form, "PL": form}
+    adjs = {}      # lemma -> {("m","SG"): form, ...}
+    part = {}      # lemma -> masc-sg participle
+    ger = {}       # lemma -> gerund
+
+    with open(_UNIMORPH, encoding="utf-8") as fh:
+        for line in fh:
+            line = line.rstrip("\n")
+            if not line or "\t" not in line:
+                continue
+            parts = line.split("\t")
+            if len(parts) != 3:
+                continue
+            lemma, form, tag = parts
+            f = _feat_set(tag)
+            head = tag.split(";")[0]
+
+            if head == "V":
+                # skip clitic-bearing rows (we generate clitics ourselves)
+                if "PRO" in f:
+                    continue
+                if "V.PTCP" in f and "PST" in f and "MASC" in f and "SG" in f:
+                    part.setdefault(lemma, form)
+                    continue
+                if "V.CVB" in f or "NFIN" in f or "V.PTCP" in f:
+                    if "V.CVB" in f:
+                        ger.setdefault(lemma, form)
+                    continue
+                # identify mood/tense
+                mt = None
+                for (mood, tense), (a, b, c) in _VERB_KEYMAP.items():
+                    if a not in f:
+                        continue
+                    if b is not None and b not in f:
+                        continue
+                    if c is not None and c not in f:
+                        continue
+                    # disambiguate IND;PST needing PFV vs IPFV
+                    if a == "IND" and b == "PST" and c not in f:
+                        continue
+                    mt = (mood, tense)
+                    break
+                if mt is None:
+                    continue
+                person = next((p for p in ("1", "2", "3") if p in f), None)
+                number = "SG" if "SG" in f else ("PL" if "PL" in f else None)
+                if person is None or number is None:
+                    continue
+                formal = "form" if "FORM" in f else ("infm" if "INFM" in f else "any")
+                key = f"{mt[0]}|{mt[1]}|{person}|{number}|{formal}"
+                verbs.setdefault((lemma, key), form)
+
+            elif head == "N":
+                # substring test handles epicene "MASC+FEM" (-> masc citation)
+                g = "m" if "MASC" in tag else ("f" if "FEM" in tag else None)
+                num = "SG" if "SG" in f else ("PL" if "PL" in f else None)
+                if num is None:
+                    continue
+                # store forms keyed by (gender,number); animate nouns list BOTH
+                # genders under one lemma (niño -> niño/niña). Resolve citation
+                # gender in a post-pass (gender of the row whose form == lemma).
+                d = nouns.setdefault(lemma, {})
+                d.setdefault("_rows", []).append((g, num, form))
+
+            elif head == "ADJ":
+                g = "m" if "MASC" in tag else ("f" if "FEM" in tag else "m")
+                num = "SG" if "SG" in f else ("PL" if "PL" in f else None)
+                if num is None:
+                    continue
+                adjs.setdefault(lemma, {})[(g, num)] = form
+
+    # post-pass: resolve noun citation gender + default SG/PL forms
+    for lemma, d in nouns.items():
+        rows = d.pop("_rows", [])
+        # citation gender = gender of the row whose form == lemma; else first MASC;
+        # else first seen gender.
+        cite_g = None
+        for g, num, form in rows:
+            if form == lemma and g:
+                cite_g = g
+                break
+        if cite_g is None:
+            for g, num, form in rows:
+                if g == "m":
+                    cite_g = "m"
+                    break
+        if cite_g is None:
+            cite_g = next((g for g, _, _ in rows if g), "m")
+        d["g"] = cite_g
+        for g, num, form in rows:
+            d[(g, num)] = form
+        d["SG"] = d.get((cite_g, "SG")) or next((f for g, n, f in rows if n == "SG"), lemma)
+        d["PL"] = d.get((cite_g, "PL")) or next((f for g, n, f in rows if n == "PL"), None)
+
+    # post-pass: UniMorph omits the identity inflection (masc-sg == lemma) for
+    # adjectives, so fill it in; without this a fem-sg row wrongly satisfies a
+    # masc-sg request (alto -> alta bug).
+    for lemma, d in adjs.items():
+        d.setdefault(("m", "SG"), lemma)
+
+    data = {"verbs": verbs, "nouns": nouns, "adjs": adjs, "part": part, "ger": ger}
+    try:
+        with open(_CACHE, "wb") as fh:
+            pickle.dump(data, fh, protocol=pickle.HIGHEST_PROTOCOL)
+    except OSError:
+        pass
+    return data
+
+
+def _load():
+    if os.path.exists(_CACHE) and os.path.getmtime(_CACHE) >= os.path.getmtime(_UNIMORPH):
+        try:
+            with open(_CACHE, "rb") as fh:
+                return pickle.load(fh)
+        except Exception:
+            pass
+    return _build_cache()
+
+
+_LEX = _load()
+_VERBS, _NOUNS, _ADJS, _PART, _GER = (
+    _LEX["verbs"], _LEX["nouns"], _LEX["adjs"], _LEX["part"], _LEX["ger"])
+
+# ── mlconjug3 fallback (lazy) ───────────────────────────────────────────────────
+_MLC = None
+_MLC_TENSE = {  # (mood,tense) -> (mlconjug mood label, tense label)
+    ("ind", "present"):     ("Indicativo", "Indicativo presente"),
+    ("ind", "preterite"):   ("Indicativo", "Indicativo pretérito perfecto simple"),
+    ("ind", "imperfect"):   ("Indicativo", "Indicativo pretérito imperfecto"),
+    ("ind", "future"):      ("Indicativo", "Indicativo futuro"),
+    ("ind", "conditional"): ("Condicional", "Condicional Condicional"),
+    ("sbjv", "present"):    ("Subjuntivo", "Subjuntivo presente"),
+    ("sbjv", "imperfect"):  ("Subjuntivo", "Subjuntivo pretérito imperfecto 1"),
+    ("imp", "present"):     ("Imperativo", "Imperativo Afirmativo"),
+}
+_MLC_SLOT = {  # (person,number) -> mlconjug slot key
+    ("first", "singular"):  "1s", ("second", "singular"): "2s",
+    ("third", "singular"):  "3s", ("first", "plural"):    "1p",
+    ("second", "plural"):   "2p", ("third", "plural"):    "3p",
+}
+
+
+def _mlc_conjugate(lemma, mood, tense, person, number):
+    global _MLC
+    try:
+        if _MLC is None:
+            from mlconjug3 import Conjugator
+            _MLC = Conjugator(language="es")
+        v = _MLC.conjugate(lemma)
+        if v is None:
+            return None
+        info = v.conjug_info
+        m, t = _MLC_TENSE.get((mood, tense), (None, None))
+        if m is None or m not in info or t not in info[m]:
+            return None
+        block = info[m][t]
+        slot = _MLC_SLOT.get((person, number))
+        if isinstance(block, dict) and slot in block and block[slot]:
+            return block[slot]
+        return None
+    except Exception:
+        return None
+
+
+# ── regular-ending rule fallback (last resort, deterministic) ───────────────────
+def _vclass(lemma):
+    return lemma[-2:] if lemma[-2:] in ("ar", "er", "ir") else "ar"
+
+
+def _stem(lemma):
+    return lemma[:-2]
+
+
+_REG = {
+    ("ind", "present", "ar"): ["o", "as", "a", "amos", "áis", "an"],
+    ("ind", "present", "er"): ["o", "es", "e", "emos", "éis", "en"],
+    ("ind", "present", "ir"): ["o", "es", "e", "imos", "ís", "en"],
+    ("ind", "preterite", "ar"): ["é", "aste", "ó", "amos", "asteis", "aron"],
+    ("ind", "preterite", "er"): ["í", "iste", "ió", "imos", "isteis", "ieron"],
+    ("ind", "preterite", "ir"): ["í", "iste", "ió", "imos", "isteis", "ieron"],
+    ("ind", "imperfect", "ar"): ["aba", "abas", "aba", "ábamos", "abais", "aban"],
+    ("ind", "imperfect", "er"): ["ía", "ías", "ía", "íamos", "íais", "ían"],
+    ("ind", "imperfect", "ir"): ["ía", "ías", "ía", "íamos", "íais", "ían"],
+    ("sbjv", "present", "ar"): ["e", "es", "e", "emos", "éis", "en"],
+    ("sbjv", "present", "er"): ["a", "as", "a", "amos", "áis", "an"],
+    ("sbjv", "present", "ir"): ["a", "as", "a", "amos", "áis", "an"],
+    ("sbjv", "imperfect", "ar"): ["ara", "aras", "ara", "áramos", "arais", "aran"],
+    ("sbjv", "imperfect", "er"): ["iera", "ieras", "iera", "iéramos", "ierais", "ieran"],
+    ("sbjv", "imperfect", "ir"): ["iera", "ieras", "iera", "iéramos", "ierais", "ieran"],
+}
+_FUT = ["é", "ás", "á", "emos", "éis", "án"]
+_COND = ["ía", "ías", "ía", "íamos", "íais", "ían"]
+
+
+def _slot_idx(person, number):
+    base = {"first": 0, "second": 1, "third": 2}[person]
+    return base + (0 if number == "singular" else 3)
+
+
+def _rule_conjugate(lemma, mood, tense, person, number):
+    if len(lemma) < 3 or lemma[-2:] not in ("ar", "er", "ir"):
+        return None
+    vc, st, i = _vclass(lemma), _stem(lemma), _slot_idx(person, number)
+    if tense == "future":
+        return lemma + _FUT[i]
+    if tense == "conditional":
+        return lemma + _COND[i]
+    table = _REG.get((mood, tense, vc))
+    if table:
+        return st + table[i]
+    if mood == "imp" and tense == "present":
+        # affirmative tú imperative = 3sg present indicative
+        pres = _REG.get(("ind", "present", vc))
+        return st + pres[2] if number == "singular" else st + pres[5]
+    return None
+
+
+# ── PUBLIC: verb conjugation ────────────────────────────────────────────────────
+def conjugate(lemma, mood, tense, person, number, formality="informal"):
+    """Return (surface, confidence). mood in ind|sbjv|imp; tense per _VERB_KEYMAP."""
+    lemma = lemma.strip().lower()
+    p, n = _PERSON.get(person), _NUMBER.get(number)
+    formal = "form" if formality == "formal" else "infm"
+    if p and n:
+        for fkey in (formal, "any", "infm" if formal == "form" else "form"):
+            form = _VERBS.get((lemma, f"{mood}|{tense}|{p}|{n}|{fkey}"))
+            if form:
+                return form, "lexicon"
+    m = _mlc_conjugate(lemma, mood, tense, person, number)
+    if m:
+        return m, "model"
+    r = _rule_conjugate(lemma, mood, tense, person, number)
+    if r:
+        return r, "rule"
+    return lemma, "fallback"
+
+
+_IRREG_PART = {  # guarantee the common irregular participles
+    "escribir": "escrito", "describir": "descrito", "abrir": "abierto",
+    "cubrir": "cubierto", "descubrir": "descubierto", "morir": "muerto",
+    "poner": "puesto", "ver": "visto", "volver": "vuelto", "devolver": "devuelto",
+    "hacer": "hecho", "deshacer": "deshecho", "decir": "dicho", "romper": "roto",
+    "resolver": "resuelto", "freír": "frito", "imprimir": "impreso",
+    "satisfacer": "satisfecho", "prever": "previsto", "revolver": "revuelto",
+}
+
+
+def participle(lemma):
+    lemma = lemma.strip().lower()
+    if lemma in _IRREG_PART:
+        return _IRREG_PART[lemma], "lexicon"
+    if lemma in _PART:
+        return _PART[lemma], "lexicon"
+    if lemma.endswith("ar"):
+        return lemma[:-2] + "ado", "rule"
+    if lemma[-2:] in ("er", "ir"):
+        return lemma[:-2] + "ido", "rule"
+    return lemma, "fallback"
+
+
+_IRREG_GER = {"dormir": "durmiendo", "morir": "muriendo", "pedir": "pidiendo",
+              "sentir": "sintiendo", "mentir": "mintiendo", "servir": "sirviendo",
+              "venir": "viniendo", "decir": "diciendo", "poder": "pudiendo",
+              "ir": "yendo", "leer": "leyendo", "creer": "creyendo",
+              "oír": "oyendo", "traer": "trayendo", "caer": "cayendo",
+              "construir": "construyendo", "huir": "huyendo", "reír": "riendo"}
+
+
+def gerund(lemma):
+    lemma = lemma.strip().lower()
+    if lemma in _IRREG_GER:
+        return _IRREG_GER[lemma], "lexicon"
+    if lemma in _GER:
+        return _GER[lemma], "lexicon"
+    if lemma.endswith("ar"):
+        return lemma[:-2] + "ando", "rule"
+    if lemma[-2:] in ("er", "ir"):
+        return lemma[:-2] + "iendo", "rule"
+    return lemma, "fallback"
+
+
+# ── PUBLIC: noun gender + number ────────────────────────────────────────────────
+_INVARIANT_PL = {"lunes", "martes", "miércoles", "jueves", "viernes",
+                 "crisis", "tesis", "análisis", "dosis", "virus", "paraguas"}
+
+
+def _gender_heuristic(noun):
+    for suf, g in (("ión", "f"), ("dad", "f"), ("tad", "f"), ("umbre", "f"),
+                   ("sis", "f"), ("ez", "f"), ("triz", "f"),
+                   ("ema", "m"), ("ama", "m"), ("oma", "m"), ("aje", "m"),
+                   ("or", "m"), ("án", "m"), ("ín", "m")):
+        if noun.endswith(suf):
+            return g
+    if noun.endswith("o"):
+        return "m"
+    if noun.endswith("a"):
+        return "f"
+    return "m"
+
+
+def noun_gender(lemma):
+    lemma = lemma.strip().lower()
+    d = _NOUNS.get(lemma)
+    if d and d.get("g"):
+        return d["g"]
+    return _gender_heuristic(lemma)
+
+
+def _regular_plural(noun):
+    if noun in _INVARIANT_PL:
+        return noun
+    if not noun:
+        return noun
+    last = noun[-1]
+    if last == "z":
+        return noun[:-1] + "ces"
+    if last in "aeiouáéíóú":
+        # stressed final vowel í/ú -> +es (rubí->rubíes), else +s
+        if last in "íú":
+            return noun + "es"
+        return noun + "s"
+    if last == "s":
+        # esdrújula / stress-final handled crudely; most polysyllables invariant
+        return noun
+    return noun + "es"
+
+
+def inflect_noun(lemma, number, gender=None):
+    lemma = lemma.strip().lower()
+    d = _NOUNS.get(lemma)
+    num = "SG" if number == "singular" else "PL"
+    if d:
+        # honor a requested gender for animate nouns (gato -> gata)
+        if gender and (gender, num) in d:
+            return d[(gender, num)], "lexicon"
+        if d.get(num):
+            return d[num], "lexicon"
+    if number == "singular":
+        return lemma, "rule" if not d else "lexicon"
+    return _regular_plural(lemma), "rule"
+
+
+# ── PUBLIC: adjective agreement ─────────────────────────────────────────────────
+_INV_GENDER_ADJ = {"español": "española", "trabajador": "trabajadora",
+                   "hablador": "habladora", "encantador": "encantadora",
+                   "alemán": "alemana", "francés": "francesa", "inglés": "inglesa"}
+
+
+def inflect_adj(lemma, gender, number):
+    lemma = lemma.strip().lower()
+    d = _ADJS.get(lemma)
+    num = "SG" if number == "singular" else "PL"
+    if d:
+        form = d.get((gender, num))
+        if form:
+            return form, "lexicon"
+        # gender-invariant adjective (grande, feliz, azul): fem == masc.
+        # For a missing plural, pluralize this gender's singular form.
+        sg = d.get((gender, "SG")) or d.get(("m", "SG")) or lemma
+        if number == "plural":
+            return _regular_plural(sg), "rule"
+        return sg, "lexicon"
+    # rule fallback
+    a = lemma
+    if gender == "f":
+        if a in _INV_GENDER_ADJ:
+            a = _INV_GENDER_ADJ[a]
+        elif a.endswith("o"):
+            a = a[:-1] + "a"
+    if number == "plural":
+        a = _regular_plural(a)
+    return a, ("rule" if (a != lemma or gender == "m") else "rule")
+
+
+# ── PUBLIC: clitic enclisis (dá + me + lo -> dámelo) ────────────────────────────
+def _strip_accents(s):
+    return "".join(c for c in unicodedata.normalize("NFD", s)
+                   if unicodedata.category(c) != "Mn")
+
+
+def _count_syllables_vowelgroups(word):
+    # crude: count vowel groups
+    w = _strip_accents(word).lower()
+    groups, prev = 0, False
+    for ch in w:
+        isv = ch in "aeiou"
+        if isv and not prev:
+            groups += 1
+        prev = isv
+    return groups
+
+
+def _host_stress_from_end(word):
+    """Stressed-syllable index counted from the end (1=last) of a verb host."""
+    syls = _count_syllables_vowelgroups(word)
+    if any(c in "áéíóú" for c in word):
+        return None                         # already carries its own accent
+    if word[-2:] in ("ar", "er", "ir"):     # infinitive: oxytone
+        return 1
+    if word.endswith("ndo"):                # gerund: paroxytone
+        return 2
+    if word[-1:] in "aeiouns" and syls >= 2:  # default paroxytone
+        return 2
+    return 1                                 # monosyllable / consonant-final oxytone
+
+
+def attach_enclitics(verb_form, clitics):
+    """Append clitic pronouns to a verb (imperative/infinitive/gerund enclisis)
+    and add a written accent when the resulting word becomes esdrújula/
+    sobreesdrújula (stress >= 3 syllables from the end): dá+me+lo -> dámelo,
+    lleva+me -> llévame, but dar+te -> darte and da+me -> dame (no accent)."""
+    if not clitics:
+        return verb_form
+    tail = "".join(clitics)
+    if any(c in "áéíóú" for c in verb_form):    # host already accented
+        return verb_form + tail
+    sfe = _host_stress_from_end(verb_form)
+    total_sfe = sfe + len(clitics)              # each clitic = 1 syllable
+    if total_sfe >= 3:
+        return _accentuate_nucleus(verb_form, sfe) + tail
+    return verb_form + tail
+
+
+def _accentuate_nucleus(word, sfe):
+    """Put a written accent on the syllable `sfe` positions from the word's end."""
+    vowels = "aeiou"
+    nuclei = [i for i, ch in enumerate(word) if ch in vowels]
+    if not nuclei or sfe > len(nuclei):
+        return word
+    i = nuclei[-sfe]
+    acc = {"a": "á", "e": "é", "i": "í", "o": "ó", "u": "ú"}
+    return word[:i] + acc[word[i]] + word[i + 1:]
+
+
+def _accentuate_last_stressed(word):
+    # Restore the host's ORIGINAL lexical stress with a written accent.
+    # Default Spanish stress: word ending in vowel/n/s -> penultimate syllable;
+    # otherwise (e.g. infinitives in -r) -> last syllable.
+    vowels = "aeiou"
+    nuclei = [i for i, ch in enumerate(word) if ch in vowels]
+    if not nuclei:
+        return word
+    if word[-1] in "aeiouns" and len(nuclei) >= 2:
+        i = nuclei[-2]                      # paroxytone: penult nucleus
+    else:
+        i = nuclei[-1]                      # oxytone / monosyllable: last nucleus
+    acc = {"a": "á", "e": "é", "i": "í", "o": "ó", "u": "ú"}
+    return word[:i] + acc[word[i]] + word[i + 1:]
+
+
+def lexicon_stats():
+    return {
+        "source": "UniMorph Spanish (github.com/unimorph/spa)",
+        "license": "CC-BY-SA 3.0 (Wiktionary-derived)",
+        "total_forms": sum(len(v) for v in (_VERBS, _NOUNS, _ADJS)) if False else None,
+        "verb_forms": len(_VERBS),
+        "verb_lemmas": len({k[0] for k in _VERBS}),
+        "noun_lemmas": len(_NOUNS),
+        "adj_lemmas": len(_ADJS),
+        "participles": len(_PART),
+        "gerunds": len(_GER),
+    }
+
+
+if __name__ == "__main__":
+    import json
+    print(json.dumps(lexicon_stats(), indent=2, ensure_ascii=False))
+    tests = [
+        ("hablar", "ind", "present", "first", "singular", "hablo"),
+        ("comer", "ind", "present", "third", "plural", "comen"),
+        ("vivir", "ind", "present", "first", "plural", "vivimos"),
+        ("ser", "ind", "present", "third", "singular", "es"),
+        ("ir", "ind", "preterite", "first", "singular", "fui"),
+        ("tener", "ind", "future", "first", "singular", "tendré"),
+        ("hacer", "sbjv", "present", "first", "singular", "haga"),
+        ("dormir", "ind", "present", "first", "singular", "duermo"),
+        ("pensar", "sbjv", "present", "third", "singular", "piense"),
+        ("dar", "ind", "preterite", "third", "singular", "dio"),
+        ("poner", "ind", "conditional", "first", "singular", "pondría"),
+    ]
+    ok = 0
+    for lemma, mood, tense, per, num, exp in tests:
+        got, conf = conjugate(lemma, mood, tense, per, num)
+        flag = "OK " if got == exp else "XX "
+        if got == exp:
+            ok += 1
+        print(f"  {flag}{lemma:8} {mood}/{tense} {per[:3]}.{num[:2]:3} -> {got:14} ({conf})  exp={exp}")
+    print(f"verb tests {ok}/{len(tests)}")
+    print("  gender casa:", noun_gender("casa"), "| problema:", noun_gender("problema"),
+          "| agua:", noun_gender("agua"), "| mano:", noun_gender("mano"))
+    print("  plural: luz->", inflect_noun("luz", "plural"), "| rey->", inflect_noun("rey", "plural"))
+    print("  adj: rojo/f/pl->", inflect_adj("rojo", "f", "plural"),
+          "| feliz/m/pl->", inflect_adj("feliz", "m", "plural"),
+          "| grande/f/pl->", inflect_adj("grande", "f", "plural"))
+    print("  enclisis: da+[me,lo]->", attach_enclitics("da", ["me", "lo"]),
+          "| di+[me]->", attach_enclitics("di", ["me"]),
+          "| dar+[se,lo]->", attach_enclitics("dar", ["se", "lo"]))

elp/tests/lang-gen/morphology_fr_full.py

@@ -0,0 +1,629 @@
+"""morphology_fr_full.py — production-grade French morphological generator.
+
+Same architecture as morphology_it_full.py (shared Romance engine); French-specific
+data and rules swapped in. Backed by three real, Wiktionary-lineage sources:
+
+  VERBS
+    UniMorph French (github.com/unimorph/fra, CC-BY-SA 3.0)
+      7,535 verb lemmas × full paradigm, CLEAN orthography:
+        indicatif présent / imparfait (PST;IPFV) / passé simple (PST;PFV) /
+        futur, conditionnel (COND), subjonctif présent (SBJV;PRS) /
+        subjonctif imparfait (SBJV;PST), impératif (POS;IMP), infinitif (NFIN),
+        participe présent (V.CVB/V.PTCP;PRS), participe passé (V.PTCP;PST, m.sg).
+    fr_irreg_verbs.json — high-frequency verbs UniMorph MISSES or mis-slots,
+      above all ÊTRE (absent from UniMorph fra), plus avoir/aller/faire/… — the
+      auxiliaries the passé-composé + être-agreement system depends on. Extracted
+      from kaikki.org French (build_fr_irreg.py), reflexive/multiword forms
+      dropped. This layer takes PRIORITY.
+
+  NOUNS + ADJECTIVES — kaikki.org French (Wiktionary extract, CC-BY-SA 3.0)
+    noun lemmas WITH inherent gender (head-template arg) + real plural
+      (cheval->chevaux, œil->yeux, invariable -s/-x/-z), resolved PER LEMMA.
+    adjective lemmas with real feminine + plural (petit->petite/petits/petites,
+      beau->belle/beaux/belles, heureux->heureuse, rouge invariant-gender).
+
+Fallbacks (degrade, never crash, on OOV input):
+  verbs : rule generator for -er / -ir(-iss-) / -re (with -cer/-ger spelling,
+          future/conditional stems, imparfait/subjonctif endings)
+  nouns : gender heuristic (endings) + rule pluralization (-al->-aux, -eau->-eaux)
+  adjs  : fem/plural agreement rules (-er->-ère, -eux->-euse, -f->-ve, +e default)
+
+Confidence flag on every form: "lexicon" | "rule" | "fallback".
+
+Public API (used by realizer_fr.py): identical signature to morphology_it_full.
+"""
+import json
+import os
+import pickle
+
+_HERE = os.path.dirname(os.path.abspath(__file__))
+_UNIMORPH = os.path.join(_HERE, "data", "fra.unimorph")
+_IRREG = os.path.join(_HERE, "data", "fr_irreg_verbs.json")
+_KAIKKI = os.path.join(_HERE, "data", "kaikki_fr.jsonl")
+_CACHE = os.path.join(_HERE, "data", "fr_morph_cache.pkl")
+
+# ── (mood, tense) -> UniMorph feature set that must ALL be present ────────────────
+_VERB_KEYMAP = {
+    ("ind", "present"):      {"IND", "PRS"},
+    ("ind", "imperfect"):    {"IND", "PST", "IPFV"},   # imparfait
+    ("ind", "passe_simple"): {"IND", "PST", "PFV"},    # passé simple
+    ("ind", "future"):       {"IND", "FUT"},
+    ("ind", "conditional"):  {"COND"},                 # French: V;COND;1;SG
+    ("sbjv", "present"):     {"SBJV", "PRS"},
+    ("sbjv", "imperfect"):   {"SBJV", "PST"},
+    ("imp", "affirmative"):  {"POS", "IMP"},
+}
+_PERSON = {"first": "1", "second": "2", "third": "3"}
+_NUMBER = {"singular": "SG", "plural": "PL"}
+
+
+def _feat_set(tag):
+    return set(tag.split(";"))
+
+
+# ── build verb lexicon from UniMorph ─────────────────────────────────────────────
+def _build_verbs():
+    verbs = {}
+    part = {}
+    ger = {}
+    with open(_UNIMORPH, encoding="utf-8") as fh:
+        for line in fh:
+            line = line.rstrip("\n")
+            if not line or "\t" not in line:
+                continue
+            parts = line.split("\t")
+            if len(parts) != 3:
+                continue
+            lemma, form, tag = parts
+            f = _feat_set(tag)
+            head = tag.split(";")[0]
+
+            if head == "V.PTCP":
+                if "PST" in f:
+                    part.setdefault(lemma, form)
+                elif "PRS" in f:
+                    ger.setdefault(lemma, form)
+                continue
+            if head == "V.CVB":
+                if "PRS" in f:
+                    ger.setdefault(lemma, form)
+                continue
+            if head != "V":
+                continue
+
+            person = next((p for p in ("1", "2", "3") if p in f), None)
+            number = "SG" if "SG" in f else ("PL" if "PL" in f else None)
+            if person is None or number is None:
+                continue
+            for (mood, tense), req in _VERB_KEYMAP.items():
+                if not req <= f:
+                    continue
+                if tense == "imperfect" and "PFV" in f:
+                    continue
+                if tense == "passe_simple" and "IPFV" in f:
+                    continue
+                verbs.setdefault((lemma, f"{mood}|{tense}|{person}|{number}"), form)
+                break
+    return verbs, part, ger
+
+
+# ── kaikki nouns + adjectives ────────────────────────────────────────────────────
+_EXCL_FORM_TAGS = {"alternative", "archaic", "obsolete", "dialectal", "regional",
+                   "diminutive", "augmentative", "pejorative", "comparative",
+                   "superlative", "misspelling", "rare", "informal", "literary",
+                   "poetic", "error-unrecognized-form", "construed", "collective",
+                   "nonstandard", "dated", "Louisiana", "Switzerland", "Belgium"}
+
+
+def _kaikki_gender(arg):
+    if not arg:
+        return None
+    a = str(arg).lower()
+    if a.startswith("f"):
+        return "f"
+    if a.startswith("m"):
+        return "m"
+    return None
+
+
+def _build_nouns_adjs():
+    nouns = {}
+    adjs = {}
+    with open(_KAIKKI, encoding="utf-8") as fh:
+        for line in fh:
+            try:
+                d = json.loads(line)
+            except Exception:
+                continue
+            pos = d.get("pos")
+            word = d.get("word", "")
+            if not word or " " in word:
+                continue
+            forms = d.get("forms", []) or []
+
+            if pos == "noun":
+                ht = d.get("head_templates") or []
+                g = None
+                if ht:
+                    g = _kaikki_gender((ht[0].get("args") or {}).get("1"))
+                if g is None:
+                    tags = d.get("tags") or []
+                    if "feminine" in tags:
+                        g = "f"
+                    elif "masculine" in tags:
+                        g = "m"
+                pl = None
+                for x in forms:
+                    t = set(x.get("tags") or [])
+                    if "plural" in t and not (t & _EXCL_FORM_TAGS):
+                        fm = x.get("form")
+                        if fm and " " not in fm and fm not in ("#", "-", "—"):
+                            pl = fm
+                            break
+                if word not in nouns:
+                    nouns[word] = {"g": g, "SG": word, "PL": pl}
+                else:
+                    cur = nouns[word]
+                    if cur.get("g") is None and g:
+                        cur["g"] = g
+                    if not cur.get("PL") and pl:
+                        cur["PL"] = pl
+
+            elif pos == "adj":
+                d0 = adjs.setdefault(word, {})
+                d0.setdefault(("m", "SG"), word)
+                for x in forms:
+                    t = set(x.get("tags") or [])
+                    fm = x.get("form")
+                    if not fm or " " in fm or (t & _EXCL_FORM_TAGS):
+                        continue
+                    if "feminine" in t and "plural" in t:
+                        d0[("f", "PL")] = d0.get(("f", "PL")) or fm
+                    elif "masculine" in t and "plural" in t:
+                        d0[("m", "PL")] = d0.get(("m", "PL")) or fm
+                    elif "feminine" in t:
+                        d0[("f", "SG")] = d0.get(("f", "SG")) or fm
+                    elif "plural" in t:
+                        d0[("m", "PL")] = d0.get(("m", "PL")) or fm
+    return nouns, adjs
+
+
+def _build_cache():
+    verbs, part, ger = _build_verbs()
+    nouns, adjs = _build_nouns_adjs()
+    with open(_IRREG, encoding="utf-8") as fh:
+        irreg = json.load(fh)
+    data = {"verbs": verbs, "part": part, "ger": ger,
+            "nouns": nouns, "adjs": adjs, "irreg": irreg}
+    try:
+        with open(_CACHE, "wb") as fh:
+            pickle.dump(data, fh, protocol=pickle.HIGHEST_PROTOCOL)
+    except OSError:
+        pass
+    return data
+
+
+def _load():
+    if os.path.exists(_CACHE):
+        srcs = [_UNIMORPH, _KAIKKI, _IRREG]
+        newest = max(os.path.getmtime(s) for s in srcs if os.path.exists(s))
+        if os.path.getmtime(_CACHE) >= newest:
+            try:
+                with open(_CACHE, "rb") as fh:
+                    return pickle.load(fh)
+            except Exception:
+                pass
+    return _build_cache()
+
+
+_LEX = _load()
+_VERBS, _PART, _GER, _NOUNS, _ADJS, _IRREGV = (
+    _LEX["verbs"], _LEX["part"], _LEX["ger"], _LEX["nouns"], _LEX["adjs"],
+    _LEX["irreg"])
+
+
+# ── regular-ending rule fallback ─────────────────────────────────────────────────
+def _vclass(lemma):
+    if lemma.endswith("er"):
+        return "er"
+    if lemma.endswith("ir"):
+        return "ir"
+    if lemma.endswith("re"):
+        return "re"
+    if lemma.endswith("oir"):
+        return "oir"
+    return None
+
+
+# present-tense endings [1sg,2sg,3sg,1pl,2pl,3pl]
+_REG_PRES = {
+    "er": ["e", "es", "e", "ons", "ez", "ent"],
+    "ir": ["is", "is", "it", "issons", "issez", "issent"],   # -iss- class (finir)
+    "re": ["s", "s", "", "ons", "ez", "ent"],                # vendre: vends/vend
+}
+_REG_IMPF = ["ais", "ais", "ait", "ions", "iez", "aient"]     # attaches to pres-1pl stem
+_REG_SUBJ = ["e", "es", "e", "ions", "iez", "ent"]           # attaches to 3pl stem
+_REG_PS = {   # passé simple
+    "er": ["ai", "as", "a", "âmes", "âtes", "èrent"],
+    "ir": ["is", "is", "it", "îmes", "îtes", "irent"],
+    "re": ["is", "is", "it", "îmes", "îtes", "irent"],
+}
+_FUT = ["ai", "as", "a", "ons", "ez", "ont"]
+_COND = ["ais", "ais", "ait", "ions", "iez", "aient"]
+
+
+def _slot_idx(person, number):
+    base = {"first": 0, "second": 1, "third": 2}[person]
+    return base + (0 if number == "singular" else 3)
+
+
+def _fut_stem(lemma, vc):
+    """Future/conditional stem = infinitive (drop final -e of -re)."""
+    if vc == "re":
+        return lemma[:-1]        # vendre -> vendr-
+    return lemma                 # parler-, finir-
+
+
+def _pres_1pl_stem(lemma, vc):
+    """Imparfait stem = present 1pl minus -ons (parlons->parl-, finissons->finiss-)."""
+    if vc == "er":
+        stem = lemma[:-2]
+        if stem.endswith("g"):
+            return stem + "e"    # mangeons -> mange-  (imparfait mangeais)
+        if stem.endswith("c"):
+            return stem[:-1] + "ç"   # commençons -> commenç-
+        return stem
+    if vc == "ir":
+        return lemma[:-1] + "iss"   # finir -> finiss-
+    if vc == "re":
+        return lemma[:-2]           # vendre -> vend-
+    return lemma[:-2]
+
+
+def _apply_er_spelling(stem, ending):
+    """-cer/-ger softening before a/o (commençons, mangeons)."""
+    if ending and ending[0] in ("a", "o"):
+        if stem.endswith("c"):
+            return stem[:-1] + "ç" + ending
+        if stem.endswith("g"):
+            return stem + "e" + ending
+    return stem + ending
+
+
+def _rule_conjugate(lemma, mood, tense, person, number):
+    vc = _vclass(lemma)
+    if vc is None:
+        return None
+    i = _slot_idx(person, number)
+
+    if mood == "ind" and tense in ("future", "conditional"):
+        stem = _fut_stem(lemma, vc)
+        end = (_FUT if tense == "future" else _COND)[i]
+        return stem + end
+
+    if mood == "ind" and tense == "present":
+        table = _REG_PRES.get("ir" if vc == "ir" else vc)
+        if not table:
+            return None
+        body = lemma[:-2] if vc in ("er", "re") else lemma[:-1] if vc == "ir" else lemma[:-2]
+        if vc == "ir":
+            body = lemma[:-2]        # fin- ; endings carry -iss-
+            end = table[i]
+            return body + end
+        end = table[i]
+        if vc == "er":
+            return _apply_er_spelling(body, end)
+        return body + end
+
+    if mood == "ind" and tense == "imperfect":
+        stem = _pres_1pl_stem(lemma, vc)
+        return stem + _REG_IMPF[i]
+
+    if mood == "ind" and tense == "passe_simple":
+        table = _REG_PS.get("ir" if vc == "ir" else vc)
+        if not table:
+            return None
+        body = lemma[:-2] if vc in ("er", "re") else lemma[:-2]
+        end = table[i]
+        if vc == "er":
+            return _apply_er_spelling(body, end)
+        return body + end
+
+    if mood == "sbjv" and tense == "present":
+        # subjonctif: present-3pl stem + e/es/e/ions/iez/ent
+        stem3 = _pres_1pl_stem(lemma, vc) if vc == "ir" else (
+            lemma[:-2] if vc in ("er", "re") else lemma[:-2])
+        if vc == "ir":
+            stem3 = lemma[:-2] + "iss"
+        end = _REG_SUBJ[i]
+        if vc == "er":
+            return _apply_er_spelling(stem3, end)
+        return stem3 + end
+
+    if mood == "imp" and tense == "affirmative":
+        # impératif ~ present indicative (tu drops -s for -er verbs)
+        pres = _rule_conjugate(lemma, "ind", "present", person, number)
+        if pres and vc == "er" and person == "second" and number == "singular":
+            return pres[:-1] if pres.endswith("es") else pres
+        return pres
+    return None
+
+
+# ── PUBLIC: verb conjugation ─────────────────────────────────────────────────────
+def conjugate(lemma, mood, tense, person, number):
+    """Return (surface, confidence)."""
+    lemma = lemma.strip().lower()
+    key = f"{mood}|{tense}|{_PERSON.get(person,'?')}|{number}"
+    ir = _IRREGV.get(lemma)
+    if ir and key in ir:
+        return ir[key], "lexicon"
+    p, n = _PERSON.get(person), _NUMBER.get(number)
+    if p and n:
+        form = _VERBS.get((lemma, f"{mood}|{tense}|{p}|{n}"))
+        if form:
+            return form, "lexicon"
+    r = _rule_conjugate(lemma, mood, tense, person, number)
+    if r:
+        return r, "rule"
+    return lemma, "fallback"
+
+
+# ── PUBLIC: participle + gerund/participe présent ────────────────────────────────
+def _participle_msg(lemma):
+    ir = _IRREGV.get(lemma)
+    if ir and "part" in ir:
+        return ir["part"], "lexicon"
+    if lemma in _PART:
+        return _PART[lemma], "lexicon"
+    return None, None
+
+
+# irregular participle fem/plural quirks (drop circonflexe: dû->due, dus)
+_PART_FIX = {"dû": {"f|SG": "due", "m|PL": "dus", "f|PL": "dues"}}
+
+
+def participle(lemma, gender="m", number="singular"):
+    """Past participle with French gender/number agreement.
+    m.sg = base;  f.sg = base+e;  m.pl = base+s (invariable if base ends s/x);
+    f.pl = f.sg+s."""
+    lemma = lemma.strip().lower()
+    g = "f" if gender == "f" else "m"
+    num = "SG" if number == "singular" else "PL"
+    msg, src = _participle_msg(lemma)
+    conf = "lexicon"
+    if msg is None:
+        vc = _vclass(lemma)
+        if vc == "er":
+            msg = lemma[:-2] + "é"
+        elif vc == "ir":
+            msg = lemma[:-1]          # finir -> fini, partir -> parti
+        elif vc == "re":
+            msg = lemma[:-2] + "u"    # vendre -> vendu
+        elif vc == "oir":
+            msg = lemma[:-3] + "u"    # (rough) recevoir handled by irreg
+        else:
+            return lemma, "fallback"
+        conf = "rule"
+    fix = _PART_FIX.get(msg)
+    if fix and f"{g}|{num}" in fix:
+        return fix[f"{g}|{num}"], conf
+    if g == "m" and num == "SG":
+        return msg, conf
+    fem = msg + "e" if not msg.endswith("e") else msg
+    if g == "f" and num == "SG":
+        return fem, conf
+    if g == "m" and num == "PL":
+        return msg if msg.endswith(("s", "x")) else msg + "s", conf
+    # f|PL
+    return fem + "s", conf
+
+
+def gerund(lemma):
+    """Participe présent (base for gérondif 'en -ant')."""
+    lemma = lemma.strip().lower()
+    ir = _IRREGV.get(lemma)
+    if ir and "ger" in ir:
+        return ir["ger"], "lexicon"
+    if lemma in _GER:
+        return _GER[lemma], "lexicon"
+    vc = _vclass(lemma)
+    if vc == "er":
+        stem = lemma[:-2]
+        if stem.endswith("g"):
+            return stem + "eant", "rule"
+        if stem.endswith("c"):
+            return stem[:-1] + "çant", "rule"
+        return stem + "ant", "rule"
+    if vc == "ir":
+        return lemma[:-2] + "issant", "rule"
+    if vc == "re":
+        return lemma[:-2] + "ant", "rule"
+    return lemma, "fallback"
+
+
+# ── PUBLIC: noun gender + number ─────────────────────────────────────────────────
+_FEM_SUF = ("tion", "sion", "aison", "ance", "ence", "ette", "elle", "esse",
+            "ude", "ade", "ée", "té", "tié", "ie", "ise", "ure", "eur")
+_MASC_SUF = ("ment", "age", "eau", "isme", "oir", "ier", "eur", "in", "on")
+
+
+def _gender_heuristic(noun):
+    for suf in _FEM_SUF:
+        if noun.endswith(suf):
+            return "f"
+    for suf in _MASC_SUF:
+        if noun.endswith(suf):
+            return "m"
+    if noun.endswith("e"):
+        return "f"
+    return "m"
+
+
+def noun_gender(lemma):
+    lemma = lemma.strip().lower()
+    d = _NOUNS.get(lemma)
+    if d and d.get("g") in ("m", "f"):
+        return d["g"]
+    return _gender_heuristic(lemma)
+
+
+# closed sets for French plural irregularities
+_OU_X = {"bijou", "caillou", "chou", "genou", "hibou", "joujou", "pou"}
+_AIL_AUX = {"travail", "vitrail", "corail", "émail", "bail", "soupirail", "vantail"}
+_AL_S = {"bal", "carnaval", "festival", "récital", "chacal", "régal", "cal", "aval"}
+
+
+def _rule_plural(noun, gender):
+    """Deterministic French pluralization. (form, ok); ok=False FLAGS ambiguity."""
+    if not noun:
+        return noun, True
+    if noun[-1:] in ("s", "x", "z"):
+        return noun, True                      # invariable
+    if noun in _OU_X:
+        return noun + "x", True
+    if noun.endswith(("eau", "au", "eu")):
+        if noun in ("pneu", "bleu", "landau", "sarrau"):
+            return noun + "s", True
+        return noun + "x", True                # bateau->bateaux, jeu->jeux
+    if noun.endswith("al"):
+        if noun in _AL_S:
+            return noun + "s", True
+        return noun[:-2] + "aux", True         # cheval->chevaux
+    if noun.endswith("ail"):
+        if noun in _AIL_AUX:
+            return noun[:-3] + "aux", True      # travail->travaux
+        return noun + "s", True
+    return noun + "s", True                     # default
+
+
+def inflect_noun(lemma, number, gender=None):
+    lemma = lemma.strip().lower()
+    d = _NOUNS.get(lemma)
+    if number == "singular":
+        return (d["SG"] if d and d.get("SG") else lemma), ("lexicon" if d else "rule")
+    if d and d.get("PL"):
+        return d["PL"], "lexicon"
+    g = gender or noun_gender(lemma)
+    form, ok = _rule_plural(lemma, g)
+    return form, ("rule" if ok else "fallback")
+
+
+# adjectives whose kaikki entries are unreliable: audited forms
+_ADJ_FIX = {
+    "beau": {("m", "SG"): "beau", ("f", "SG"): "belle",
+             ("m", "PL"): "beaux", ("f", "PL"): "belles"},
+    "nouveau": {("m", "SG"): "nouveau", ("f", "SG"): "nouvelle",
+                ("m", "PL"): "nouveaux", ("f", "PL"): "nouvelles"},
+    "vieux": {("m", "SG"): "vieux", ("f", "SG"): "vieille",
+              ("m", "PL"): "vieux", ("f", "PL"): "vieilles"},
+    "fou": {("m", "SG"): "fou", ("f", "SG"): "folle",
+            ("m", "PL"): "fous", ("f", "PL"): "folles"},
+    "blanc": {("m", "SG"): "blanc", ("f", "SG"): "blanche",
+              ("m", "PL"): "blancs", ("f", "PL"): "blanches"},
+    "long": {("m", "SG"): "long", ("f", "SG"): "longue",
+             ("m", "PL"): "longs", ("f", "PL"): "longues"},
+    "bon": {("m", "SG"): "bon", ("f", "SG"): "bonne",
+            ("m", "PL"): "bons", ("f", "PL"): "bonnes"},
+}
+
+
+def _rule_fem(a):
+    if a.endswith("e"):
+        return a
+    if a.endswith("er"):
+        return a[:-2] + "ère"
+    if a.endswith("eau"):
+        return a[:-3] + "elle"
+    if a.endswith("eux"):
+        return a[:-3] + "euse"
+    if a.endswith("f"):
+        return a[:-1] + "ve"
+    if a.endswith(("on", "en", "el", "eil", "et")):
+        return a + a[-1] + "e"        # bon->bonne, ancien->ancienne, muet->muette
+    if a.endswith("c"):
+        return a[:-1] + "che"         # blanc->blanche (public->publique via FIX)
+    return a + "e"                    # grand->grande, petit->petite, vert->verte
+
+
+def inflect_adj(lemma, gender, number):
+    lemma = lemma.strip().lower()
+    g = "f" if gender == "f" else "m"
+    num = "SG" if number == "singular" else "PL"
+    fix = _ADJ_FIX.get(lemma)
+    if fix and (g, num) in fix:
+        return fix[(g, num)], "lexicon"
+    d = _ADJS.get(lemma)
+    if d and d.get((g, num)):
+        return d[(g, num)], "lexicon"
+    # derive
+    msc = (d.get(("m", "SG")) if d else None) or lemma
+    if g == "m" and num == "SG":
+        return msc, "lexicon" if d else "rule"
+    fem = (d.get(("f", "SG")) if d else None) or _rule_fem(msc)
+    if g == "f" and num == "SG":
+        return fem, "lexicon" if (d and d.get(("f", "SG"))) else "rule"
+    if g == "m" and num == "PL":
+        if msc.endswith(("s", "x")):
+            return msc, "rule"
+        if msc.endswith("al"):
+            return msc[:-2] + "aux", "rule"
+        if msc.endswith("eau"):
+            return msc + "x", "rule"
+        return msc + "s", "rule"
+    # f|PL
+    return (fem if fem.endswith("s") else fem + "s"), "rule"
+
+
+def lexicon_stats():
+    return {
+        "verb_source": "UniMorph French (github.com/unimorph/fra) + kaikki.org "
+                       "irregulars (être + high-frequency)",
+        "noun_adj_source": "kaikki.org French (Wiktionary extract)",
+        "license": "CC-BY-SA 3.0 (Wiktionary/UniMorph lineage)",
+        "unimorph_verb_forms": len(_VERBS),
+        "unimorph_verb_lemmas": len({k[0] for k in _VERBS}),
+        "irregular_verb_lemmas": len(_IRREGV),
+        "participle_lemmas": len(_PART),
+        "gerund_lemmas": len(_GER),
+        "noun_lemmas": len(_NOUNS),
+        "adj_lemmas": len(_ADJS),
+    }
+
+
+if __name__ == "__main__":
+    print(json.dumps(lexicon_stats(), indent=2, ensure_ascii=False))
+    tests = [
+        ("parler", "ind", "present", "first", "singular", "parle"),
+        ("être", "ind", "present", "third", "singular", "est"),
+        ("avoir", "ind", "present", "first", "singular", "ai"),
+        ("aller", "ind", "present", "third", "plural", "vont"),
+        ("finir", "ind", "present", "first", "singular", "finis"),
+        ("finir", "ind", "present", "first", "plural", "finissons"),
+        ("manger", "ind", "present", "first", "plural", "mangeons"),
+        ("faire", "ind", "future", "first", "singular", "ferai"),
+        ("pouvoir", "sbjv", "present", "third", "singular", "puisse"),
+        ("prendre", "ind", "passe_simple", "third", "singular", "prit"),
+        ("vendre", "ind", "present", "third", "singular", "vend"),
+        ("commencer", "ind", "imperfect", "first", "singular", "commençais"),
+    ]
+    ok = 0
+    for lemma, mood, tense, per, num, exp in tests:
+        got, conf = conjugate(lemma, mood, tense, per, num)
+        flag = "OK " if got == exp else "XX "
+        ok += got == exp
+        print(f"  {flag}{lemma:10} {mood}/{tense:12} {per[:3]}.{num[:2]} -> {got:12} ({conf}) exp={exp}")
+    print(f"verb tests {ok}/{len(tests)}")
+    print("  gender: maison=", noun_gender("maison"), "chat=", noun_gender("chat"),
+          "cheval=", noun_gender("cheval"), "nation=", noun_gender("nation"))
+    print("  plural: cheval->", inflect_noun("cheval", "plural"),
+          "| bateau->", inflect_noun("bateau", "plural"),
+          "| prix->", inflect_noun("prix", "plural"),
+          "| chat->", inflect_noun("chat", "plural"))
+    print("  adj: petit/f/sg->", inflect_adj("petit", "f", "singular"),
+          "| beau/f/sg->", inflect_adj("beau", "f", "singular"),
+          "| heureux/f/sg->", inflect_adj("heureux", "f", "singular"),
+          "| national/m/pl->", inflect_adj("national", "m", "plural"))
+    print("  part: aller/f/sg->", participle("aller", "f", "singular"),
+          "| prendre/f/pl->", participle("prendre", "f", "plural"),
+          "| finir/m/pl->", participle("finir", "m", "plural"))
+    print("  ger: manger->", gerund("manger"), "| finir->", gerund("finir"))

elp/tests/lang-gen/morphology_it_full.py

@@ -0,0 +1,588 @@
+"""morphology_it_full.py — production-grade Italian morphological generator.
+
+NOT a toy. Backed by three real, Wiktionary-lineage lexical sources:
+
+  VERBS
+    UniMorph Italian (github.com/unimorph/ita, CC-BY-SA 3.0)
+      10,009 verb lemmas × full paradigm, CLEAN orthography (no stress marks):
+        indicative present / imperfetto (PST;IPFV) / passato remoto (PST;PFV) /
+                   futuro, condizionale (COND),
+        congiuntivo presente (SBJV;PRS) / imperfetto (SBJV;PST),
+        affirmative imperative, infinitive, gerundio (V.CVB;PRS),
+        past participle (masc-sg; fem/plural derived by vowel rule).
+    it_irreg_verbs.json — 66 high-frequency verbs UniMorph MISSES
+      (essere, avere, potere, uscire, tenere, prendere, piacere, …), extracted
+      from kaikki.org Italian, filtered to standard forms, and DE-STRESSED to
+      real orthography (kaikki marks tonic stress everywhere: pàrlo->parlo,
+      avùto->avuto; final legit accents kept: sarò, è). Built by build_it_irreg.py.
+      This layer takes priority — it supplies the two auxiliaries essere/avere,
+      which the whole passato-prossimo / essere-agreement system depends on.
+
+  NOUNS + ADJECTIVES — kaikki.org Italian (Wiktionary extract, CC-BY-SA 3.0)
+    noun lemmas WITH inherent gender (head-template arg) + real (often irregular)
+      plural — uomo->uomini, uovo->uova, dito->dita, città invariant — resolved
+      PER LEMMA, never guessed.
+    adjective lemmas with real feminine + masc/fem plural (italiano->italiana/
+      italiani/italiane, felice->felici invariant).
+
+Fallbacks (degrade, never crash, on OOV input):
+  verbs : rule generator for regular -are/-ere/-ire (with -care/-gare h-insertion
+          and -ciare/-giare/-iare i-drop spelling rules)
+  nouns : gender heuristic (endings) + rule pluralization (ambiguous -co/-go FLAGGED)
+  adjs  : -o/-a/-e gender rule + rule pluralization
+
+Confidence flag on every form:
+  "lexicon"  from UniMorph / kaikki-irregular / kaikki noun-adj   (trust: high)
+  "rule"     deterministic rule                                   (trust: medium)
+  "fallback" could not inflect; returned lemma / ambiguous        (trust: low -> FLAG)
+
+Public API (used by realizer_it.py):
+  conjugate(lemma, mood, tense, person, number) -> (form, conf)
+  participle(lemma, gender="m", number="singular") -> (form, conf)
+  gerund(lemma) -> (form, conf)
+  noun_gender(lemma) -> "m"|"f"
+  inflect_noun(lemma, number, gender=None) -> (form, conf)
+  inflect_adj(lemma, gender, number) -> (form, conf)
+  lexicon_stats() -> dict
+"""
+import json
+import os
+import pickle
+
+_HERE = os.path.dirname(os.path.abspath(__file__))
+_UNIMORPH = os.path.join(_HERE, "data", "ita.unimorph")
+_IRREG = os.path.join(_HERE, "data", "it_irreg_verbs.json")
+_KAIKKI = os.path.join(_HERE, "data", "kaikki_it.jsonl")
+_CACHE = os.path.join(_HERE, "data", "it_morph_cache.pkl")
+
+# ── (mood, tense) -> UniMorph feature set that must ALL be present ────────────────
+_VERB_KEYMAP = {
+    ("ind", "present"):        {"IND", "PRS"},
+    ("ind", "imperfect"):      {"IND", "PST", "IPFV"},
+    ("ind", "passato_remoto"): {"IND", "PST", "PFV"},
+    ("ind", "future"):         {"IND", "FUT"},
+    ("ind", "conditional"):    {"COND"},
+    ("sbjv", "present"):       {"SBJV", "PRS"},
+    ("sbjv", "imperfect"):     {"SBJV", "PST"},
+    ("imp", "affirmative"):    {"POS", "IMP"},
+}
+_PERSON = {"first": "1", "second": "2", "third": "3"}
+_NUMBER = {"singular": "SG", "plural": "PL"}
+
+
+def _feat_set(tag):
+    return set(tag.split(";"))
+
+
+# ── build verb lexicon from UniMorph ─────────────────────────────────────────────
+def _build_verbs():
+    verbs = {}   # (lemma, "mood|tense|person|number") -> form
+    part = {}    # lemma -> masc-sg past participle
+    ger = {}     # lemma -> gerundio
+    with open(_UNIMORPH, encoding="utf-8") as fh:
+        for line in fh:
+            line = line.rstrip("\n")
+            if not line or "\t" not in line:
+                continue
+            parts = line.split("\t")
+            if len(parts) != 3:
+                continue
+            lemma, form, tag = parts
+            f = _feat_set(tag)
+            head = tag.split(";")[0]
+
+            if head == "V.PTCP":
+                if "PST" in f:
+                    part.setdefault(lemma, form)
+                continue
+            if head == "V.CVB":         # gerundio (converb, present)
+                if "PRS" in f:
+                    ger.setdefault(lemma, form)
+                continue
+            if head != "V":
+                continue
+
+            person = next((p for p in ("1", "2", "3") if p in f), None)
+            number = "SG" if "SG" in f else ("PL" if "PL" in f else None)
+            if person is None or number is None:
+                continue
+            for (mood, tense), req in _VERB_KEYMAP.items():
+                # exact-set discipline: PST;PFV must not match PST;IPFV, etc.
+                if not req <= f:
+                    continue
+                # guard IND;PST ambiguity: require the specific aspect feature
+                if tense == "imperfect" and "PFV" in f:
+                    continue
+                if tense == "passato_remoto" and "IPFV" in f:
+                    continue
+                # COND must not also be a subjunctive/imperative slot
+                verbs.setdefault((lemma, f"{mood}|{tense}|{person}|{number}"), form)
+                break
+    return verbs, part, ger
+
+
+# ── kaikki nouns + adjectives ────────────────────────────────────────────────────
+_EXCL_FORM_TAGS = {"alternative", "archaic", "obsolete", "dialectal", "regional",
+                   "diminutive", "augmentative", "pejorative", "comparative",
+                   "superlative", "misspelling", "rare", "informal", "literary",
+                   "poetic", "error-unrecognized-form", "apocopic", "obsolete",
+                   "construed", "collective"}
+
+
+def _kaikki_gender(arg):
+    if not arg:
+        return None
+    a = str(arg).lower()
+    if a.startswith("f"):
+        return "f"
+    if a.startswith("m"):
+        return "m"
+    return None
+
+
+def _build_nouns_adjs():
+    nouns = {}   # lemma -> {"g","SG","PL"}
+    adjs = {}    # lemma -> {("m","SG"),("f","SG"),("m","PL"),("f","PL")}
+    with open(_KAIKKI, encoding="utf-8") as fh:
+        for line in fh:
+            try:
+                d = json.loads(line)
+            except Exception:
+                continue
+            pos = d.get("pos")
+            word = d.get("word", "")
+            if not word or " " in word:
+                continue
+            forms = d.get("forms", []) or []
+
+            if pos == "noun":
+                ht = d.get("head_templates") or []
+                g = None
+                if ht:
+                    g = _kaikki_gender((ht[0].get("args") or {}).get("1"))
+                if g is None:
+                    tags = d.get("tags") or []
+                    if "feminine" in tags:
+                        g = "f"
+                    elif "masculine" in tags:
+                        g = "m"
+                pl = None
+                for x in forms:
+                    t = set(x.get("tags") or [])
+                    if "plural" in t and not (t & _EXCL_FORM_TAGS):
+                        fm = x.get("form")
+                        if fm and " " not in fm and fm != "#":
+                            pl = fm
+                            break
+                if word not in nouns:
+                    nouns[word] = {"g": g, "SG": word, "PL": pl}
+                else:
+                    cur = nouns[word]
+                    if cur.get("g") is None and g:
+                        cur["g"] = g
+                    if not cur.get("PL") and pl:
+                        cur["PL"] = pl
+
+            elif pos == "adj":
+                d0 = adjs.setdefault(word, {})
+                d0.setdefault(("m", "SG"), word)
+                for x in forms:
+                    t = set(x.get("tags") or [])
+                    fm = x.get("form")
+                    if not fm or " " in fm or (t & _EXCL_FORM_TAGS):
+                        continue
+                    if "feminine" in t and "plural" in t:
+                        d0[("f", "PL")] = d0.get(("f", "PL")) or fm
+                    elif "masculine" in t and "plural" in t:
+                        d0[("m", "PL")] = d0.get(("m", "PL")) or fm
+                    elif "feminine" in t:
+                        d0[("f", "SG")] = d0.get(("f", "SG")) or fm
+                    elif "plural" in t:   # invariant-gender adj (felice -> felici)
+                        d0[("m", "PL")] = d0.get(("m", "PL")) or fm
+                        d0[("f", "PL")] = d0.get(("f", "PL")) or fm
+    return nouns, adjs
+
+
+def _build_cache():
+    verbs, part, ger = _build_verbs()
+    nouns, adjs = _build_nouns_adjs()
+    with open(_IRREG, encoding="utf-8") as fh:
+        irreg = json.load(fh)
+    data = {"verbs": verbs, "part": part, "ger": ger,
+            "nouns": nouns, "adjs": adjs, "irreg": irreg}
+    try:
+        with open(_CACHE, "wb") as fh:
+            pickle.dump(data, fh, protocol=pickle.HIGHEST_PROTOCOL)
+    except OSError:
+        pass
+    return data
+
+
+def _load():
+    if os.path.exists(_CACHE):
+        srcs = [_UNIMORPH, _KAIKKI, _IRREG]
+        newest = max(os.path.getmtime(s) for s in srcs if os.path.exists(s))
+        if os.path.getmtime(_CACHE) >= newest:
+            try:
+                with open(_CACHE, "rb") as fh:
+                    return pickle.load(fh)
+            except Exception:
+                pass
+    return _build_cache()
+
+
+_LEX = _load()
+_VERBS, _PART, _GER, _NOUNS, _ADJS, _IRREGV = (
+    _LEX["verbs"], _LEX["part"], _LEX["ger"], _LEX["nouns"], _LEX["adjs"],
+    _LEX["irreg"])
+
+
+# ── regular-ending rule fallback ─────────────────────────────────────────────────
+def _vclass(lemma):
+    if lemma.endswith("are"):
+        return "are"
+    if lemma.endswith("ere"):
+        return "ere"
+    if lemma.endswith("ire"):
+        return "ire"
+    return None
+
+
+# endings [1sg,2sg,3sg,1pl,2pl,3pl]
+_REG = {
+    ("ind", "present", "are"): ["o", "i", "a", "iamo", "ate", "ano"],
+    ("ind", "present", "ere"): ["o", "i", "e", "iamo", "ete", "ono"],
+    ("ind", "present", "ire"): ["o", "i", "e", "iamo", "ite", "ono"],
+    ("ind", "imperfect", "are"): ["avo", "avi", "ava", "avamo", "avate", "avano"],
+    ("ind", "imperfect", "ere"): ["evo", "evi", "eva", "evamo", "evate", "evano"],
+    ("ind", "imperfect", "ire"): ["ivo", "ivi", "iva", "ivamo", "ivate", "ivano"],
+    ("ind", "passato_remoto", "are"): ["ai", "asti", "ò", "ammo", "aste", "arono"],
+    ("ind", "passato_remoto", "ere"): ["ei", "esti", "é", "emmo", "este", "erono"],
+    ("ind", "passato_remoto", "ire"): ["ii", "isti", "ì", "immo", "iste", "irono"],
+    ("sbjv", "present", "are"): ["i", "i", "i", "iamo", "iate", "ino"],
+    ("sbjv", "present", "ere"): ["a", "a", "a", "iamo", "iate", "ano"],
+    ("sbjv", "present", "ire"): ["a", "a", "a", "iamo", "iate", "ano"],
+    ("sbjv", "imperfect", "are"): ["assi", "assi", "asse", "assimo", "aste", "assero"],
+    ("sbjv", "imperfect", "ere"): ["essi", "essi", "esse", "essimo", "este", "essero"],
+    ("sbjv", "imperfect", "ire"): ["issi", "issi", "isse", "issimo", "iste", "issero"],
+    # imperative: 2sg,3sg(Lei),1pl,2pl,3pl  (1sg has none)
+    ("imp", "affirmative", "are"): [None, "a", "i", "iamo", "ate", "ino"],
+    ("imp", "affirmative", "ere"): [None, "i", "a", "iamo", "ete", "ano"],
+    ("imp", "affirmative", "ire"): [None, "i", "a", "iamo", "ite", "ano"],
+}
+# future / conditional attach to a stem = infinitive minus final -e, with
+# -are -> -er (parlare->parler-), -ere/-ire keep (credere->creder-, dormir-)
+_FUT = ["ò", "ai", "à", "emo", "ete", "anno"]
+_COND = ["ei", "esti", "ebbe", "emmo", "este", "ebbero"]
+
+
+def _slot_idx(person, number):
+    base = {"first": 0, "second": 1, "third": 2}[person]
+    return base + (0 if number == "singular" else 3)
+
+
+def _fut_stem(lemma, vc):
+    body = lemma[:-3]           # drop are/ere/ire
+    if vc == "are":
+        return body + "er"
+    return body + vc[0] + "r"   # ere->er? no: keep vowel: creder-, dormir-
+    # NOTE corrected below
+
+
+def _apply_are_spelling(stem, ending):
+    """-care/-gare insert h before front endings; -ciare/-giare/-sciare/-iare drop i."""
+    front = ending[:1] in ("i", "e")
+    if stem.endswith(("c", "g")) and front:
+        return stem + "h" + ending
+    if stem.endswith(("ci", "gi", "sci")) and ending[:1] == "i":
+        return stem[:-1] + ending          # mangi+iamo -> mangiamo
+    if stem.endswith("i") and ending[:1] == "i":
+        return stem[:-1] + ending          # studi+iamo -> studiamo
+    return stem + ending
+
+
+def _rule_conjugate(lemma, mood, tense, person, number):
+    vc = _vclass(lemma)
+    if vc is None:
+        return None
+    body = lemma[:-3]
+    i = _slot_idx(person, number)
+    if mood == "ind" and tense in ("future", "conditional"):
+        stem = body + "er" if vc == "are" else body + vc[0] + "r"
+        # ere: creder-, ire: dormir-  -> body + 'e'/'i' + 'r'
+        if vc == "ere":
+            stem = body + "er"
+        elif vc == "ire":
+            stem = body + "ir"
+        end = (_FUT if tense == "future" else _COND)[i]
+        # spelling: -care/-gare -> cherò/gherò ; -ciare/-giare -> cerò/gerò
+        if vc == "are":
+            if body.endswith(("c", "g")):
+                stem = body + "her"
+            elif body.endswith(("ci", "gi", "sci")):
+                stem = body[:-1] + "er"
+            elif body.endswith("i"):
+                stem = body[:-1] + "er"
+        return stem + end
+    table = _REG.get((mood, tense, vc))
+    if not table:
+        return None
+    end = table[i]
+    if end is None:
+        return None
+    if vc == "are":
+        return _apply_are_spelling(body, end)
+    # -ere/-ire: guard against double-i (dormi+iamo -> dormiamo)
+    if body.endswith("i") and end[:1] == "i":
+        return body[:-1] + end
+    return body + end
+
+
+# ── PUBLIC: verb conjugation ─────────────────────────────────────────────────────
+def conjugate(lemma, mood, tense, person, number):
+    """Return (surface, confidence). mood in ind|sbjv|imp; tense per _VERB_KEYMAP."""
+    lemma = lemma.strip().lower()
+    key = f"{mood}|{tense}|{_PERSON.get(person,'?')}|{number}"
+    ir = _IRREGV.get(lemma)
+    if ir and key in ir:
+        return ir[key], "lexicon"
+    p, n = _PERSON.get(person), _NUMBER.get(number)
+    if p and n:
+        form = _VERBS.get((lemma, f"{mood}|{tense}|{p}|{n}"))
+        if form:
+            return form, "lexicon"
+    r = _rule_conjugate(lemma, mood, tense, person, number)
+    if r:
+        return r, "rule"
+    return lemma, "fallback"
+
+
+# ── PUBLIC: participle + gerund ──────────────────────────────────────────────────
+def _participle_msg(lemma):
+    """Return (masc-sg participle, source) or (None, None)."""
+    ir = _IRREGV.get(lemma)
+    if ir and "part" in ir:
+        return ir["part"], "lexicon"
+    if lemma in _PART:
+        return _PART[lemma], "lexicon"
+    return None, None
+
+
+def participle(lemma, gender="m", number="singular"):
+    """Past participle with gender/number agreement (for essere-perfect & passives).
+    UniMorph/irregular give masc-sg; fem/plural derived by final-vowel swap
+    (-o -> -a/-i/-e), valid for regular -ato/-uto/-ito AND irregulars
+    (preso->presa/presi/prese, aperto->aperta/aperti/aperte, morto->morta/...)."""
+    lemma = lemma.strip().lower()
+    g = "f" if gender == "f" else "m"
+    num = "SG" if number == "singular" else "PL"
+    msg, src = _participle_msg(lemma)
+    conf = "lexicon"
+    if msg is None:
+        vc = _vclass(lemma)
+        if vc == "are":
+            msg = lemma[:-3] + "ato"
+        elif vc == "ere":
+            msg = lemma[:-3] + "uto"
+        elif vc == "ire":
+            msg = lemma[:-3] + "ito"
+        else:
+            return lemma, "fallback"
+        conf = "rule"
+    # agreement: only -o participles inflect for gender+number
+    if msg.endswith("o"):
+        stem = msg[:-1]
+        suf = {"m|SG": "o", "f|SG": "a", "m|PL": "i", "f|PL": "e"}[f"{g}|{num}"]
+        return stem + suf, conf
+    return msg, conf   # non -o participle: leave as-is (rare)
+
+
+def gerund(lemma):
+    lemma = lemma.strip().lower()
+    ir = _IRREGV.get(lemma)
+    if ir and "ger" in ir:
+        return ir["ger"], "lexicon"
+    if lemma in _GER:
+        return _GER[lemma], "lexicon"
+    vc = _vclass(lemma)
+    if vc == "are":
+        return lemma[:-3] + "ando", "rule"
+    if vc in ("ere", "ire"):
+        return lemma[:-3] + "endo", "rule"
+    return lemma, "fallback"
+
+
+# ── PUBLIC: noun gender + number ─────────────────────────────────────────────────
+_FEM_SUF = ("zione", "sione", "gione", "tà", "tù", "trice", "aggine", "udine",
+            "igine", "ie", "essa", "izia", "ezza")
+_MASC_SUF = ("ore", "ame", "iere", "ale", "ile")
+
+
+def _gender_heuristic(noun):
+    for suf in _FEM_SUF:
+        if noun.endswith(suf):
+            return "f"
+    for suf in _MASC_SUF:
+        if noun.endswith(suf):
+            return "m"
+    if noun.endswith("o"):
+        return "m"
+    if noun.endswith("a"):
+        return "f"
+    if noun.endswith("à") or noun.endswith("ù"):
+        return "f"
+    return "m"        # -e and consonant-final loanwords default masculine
+
+
+def noun_gender(lemma):
+    lemma = lemma.strip().lower()
+    d = _NOUNS.get(lemma)
+    if d and d.get("g") in ("m", "f"):
+        return d["g"]
+    return _gender_heuristic(lemma)
+
+
+def _rule_plural(noun, gender):
+    """Deterministic Italian pluralization. Returns (form, ok); ok=False FLAGS an
+    ambiguous case the lexicon would normally resolve (-co/-go palatalization)."""
+    if not noun:
+        return noun, True
+    # invariant: accented final vowel, consonant-final, monosyllable, -i final
+    if noun[-1:] in ("à", "è", "é", "ì", "í", "ò", "ó", "ù", "ú"):
+        return noun, True
+    if noun[-1:] not in ("a", "e", "o", "i", "u"):
+        return noun, True            # consonant-final loanword: invariant
+    if noun.endswith("i"):
+        return noun, True            # e.g. crisi, analisi: invariant
+    if noun.endswith("io"):
+        return noun[:-2] + "i", True          # figlio->figli (unstressed i)
+    if noun.endswith("cia") or noun.endswith("gia"):
+        # vowel before cia/gia -> -cie/-gie ; consonant -> -ce/-ge (approx)
+        return noun[:-2] + "e", True          # arancia->arance (majority)
+    if noun.endswith("ca"):
+        return noun[:-2] + "che", True         # amica->amiche
+    if noun.endswith("ga"):
+        return noun[:-2] + "ghe", True
+    if noun.endswith("co"):
+        return noun[:-2] + "chi", False        # AMBIGUOUS (amico->amici) -> flag
+    if noun.endswith("go"):
+        return noun[:-2] + "ghi", False        # AMBIGUOUS (psicologo->psicologi)
+    if noun.endswith("a"):
+        return noun[:-1] + "e", True           # casa->case (m -a: -i, but rare)
+    if noun.endswith("o"):
+        return noun[:-1] + "i", True           # libro->libri
+    if noun.endswith("e"):
+        return noun[:-1] + "i", True           # cane->cani, chiave->chiavi
+    return noun, True
+
+
+def inflect_noun(lemma, number, gender=None):
+    lemma = lemma.strip().lower()
+    d = _NOUNS.get(lemma)
+    if number == "singular":
+        return (d["SG"] if d and d.get("SG") else lemma), ("lexicon" if d else "rule")
+    if d and d.get("PL"):
+        return d["PL"], "lexicon"
+    g = gender or noun_gender(lemma)
+    form, ok = _rule_plural(lemma, g)
+    return form, ("rule" if ok else "fallback")
+
+
+# adjectives whose kaikki entries are unreliable (messy inflection templates):
+# supply audited regular agreement forms (prenominal apocope handled in realizer).
+_ADJ_FIX = {
+    "bello": {("m", "SG"): "bello", ("f", "SG"): "bella",
+              ("m", "PL"): "belli", ("f", "PL"): "belle"},
+    "quello": {("m", "SG"): "quello", ("f", "SG"): "quella",
+               ("m", "PL"): "quelli", ("f", "PL"): "quelle"},
+}
+
+
+# ── PUBLIC: adjective agreement ──────────────────────────────────────────────────
+def inflect_adj(lemma, gender, number):
+    lemma = lemma.strip().lower()
+    g = "f" if gender == "f" else "m"
+    num = "SG" if number == "singular" else "PL"
+    fix = _ADJ_FIX.get(lemma)
+    if fix and (g, num) in fix:
+        return fix[(g, num)], "lexicon"
+    d = _ADJS.get(lemma)
+    if d:
+        form = d.get((g, num))
+        if form:
+            return form, "lexicon"
+        sg = d.get((g, "SG")) or d.get(("m", "SG")) or lemma
+        if num == "PL":
+            pl, ok = _rule_plural(sg, g)
+            return pl, ("rule" if ok else "fallback")
+        return sg, "lexicon"
+    # rule fallback
+    a = lemma
+    if a.endswith("o"):                      # -o/-a/-i/-e class
+        base = a[:-1]
+        suf = {"m|SG": "o", "f|SG": "a", "m|PL": "i", "f|PL": "e"}[f"{g}|{num}"]
+        return base + suf, "rule"
+    if a.endswith("e"):                      # felice-class: SG invariant, PL -i
+        if num == "PL":
+            return a[:-1] + "i", "rule"
+        return a, "rule"
+    if num == "PL":
+        p, ok = _rule_plural(a, g)
+        return p, ("rule" if ok else "fallback")
+    return a, "rule"
+
+
+def lexicon_stats():
+    return {
+        "verb_source": "UniMorph Italian (github.com/unimorph/ita) + kaikki.org "
+                       "irregulars (de-stressed)",
+        "noun_adj_source": "kaikki.org Italian (Wiktionary extract)",
+        "license": "CC-BY-SA 3.0 (Wiktionary/UniMorph lineage)",
+        "unimorph_verb_forms": len(_VERBS),
+        "unimorph_verb_lemmas": len({k[0] for k in _VERBS}),
+        "irregular_verb_lemmas": len(_IRREGV),
+        "participle_lemmas": len(_PART),
+        "gerund_lemmas": len(_GER),
+        "noun_lemmas": len(_NOUNS),
+        "adj_lemmas": len(_ADJS),
+    }
+
+
+if __name__ == "__main__":
+    print(json.dumps(lexicon_stats(), indent=2, ensure_ascii=False))
+    tests = [
+        ("parlare", "ind", "present", "first", "singular", "parlo"),
+        ("essere", "ind", "present", "third", "singular", "è"),
+        ("avere", "ind", "present", "first", "singular", "ho"),
+        ("mangiare", "ind", "present", "second", "singular", "mangi"),
+        ("finire", "ind", "present", "first", "singular", "finisco"),
+        ("andare", "ind", "present", "third", "plural", "vanno"),
+        ("fare", "ind", "future", "first", "singular", "farò"),
+        ("potere", "sbjv", "present", "third", "singular", "possa"),
+        ("prendere", "ind", "passato_remoto", "first", "singular", "presi"),
+        ("cercare", "ind", "present", "second", "singular", "cerchi"),
+        ("dormire", "ind", "present", "third", "plural", "dormono"),
+        ("credere", "ind", "future", "first", "singular", "crederò"),
+    ]
+    ok = 0
+    for lemma, mood, tense, per, num, exp in tests:
+        got, conf = conjugate(lemma, mood, tense, per, num)
+        flag = "OK " if got == exp else "XX "
+        ok += got == exp
+        print(f"  {flag}{lemma:9} {mood}/{tense:14} {per[:3]}.{num[:2]} -> {got:12} ({conf}) exp={exp}")
+    print(f"verb tests {ok}/{len(tests)}")
+    print("  gender: casa=", noun_gender("casa"), "problema=", noun_gender("problema"),
+          "mano=", noun_gender("mano"), "città=", noun_gender("città"),
+          "cane=", noun_gender("cane"))
+    print("  plural: uomo->", inflect_noun("uomo", "plural"),
+          "| uovo->", inflect_noun("uovo", "plural"),
+          "| città->", inflect_noun("città", "plural"),
+          "| amico->", inflect_noun("amico", "plural"),
+          "| casa->", inflect_noun("casa", "plural"))
+    print("  adj: italiano/f/pl->", inflect_adj("italiano", "f", "plural"),
+          "| felice/m/pl->", inflect_adj("felice", "m", "plural"),
+          "| bello/f/sg->", inflect_adj("bello", "f", "singular"))
+    print("  part: aprire/f/sg->", participle("aprire", "f", "singular"),
+          "| prendere/m/pl->", participle("prendere", "m", "plural"),
+          "| andare/f/sg->", participle("andare", "f", "singular"))
+    print("  ger: fare->", gerund("fare"), "| parlare->", gerund("parlare"))

elp/tests/lang-gen/morphology_lat_full.py

@@ -0,0 +1,666 @@
+# -*- coding: utf-8 -*-
+"""morphology_lat_full.py — production-grade Latin morphological generator.
+
+Latin is the FLAGSHIP dead-language realizer. It rides the *architecture* of the
+Romance/Italic engine (the same Realization / spec-driven design and the UniMorph
+loader pattern from morphology_it_full.py) but with the CASE SYSTEM RESTORED —
+the feature Romance lost. Latin therefore exercises machinery the modern Romance
+siblings never needed: 5 declensions x 6 cases x 2 numbers x 3 genders, plus a
+4-conjugation verb system with tense/mood/voice.
+
+DATA (real, attested — no fabrication):
+
+  NOUNS + ADJECTIVES — UniMorph Latin (github.com/unimorph/lat, CC-BY-SA 3.0)
+    163,182 N forms across ~thousands of lemmas, each with the full case paradigm
+      N;NOM/GEN/DAT/ACC/ABL/VOC;SG/PL  (real inflected forms, WITH macrons:
+      puella->puellam, rēx->rēgis, corpus->corporis).
+    244,197 ADJ forms with case x GENDER x number, incl. UniMorph's combined
+      tags (GEN+DAT, MASC+FEM, MASC+FEM+NEUT) which are split on load.
+    462,668 V.PTCP forms (participles) also carry case/gender/number.
+    UniMorph N tags DO NOT encode inherent gender, so noun gender is inferred
+      from the declension (nom-sg + gen-sg endings) with a curated exceptions
+      map — the standard, attestable rule (1st decl -a/-ae = fem, 2nd -us/-i =
+      masc, -um = neut, ...).
+
+  VERBS — RULE ENGINE (honest gap: UniMorph Latin's verb list is a 947-lemma
+    sample of rare/prefixed verbs that MISSES every core textbook verb — amō,
+    videō, sum, regō, ... are all absent). Latin conjugation is, however, highly
+    regular, so verbs are generated by a deterministic 4-conjugation engine over
+    curated principal parts (present / perfect / supine stems), sourced from
+    standard references. Irregulars (sum, possum, eō, ferō, volō, nōlō, mālō)
+    are curated full tables. Forms are flagged "rule" (not "lexicon") for honesty.
+
+Confidence flag on every form (same contract as the Romance engine):
+  "lexicon"  from UniMorph                         (trust: high)
+  "rule"     deterministic morphology rule         (trust: medium)
+  "fallback" could not inflect; returned lemma     (trust: low -> FLAG)
+
+Public API (used by realizer_lat.py):
+  decline_noun(lemma, case, number) -> (form, conf)
+  noun_gender(lemma) -> "m"|"f"|"n"
+  decline_adj(lemma, case, gender, number) -> (form, conf)
+  conjugate(lemma, tense, mood, voice, person, number) -> (form, conf)
+  participle(lemma, kind, case, gender, number) -> (form, conf)   # kind: prs|pfv|fut
+  infinitive(lemma, tense="present", voice="active") -> (form, conf)
+  lexicon_stats() -> dict
+"""
+import os
+import pickle
+
+_HERE = os.path.dirname(os.path.abspath(__file__))
+_UNIMORPH = os.path.join(_HERE, "data", "lat.unimorph")
+_CACHE = os.path.join(_HERE, "data", "lat_morph_cache.pkl")
+
+_CASES = ("NOM", "GEN", "DAT", "ACC", "ABL", "VOC")
+_CASE_MAP = {"nom": "NOM", "gen": "GEN", "dat": "DAT", "acc": "ACC",
+             "abl": "ABL", "voc": "VOC"}
+_NUM = {"singular": "SG", "plural": "PL"}
+_GEN = {"m": "MASC", "f": "FEM", "n": "NEUT"}
+
+
+# ── UniMorph loader: noun + adjective + participle case paradigms ────────────────
+def _build_cache():
+    nouns = {}        # lemma -> {(CASE, NUM): form}
+    adjs = {}         # lemma -> {(CASE, GEN, NUM): form}
+    ptcps = {}        # lemma -> {(CASE, GEN, NUM): form}  (from V.PTCP; keyed loosely)
+    with open(_UNIMORPH, encoding="utf-8") as fh:
+        for line in fh:
+            line = line.rstrip("\n")
+            if not line or "\t" not in line:
+                continue
+            parts = line.split("\t")
+            if len(parts) != 3:
+                continue
+            lemma, form, tag = parts
+            feats = tag.split(";")
+            head = feats[0]
+            fs = set(feats)
+            case = next((c for c in _CASES if c in fs), None)
+            # handle combined case tags like GEN+DAT
+            if case is None:
+                for f in feats:
+                    if "+" in f and any(c in f.split("+") for c in _CASES):
+                        case = [c for c in _CASES if c in f.split("+")]
+                        break
+            num = "SG" if "SG" in fs else ("PL" if "PL" in fs else None)
+            if case is None or num is None:
+                continue
+            cases = case if isinstance(case, list) else [case]
+
+            if head == "N":
+                d = nouns.setdefault(lemma, {})
+                for c in cases:
+                    d.setdefault((c, num), form)
+            elif head == "ADJ":
+                # gender may be combined: MASC+FEM+NEUT, MASC+FEM
+                genders = []
+                for g in ("MASC", "FEM", "NEUT"):
+                    if any(g == x or (g in x.split("+")) for x in feats):
+                        genders.append(g)
+                if not genders:
+                    genders = ["MASC", "FEM", "NEUT"]
+                d = adjs.setdefault(lemma, {})
+                for c in cases:
+                    for g in genders:
+                        d.setdefault((c, g, num), form)
+    data = {"nouns": nouns, "adjs": adjs, "ptcps": ptcps}
+    try:
+        with open(_CACHE, "wb") as fh:
+            pickle.dump(data, fh, protocol=pickle.HIGHEST_PROTOCOL)
+    except OSError:
+        pass
+    return data
+
+
+def _load():
+    if os.path.exists(_CACHE) and os.path.exists(_UNIMORPH):
+        if os.path.getmtime(_CACHE) >= os.path.getmtime(_UNIMORPH):
+            try:
+                with open(_CACHE, "rb") as fh:
+                    return pickle.load(fh)
+            except Exception:
+                pass
+    return _build_cache()
+
+
+_LEX = _load()
+_NOUNS, _ADJS = _LEX["nouns"], _LEX["adjs"]
+
+
+# ── noun gender inference (declension-based, curated exceptions) ─────────────────
+# Real, attestable rule: gender follows declension + nominative shape, with the
+# standard closed set of exceptions.
+_GENDER_EXC = {
+    # 1st-declension masculines (people/agents)
+    "agricola": "m", "poēta": "m", "nauta": "m", "incola": "m", "scrība": "m",
+    "auriga": "m", "pīrāta": "m", "athlēta": "m",
+    # 2nd-declension neuters / feminines
+    "vīrus": "n", "vulgus": "n", "pelagus": "n", "humus": "f",
+    # common 3rd-declension whose gender the ending would mispredict
+    "rēx": "m", "dux": "m", "mīles": "m", "pater": "m", "frāter": "m",
+    "homō": "m", "leō": "m", "sōl": "m", "mōns": "m", "pōns": "m", "fōns": "m",
+    "sanguis": "m", "ōrdō": "m", "sermō": "m", "amor": "m", "dolor": "m",
+    "labor": "m", "timor": "m", "honor": "m", "color": "m", "pēs": "m",
+    "dēns": "m", "flōs": "m", "mōs": "m", "mensis": "m", "orbis": "m",
+    "piscis": "m", "ignis": "m", "collis": "m", "grex": "m", "prīnceps": "m",
+    "māter": "f", "soror": "f", "uxor": "f", "mulier": "f", "virgō": "f",
+    "urbs": "f", "arx": "f", "pāx": "f", "lēx": "f", "lūx": "f", "vōx": "f",
+    "nox": "f", "nix": "f", "vīs": "f", "salūs": "f", "virtūs": "f",
+    "aetās": "f", "cīvitās": "f", "lībertās": "f", "vēritās": "f", "voluptās": "f",
+    "nātiō": "f", "ratiō": "f", "ōrātiō": "f", "legiō": "f", "regiō": "f",
+    "mens": "f", "gens": "f", "ars": "f", "pars": "f", "mors": "f", "sors": "f",
+    "nāvis": "f", "turris": "f", "avis": "f", "vallis": "f", "classis": "f",
+    "corpus": "n", "tempus": "n", "opus": "n", "genus": "n", "onus": "n",
+    "pectus": "n", "latus": "n", "vulnus": "n", "scelus": "n", "sīdus": "n",
+    "caput": "n", "iter": "n", "flūmen": "n", "nōmen": "n", "carmen": "n",
+    "agmen": "n", "certāmen": "n", "lūmen": "n", "ōmen": "n", "cōgnōmen": "n",
+    "mare": "n", "animal": "n", "exemplar": "n", "rēte": "n",
+    # 4th-declension exceptions
+    "manus": "f", "domus": "f", "tribus": "f", "porticus": "f", "īdūs": "f",
+    "cornū": "n", "genū": "n", "gelū": "n", "verū": "n",
+    # 5th-declension
+    "diēs": "m", "merīdiēs": "m",
+}
+
+
+def _infer_gender(lemma):
+    if lemma in _GENDER_EXC:
+        return _GENDER_EXC[lemma]
+    d = _NOUNS.get(lemma)
+    nom = d.get(("NOM", "SG")) if d else lemma
+    gen = d.get(("GEN", "SG")) if d else None
+    nom = nom or lemma
+    # 5th declension: gen -eī / -ēī
+    if gen and (gen.endswith("eī") or gen.endswith("ēī")):
+        return "f"
+    # 1st declension: nom -a, gen -ae
+    if nom.endswith("a") and (not gen or gen.endswith("ae")):
+        return "f"
+    # 2nd declension neuter: nom -um
+    if nom.endswith("um"):
+        return "n"
+    # 2nd declension masc: nom -us/-er/-ir, gen -ī
+    if (nom.endswith("us") or nom.endswith("er") or nom.endswith("ir")) and \
+            (not gen or gen.endswith("ī")):
+        return "m"
+    # 4th declension: gen -ūs
+    if gen and gen.endswith("ūs"):
+        return "n" if nom.endswith("ū") else "m"
+    # 3rd declension neuters by common nom endings
+    if nom.endswith(("men", "us", "ur", "al", "ar", "e", "ma")):
+        # -us here is 3rd-decl neuter type (corpus) only if gen shows -oris/-eris
+        if nom.endswith("us") and gen and (gen.endswith("oris") or gen.endswith("eris")
+                                           or gen.endswith("uris")):
+            return "n"
+        if nom.endswith(("men", "al", "ar", "e")):
+            return "n"
+    # default 3rd-declension: masculine (most common)
+    return "m"
+
+
+_GENDER_CACHE = {}
+
+
+def noun_gender(lemma):
+    lemma = lemma.strip()
+    if lemma not in _GENDER_CACHE:
+        _GENDER_CACHE[lemma] = _infer_gender(lemma)
+    return _GENDER_CACHE[lemma]
+
+
+# ── PUBLIC: noun declension ─────────────────────────────────────────────────────
+def decline_noun(lemma, case, number):
+    lemma = lemma.strip()
+    C = _CASE_MAP.get(case, case.upper())
+    N = _NUM.get(number, number)
+    d = _NOUNS.get(lemma)
+    if d and (C, N) in d:
+        return d[(C, N)], "lexicon"
+    # abl sg often == the -e/-o form; try nom fallback
+    if d:
+        # try VOC==NOM, ACC neuter==NOM etc are already in data; last resort lemma
+        return lemma, "fallback"
+    return lemma, "fallback"
+
+
+# ── PUBLIC: adjective declension ────────────────────────────────────────────────
+def decline_adj(lemma, case, gender, number):
+    lemma = lemma.strip()
+    C = _CASE_MAP.get(case, case.upper())
+    G = _GEN.get(gender, gender.upper())
+    N = _NUM.get(number, number)
+    d = _ADJS.get(lemma)
+    if d and (C, G, N) in d:
+        return d[(C, G, N)], "lexicon"
+    # try other gender (some adjs listed only under MASC+FEM etc handled at load)
+    if d:
+        for altG in ("MASC", "FEM", "NEUT"):
+            if (C, altG, N) in d:
+                return d[(C, altG, N)], "lexicon"
+        return lemma, "fallback"
+    return lemma, "fallback"
+
+
+# ═══════════════════════════════════════════════════════════════════════════════
+#  VERB RULE ENGINE  (4 conjugations + curated irregulars)
+# ═══════════════════════════════════════════════════════════════════════════════
+# Curated principal parts for common attested verbs:
+#   lemma -> (conj, present_stem, perfect_stem, supine_stem)
+# conj in {1,2,3,"3io",4}.  Stems carry macrons (matching UniMorph orthography).
+_VERBS = {
+    "amō": (1, "am", "amāv", "amāt"),
+    "laudō": (1, "laud", "laudāv", "laudāt"),
+    "portō": (1, "port", "portāv", "portāt"),
+    "vocō": (1, "voc", "vocāv", "vocāt"),
+    "dō": (1, "d", "ded", "dat"),
+    "spectō": (1, "spect", "spectāv", "spectāt"),
+    "pugnō": (1, "pugn", "pugnāv", "pugnāt"),
+    "labōrō": (1, "labōr", "labōrāv", "labōrāt"),
+    "necō": (1, "nec", "necāv", "necāt"),
+    "parō": (1, "par", "parāv", "parāt"),
+    "cōgitō": (1, "cōgit", "cōgitāv", "cōgitāt"),
+    "habitō": (1, "habit", "habitāv", "habitāt"),
+    "nārrō": (1, "nārr", "nārrāv", "nārrāt"),
+    "servō": (1, "serv", "servāv", "servāt"),
+    "superō": (1, "super", "superāv", "superāt"),
+    "oppugnō": (1, "oppugn", "oppugnāv", "oppugnāt"),
+    "ambulō": (1, "ambul", "ambulāv", "ambulāt"),
+    "clāmō": (1, "clām", "clāmāv", "clāmāt"),
+    "vulnerō": (1, "vulner", "vulnerāv", "vulnerāt"),
+    "aedificō": (1, "aedific", "aedificāv", "aedificāt"),
+    "expugnō": (1, "expugn", "expugnāv", "expugnāt"),
+    "dēfendō": (3, "dēfend", "dēfend", "dēfēns"),
+    "petō": (3, "pet", "petīv", "petīt"),
+    "occīdō": (3, "occīd", "occīd", "occīs"),
+    "interficiō": ("3io", "interfic", "interfēc", "interfect"),
+    "timeō": (2, "tim", "timu", None),
+    "iaceō": (2, "iac", "iacu", None),
+    "pāreō": (2, "pār", "pāru", "pārit"),
+    "respondeō": (2, "respond", "respond", "respōns"),
+    "vertō": (3, "vert", "vert", "vers"),
+    "ostendō": (3, "ostend", "ostend", "ostent"),
+    "cōnstituō": (3, "cōnstitu", "cōnstitu", "cōnstitūt"),
+    "cōgnōscō": (3, "cōgnōsc", "cōgnōv", "cōgnit"),
+    "crēdō": (3, "crēd", "crēdid", "crēdit"),
+    "ēdūcō": (3, "ēdūc", "ēdūx", "ēduct"),
+    "cōnservō": (1, "cōnserv", "cōnservāv", "cōnservāt"),
+    "iuvō": (1, "iuv", "iūv", "iūt"),
+    "dēbeō": (2, "dēb", "dēbu", "dēbit"),
+    "moneō": (2, "mon", "monu", "monit"),
+    "videō": (2, "vid", "vīd", "vīs"),
+    "habeō": (2, "hab", "habu", "habit"),
+    "teneō": (2, "ten", "tenu", "tent"),
+    "timeō": (2, "tim", "timu", None),
+    "terreō": (2, "terr", "terru", "territ"),
+    "dēleō": (2, "dēl", "dēlēv", "dēlēt"),
+    "iubeō": (2, "iub", "iuss", "iuss"),
+    "maneō": (2, "man", "māns", "māns"),
+    "moveō": (2, "mov", "mōv", "mōt"),
+    "doceō": (2, "doc", "docu", "doct"),
+    "sedeō": (2, "sed", "sēd", "sess"),
+    "rīdeō": (2, "rīd", "rīs", "rīs"),
+    "regō": (3, "reg", "rēx", "rēct"),
+    "dūcō": (3, "dūc", "dūx", "duct"),
+    "scrībō": (3, "scrīb", "scrīps", "scrīpt"),
+    "mittō": (3, "mitt", "mīs", "miss"),
+    "pōnō": (3, "pōn", "posu", "posit"),
+    "agō": (3, "ag", "ēg", "āct"),
+    "dīcō": (3, "dīc", "dīx", "dict"),
+    "gerō": (3, "ger", "gess", "gest"),
+    "vincō": (3, "vinc", "vīc", "vict"),
+    "petō": (3, "pet", "petīv", "petīt"),
+    "legō": (3, "leg", "lēg", "lēct"),
+    "currō": (3, "curr", "cucurr", "curs"),
+    "vīvō": (3, "vīv", "vīx", "vīct"),
+    "quaerō": (3, "quaer", "quaesīv", "quaesīt"),
+    "trahō": (3, "trah", "trāx", "tract"),
+    "claudō": (3, "claud", "claus", "claus"),
+    "cōgō": (3, "cōg", "coēg", "coāct"),
+    "relinquō": (3, "relinqu", "relīqu", "relict"),
+    "capiō": ("3io", "cap", "cēp", "capt"),
+    "faciō": ("3io", "fac", "fēc", "fact"),
+    "iaciō": ("3io", "iac", "iēc", "iact"),
+    "rapiō": ("3io", "rap", "rapu", "rapt"),
+    "fugiō": ("3io", "fug", "fūg", "fugit"),
+    "cupiō": ("3io", "cup", "cupīv", "cupīt"),
+    "accipiō": ("3io", "accip", "accēp", "accept"),
+    "audiō": (4, "aud", "audīv", "audīt"),
+    "veniō": (4, "ven", "vēn", "vent"),
+    "sciō": (4, "sc", "scīv", "scīt"),
+    "sentiō": (4, "sent", "sēns", "sēns"),
+    "mūniō": (4, "mūn", "mūnīv", "mūnīt"),
+    "dormiō": (4, "dorm", "dormīv", "dormīt"),
+    "aperiō": (4, "aper", "aperu", "apert"),
+    "inveniō": (4, "inven", "invēn", "invent"),
+}
+
+# ── Present-system paradigms: full ending tables per conjugation, attached to the
+# bare present stem (pstem). Hardcoded from the standard grammar with correct
+# macrons/vowel-lengths — deterministic and independently verifiable.  Keys:
+#   (tense, mood, voice) -> {conj: [1sg,2sg,3sg,1pl,2pl,3pl]}
+_PARADIGM = {
+    ("present", "ind", "active"): {
+        1:     ["ō", "ās", "at", "āmus", "ātis", "ant"],
+        2:     ["eō", "ēs", "et", "ēmus", "ētis", "ent"],
+        3:     ["ō", "is", "it", "imus", "itis", "unt"],
+        "3io": ["iō", "is", "it", "imus", "itis", "iunt"],
+        4:     ["iō", "īs", "it", "īmus", "ītis", "iunt"],
+    },
+    ("present", "ind", "passive"): {
+        1:     ["or", "āris", "ātur", "āmur", "āminī", "antur"],
+        2:     ["eor", "ēris", "ētur", "ēmur", "ēminī", "entur"],
+        3:     ["or", "eris", "itur", "imur", "iminī", "untur"],
+        "3io": ["ior", "eris", "itur", "imur", "iminī", "iuntur"],
+        4:     ["ior", "īris", "ītur", "īmur", "īminī", "iuntur"],
+    },
+    ("imperfect", "ind", "active"): {
+        1:     ["ābam", "ābās", "ābat", "ābāmus", "ābātis", "ābant"],
+        2:     ["ēbam", "ēbās", "ēbat", "ēbāmus", "ēbātis", "ēbant"],
+        3:     ["ēbam", "ēbās", "ēbat", "ēbāmus", "ēbātis", "ēbant"],
+        "3io": ["iēbam", "iēbās", "iēbat", "iēbāmus", "iēbātis", "iēbant"],
+        4:     ["iēbam", "iēbās", "iēbat", "iēbāmus", "iēbātis", "iēbant"],
+    },
+    ("imperfect", "ind", "passive"): {
+        1:     ["ābar", "ābāris", "ābātur", "ābāmur", "ābāminī", "ābantur"],
+        2:     ["ēbar", "ēbāris", "ēbātur", "ēbāmur", "ēbāminī", "ēbantur"],
+        3:     ["ēbar", "ēbāris", "ēbātur", "ēbāmur", "ēbāminī", "ēbantur"],
+        "3io": ["iēbar", "iēbāris", "iēbātur", "iēbāmur", "iēbāminī", "iēbantur"],
+        4:     ["iēbar", "iēbāris", "iēbātur", "iēbāmur", "iēbāminī", "iēbantur"],
+    },
+    ("future", "ind", "active"): {
+        1:     ["ābō", "ābis", "ābit", "ābimus", "ābitis", "ābunt"],
+        2:     ["ēbō", "ēbis", "ēbit", "ēbimus", "ēbitis", "ēbunt"],
+        3:     ["am", "ēs", "et", "ēmus", "ētis", "ent"],
+        "3io": ["iam", "iēs", "iet", "iēmus", "iētis", "ient"],
+        4:     ["iam", "iēs", "iet", "iēmus", "iētis", "ient"],
+    },
+    ("future", "ind", "passive"): {
+        1:     ["ābor", "āberis", "ābitur", "ābimur", "ābiminī", "ābuntur"],
+        2:     ["ēbor", "ēberis", "ēbitur", "ēbimur", "ēbiminī", "ēbuntur"],
+        3:     ["ar", "ēris", "ētur", "ēmur", "ēminī", "entur"],
+        "3io": ["iar", "iēris", "iētur", "iēmur", "iēminī", "ientur"],
+        4:     ["iar", "iēris", "iētur", "iēmur", "iēminī", "ientur"],
+    },
+    ("present", "sbjv", "active"): {
+        1:     ["em", "ēs", "et", "ēmus", "ētis", "ent"],
+        2:     ["eam", "eās", "eat", "eāmus", "eātis", "eant"],
+        3:     ["am", "ās", "at", "āmus", "ātis", "ant"],
+        "3io": ["iam", "iās", "iat", "iāmus", "iātis", "iant"],
+        4:     ["iam", "iās", "iat", "iāmus", "iātis", "iant"],
+    },
+    ("present", "sbjv", "passive"): {
+        1:     ["er", "ēris", "ētur", "ēmur", "ēminī", "entur"],
+        2:     ["ear", "eāris", "eātur", "eāmur", "eāminī", "eantur"],
+        3:     ["ar", "āris", "ātur", "āmur", "āminī", "antur"],
+        "3io": ["iar", "iāris", "iātur", "iāmur", "iāminī", "iantur"],
+        4:     ["iar", "iāris", "iātur", "iāmur", "iāminī", "iantur"],
+    },
+    ("imperfect", "sbjv", "active"): {
+        1:     ["ārem", "ārēs", "āret", "ārēmus", "ārētis", "ārent"],
+        2:     ["ērem", "ērēs", "ēret", "ērēmus", "ērētis", "ērent"],
+        3:     ["erem", "erēs", "eret", "erēmus", "erētis", "erent"],
+        "3io": ["erem", "erēs", "eret", "erēmus", "erētis", "erent"],
+        4:     ["īrem", "īrēs", "īret", "īrēmus", "īrētis", "īrent"],
+    },
+    ("imperfect", "sbjv", "passive"): {
+        1:     ["ārer", "ārēris", "ārētur", "ārēmur", "ārēminī", "ārentur"],
+        2:     ["ērer", "ērēris", "ērētur", "ērēmur", "ērēminī", "ērentur"],
+        3:     ["erer", "erēris", "erētur", "erēmur", "erēminī", "erentur"],
+        "3io": ["erer", "erēris", "erētur", "erēmur", "erēminī", "erentur"],
+        4:     ["īrer", "īrēris", "īrētur", "īrēmur", "īrēminī", "īrentur"],
+    },
+}
+# perfect-active endings (added to perfect stem) — same for all conjugations
+_PERF_ACT = {
+    ("perfect", "ind"):    ["ī", "istī", "it", "imus", "istis", "ērunt"],
+    ("pluperfect", "ind"): ["eram", "erās", "erat", "erāmus", "erātis", "erant"],
+    ("futureperfect", "ind"): ["erō", "eris", "erit", "erimus", "eritis", "erint"],
+    ("perfect", "sbjv"):   ["erim", "erīs", "erit", "erīmus", "erītis", "erint"],
+    ("pluperfect", "sbjv"):["issem", "issēs", "isset", "issēmus", "issētis", "issent"],
+}
+
+
+def _idx(person, number):
+    base = {"first": 0, "second": 1, "third": 2}[person]
+    return base + (0 if number == "singular" else 3)
+
+
+def _present_system(conj, pstem, tense, mood, voice, person, number):
+    """Generate a present-system form (present/imperfect/future ind & subj)."""
+    table = _PARADIGM.get((tense, mood, voice))
+    if not table or conj not in table:
+        return None
+    return pstem + table[conj][_idx(person, number)]
+
+
+def _active_infinitive_stem(conj, pstem):
+    return {1: pstem + "ā", 2: pstem + "ē", 3: pstem + "e",
+            "3io": pstem + "e", 4: pstem + "ī"}[conj]
+
+
+_IRREG = {
+    "sum": {
+        ("present", "ind", "active"): ["sum", "es", "est", "sumus", "estis", "sunt"],
+        ("imperfect", "ind", "active"): ["eram", "erās", "erat", "erāmus", "erātis", "erant"],
+        ("future", "ind", "active"): ["erō", "eris", "erit", "erimus", "eritis", "erunt"],
+        ("perfect", "ind", "active"): ["fuī", "fuistī", "fuit", "fuimus", "fuistis", "fuērunt"],
+        ("pluperfect", "ind", "active"): ["fueram", "fuerās", "fuerat", "fuerāmus", "fuerātis", "fuerant"],
+        ("present", "sbjv", "active"): ["sim", "sīs", "sit", "sīmus", "sītis", "sint"],
+        ("imperfect", "sbjv", "active"): ["essem", "essēs", "esset", "essēmus", "essētis", "essent"],
+    },
+    "possum": {
+        ("present", "ind", "active"): ["possum", "potes", "potest", "possumus", "potestis", "possunt"],
+        ("imperfect", "ind", "active"): ["poteram", "poterās", "poterat", "poterāmus", "poterātis", "poterant"],
+        ("future", "ind", "active"): ["poterō", "poteris", "poterit", "poterimus", "poteritis", "poterunt"],
+        ("perfect", "ind", "active"): ["potuī", "potuistī", "potuit", "potuimus", "potuistis", "potuērunt"],
+        ("present", "sbjv", "active"): ["possim", "possīs", "possit", "possīmus", "possītis", "possint"],
+    },
+    "eō": {
+        ("present", "ind", "active"): ["eō", "īs", "it", "īmus", "ītis", "eunt"],
+        ("imperfect", "ind", "active"): ["ībam", "ībās", "ībat", "ībāmus", "ībātis", "ībant"],
+        ("future", "ind", "active"): ["ībō", "ībis", "ībit", "ībimus", "ībitis", "ībunt"],
+        ("perfect", "ind", "active"): ["iī", "īstī", "iit", "iimus", "īstis", "iērunt"],
+        ("present", "sbjv", "active"): ["eam", "eās", "eat", "eāmus", "eātis", "eant"],
+    },
+    "volō": {
+        ("present", "ind", "active"): ["volō", "vīs", "vult", "volumus", "vultis", "volunt"],
+        ("imperfect", "ind", "active"): ["volēbam", "volēbās", "volēbat", "volēbāmus", "volēbātis", "volēbant"],
+        ("future", "ind", "active"): ["volam", "volēs", "volet", "volēmus", "volētis", "volent"],
+        ("perfect", "ind", "active"): ["voluī", "voluistī", "voluit", "voluimus", "voluistis", "voluērunt"],
+        ("present", "sbjv", "active"): ["velim", "velīs", "velit", "velīmus", "velītis", "velint"],
+    },
+    "nōlō": {
+        ("present", "ind", "active"): ["nōlō", "nōn vīs", "nōn vult", "nōlumus", "nōn vultis", "nōlunt"],
+        ("present", "sbjv", "active"): ["nōlim", "nōlīs", "nōlit", "nōlīmus", "nōlītis", "nōlint"],
+    },
+    "ferō": {
+        ("present", "ind", "active"): ["ferō", "fers", "fert", "ferimus", "fertis", "ferunt"],
+        ("imperfect", "ind", "active"): ["ferēbam", "ferēbās", "ferēbat", "ferēbāmus", "ferēbātis", "ferēbant"],
+        ("future", "ind", "active"): ["feram", "ferēs", "feret", "ferēmus", "ferētis", "ferent"],
+        ("perfect", "ind", "active"): ["tulī", "tulistī", "tulit", "tulimus", "tulistis", "tulērunt"],
+        ("present", "sbjv", "active"): ["feram", "ferās", "ferat", "ferāmus", "ferātis", "ferant"],
+    },
+}
+
+
+def conjugate(lemma, tense, mood, voice="active", person="third", number="singular"):
+    """Return (surface, confidence). Perfect-passive forms are periphrastic and
+    handled in the realizer (sum + PPP); this returns synthetic forms only."""
+    lemma = lemma.strip()
+    i = _idx(person, number)
+    ir = _IRREG.get(lemma)
+    if ir:
+        tbl = ir.get((tense, mood, voice)) or ir.get((tense, mood, "active"))
+        if tbl and tbl[i]:
+            return tbl[i], "rule"
+    v = _VERBS.get(lemma)
+    if not v:
+        v = _infer_principal_parts(lemma)
+        if not v:
+            return lemma, "fallback"
+    conj, pstem, perfstem, supstem = v
+    # imperative (present active) 2sg / 2pl
+    if mood == "imp":
+        return _imperative(conj, pstem, person, number), "rule"
+    # perfect-system active
+    if tense in ("perfect", "pluperfect", "futureperfect") and voice == "active":
+        if not perfstem:
+            return lemma, "fallback"
+        end = _PERF_ACT.get((tense, mood))
+        if end:
+            return perfstem + end[i], "rule"
+    # present-system (active + passive)
+    if tense in ("present", "imperfect", "future"):
+        form = _present_system(conj, pstem, tense, mood, voice, person, number)
+        if form:
+            return form, "rule"
+    return lemma, "fallback"
+
+
+def _imperative(conj, pstem, person, number):
+    if number == "singular":
+        return {1: pstem + "ā", 2: pstem + "ē", 3: pstem + "e",
+                "3io": pstem + "e", 4: pstem + "ī"}[conj]
+    return {1: pstem + "āte", 2: pstem + "ēte", 3: pstem + "ite",
+            "3io": pstem + "ite", 4: pstem + "īte"}[conj]
+
+
+def _infer_principal_parts(lemma):
+    """OOV fallback: infer conjugation + stems from the 1sg-present citation form.
+    Perfect/supine stems are guessed regularly (often wrong for 3rd conj) and the
+    resulting forms are still returned as 'rule' but the realizer down-weights."""
+    if lemma.endswith("ō"):
+        base = lemma[:-1]
+        # can't distinguish conj from 1sg alone reliably; default by ending vowel
+        if base.endswith("i"):
+            return ("3io", base[:-1], base[:-1] + "īv", base[:-1] + "īt")
+        return (3, base, base + "s", base + "t")
+    return None
+
+
+# ── PUBLIC: participles ─────────────────────────────────────────────────────────
+def participle(lemma, kind, case="nom", gender="m", number="singular"):
+    """kind: 'prs' (present active, -ns/-ntis), 'pfv' (perfect passive, -tus),
+    'fut' (future active, -tūrus). Declined as an adjective via rule endings.
+    Returns (form, conf)."""
+    v = _VERBS.get(lemma)
+    if not v:
+        return lemma, "fallback"
+    conj, pstem, perfstem, supstem = v
+    if kind == "pfv":
+        if not supstem:
+            return lemma, "fallback"
+        base = supstem[:-1] if supstem.endswith("t") or supstem.endswith("s") else supstem
+        stem = supstem  # supine stem already ends in t/s: amāt- -> amātus
+        return _decline_us_a_um(stem, case, gender, number), "rule"
+    if kind == "fut":
+        if not supstem:
+            return lemma, "fallback"
+        return _decline_us_a_um(supstem + "ūr", case, gender, number), "rule"
+    if kind == "prs":
+        # present active participle: stem + ns (nom), stem + nt- (oblique), 3rd-decl
+        pv = {1: "ā", 2: "ē", 3: "ē", "3io": "iē", 4: "iē"}[conj]
+        ntstem = pstem + pv + "nt"
+        return _decline_pres_ptcp(pstem + pv, case, gender, number), "rule"
+    return lemma, "fallback"
+
+
+def _decline_us_a_um(stem, case, gender, number):
+    """Decline a -us/-a/-um adjective/participle stem (2-1-2 declension)."""
+    C = _CASE_MAP.get(case, case.upper())
+    end = {
+        ("NOM", "m", "singular"): "us", ("NOM", "f", "singular"): "a", ("NOM", "n", "singular"): "um",
+        ("GEN", "m", "singular"): "ī", ("GEN", "f", "singular"): "ae", ("GEN", "n", "singular"): "ī",
+        ("DAT", "m", "singular"): "ō", ("DAT", "f", "singular"): "ae", ("DAT", "n", "singular"): "ō",
+        ("ACC", "m", "singular"): "um", ("ACC", "f", "singular"): "am", ("ACC", "n", "singular"): "um",
+        ("ABL", "m", "singular"): "ō", ("ABL", "f", "singular"): "ā", ("ABL", "n", "singular"): "ō",
+        ("VOC", "m", "singular"): "e", ("VOC", "f", "singular"): "a", ("VOC", "n", "singular"): "um",
+        ("NOM", "m", "plural"): "ī", ("NOM", "f", "plural"): "ae", ("NOM", "n", "plural"): "a",
+        ("GEN", "m", "plural"): "ōrum", ("GEN", "f", "plural"): "ārum", ("GEN", "n", "plural"): "ōrum",
+        ("DAT", "m", "plural"): "īs", ("DAT", "f", "plural"): "īs", ("DAT", "n", "plural"): "īs",
+        ("ACC", "m", "plural"): "ōs", ("ACC", "f", "plural"): "ās", ("ACC", "n", "plural"): "a",
+        ("ABL", "m", "plural"): "īs", ("ABL", "f", "plural"): "īs", ("ABL", "n", "plural"): "īs",
+        ("VOC", "m", "plural"): "ī", ("VOC", "f", "plural"): "ae", ("VOC", "n", "plural"): "a",
+    }.get((C, gender, number), "us")
+    return stem + end
+
+
+def _decline_pres_ptcp(stem, case, gender, number):
+    """Present active participle (amāns, amantis) — 3rd-declension, stem+ns/nt."""
+    C = _CASE_MAP.get(case, case.upper())
+    if C == "NOM" and number == "singular":
+        return stem + "ns"
+    if C == "VOC" and number == "singular":
+        return stem + "ns"
+    base = stem + "nt"
+    end = {
+        ("GEN", "singular"): "is", ("DAT", "singular"): "ī",
+        ("ACC", "singular"): "em" if gender != "n" else "",
+        ("ABL", "singular"): "e",
+        ("NOM", "plural"): "ēs" if gender != "n" else "ia",
+        ("GEN", "plural"): "ium", ("DAT", "plural"): "ibus",
+        ("ACC", "plural"): "ēs" if gender != "n" else "ia",
+        ("ABL", "plural"): "ibus", ("VOC", "plural"): "ēs",
+    }.get((C, number), "is")
+    if C == "ACC" and number == "singular" and gender == "n":
+        return stem + "ns"
+    return base + end
+
+
+def infinitive(lemma, tense="present", voice="active"):
+    lemma = lemma.strip()
+    if lemma == "sum":
+        return ("esse", "rule") if tense == "present" else ("fuisse", "rule")
+    v = _VERBS.get(lemma)
+    if not v:
+        return lemma, "fallback"
+    conj, pstem, perfstem, supstem = v
+    if tense == "present":
+        if voice == "active":
+            return _active_infinitive_stem(conj, pstem).rstrip() + \
+                ("re" if conj != 3 and conj != "3io" else "re"), "rule"
+        # passive present infinitive
+        base = {1: pstem + "ā", 2: pstem + "ē", 4: pstem + "ī"}.get(conj)
+        if base:
+            return base + "rī", "rule"
+        return pstem + "ī", "rule"  # 3rd: regī
+    if tense == "perfect" and voice == "active" and perfstem:
+        return perfstem + "isse", "rule"
+    return lemma, "fallback"
+
+
+def lexicon_stats():
+    return {
+        "noun_adj_source": "UniMorph Latin (github.com/unimorph/lat, CC-BY-SA 3.0)",
+        "verb_source": "rule-based 4-conjugation engine over curated attested "
+                       "principal parts (UniMorph verb list is a 947-lemma sample "
+                       "MISSING all core verbs — amō/sum/videō absent)",
+        "noun_lemmas": len(_NOUNS),
+        "adj_lemmas": len(_ADJS),
+        "curated_verb_lemmas": len(_VERBS) + len(_IRREG),
+        "gender_inference": "declension-based (nom+gen endings) + curated exceptions",
+    }
+
+
+if __name__ == "__main__":
+    import json
+    print(json.dumps(lexicon_stats(), indent=2, ensure_ascii=False))
+    print("\n-- noun declension puella (1st, fem) --")
+    for c in ("nom", "gen", "dat", "acc", "abl", "voc"):
+        print(f"  {c}: sg={decline_noun('puella', c, 'singular')[0]:10} "
+              f"pl={decline_noun('puella', c, 'plural')[0]}")
+    print("\n-- rēx (3rd, m):", [decline_noun('rēx', c, 'singular')[0] for c in ('nom','gen','dat','acc','abl')])
+    print("-- gender: puella=", noun_gender("puella"), "rēx=", noun_gender("rēx"),
+          "bellum=", noun_gender("bellum"), "corpus=", noun_gender("corpus"),
+          "manus=", noun_gender("manus"), "diēs=", noun_gender("diēs"))
+    print("\n-- conjugate videō (2nd) present ind active --")
+    for p in ("first", "second", "third"):
+        for n in ("singular", "plural"):
+            print(f"  {p[:3]}.{n[:2]}: {conjugate('videō','present','ind','active',p,n)[0]}")
+    print("-- amō forms:", conjugate("amō","present","ind","active","first","singular")[0],
+          conjugate("amō","imperfect","ind","active","third","plural")[0],
+          conjugate("amō","future","ind","active","first","singular")[0],
+          conjugate("amō","perfect","ind","active","third","singular")[0])
+    print("-- sum:", [conjugate("sum","present","ind","active",p,"singular")[0] for p in ("first","second","third")])
+    print("-- participle amō pfv acc.f.sg:", participle("amō","pfv","acc","f","singular")[0])
+    print("-- infinitive amō:", infinitive("amō")[0], "| regō pass:", infinitive("regō", voice="passive")[0])

elp/tests/lang-gen/morphology_pt_full.py

@@ -0,0 +1,538 @@
+"""morphology_pt_full.py — production-grade Brazilian-Portuguese morphological generator.
+
+NOT a toy. Backed by two real, broad, Wiktionary-lineage lexicons:
+
+  VERBS  — UniMorph Portuguese  (github.com/unimorph/por, CC-BY-SA 3.0)
+    4,001 verb lemmas × full paradigm (283,991 finite/non-finite forms +
+    20,005 participle forms). Every mood/tense pt actually inflects:
+      indicative present / preterite (PST;PFV) / imperfect (PST;IPFV) /
+                 pluperfect-simple (PST;PRF) / future,
+      conditional (futuro do pretérito),
+      subjunctive present / imperfect / FUTURE  (PT-specific live tense),
+      affirmative + negative imperative,
+      PERSONAL infinitive (V;{p};{n};NFIN — a PT-specific finite-ish form),
+      past participle (4 gender/number forms) + gerúndio (V.PTCP;PRS).
+
+  NOUNS + ADJECTIVES — kaikki.org Portuguese (Wiktionary extract, same lineage)
+    81,138 noun lemmas WITH inherent gender + real (often irregular) plural —
+      so -ão→-ões / -ãos / -ães / -õos is resolved PER LEMMA by Wiktionary,
+      never guessed (mão→mãos, pão→pães, coração→corações).
+    40,252 adjective lemmas with real feminine + masc/fem plural forms.
+
+Fallbacks (degrade, never crash, on out-of-vocabulary input):
+  verbs : rule generator for regular -ar/-er/-ir paradigms
+  nouns : gender heuristic (endings) + rule pluralization (with -ão FLAGGED)
+  adjs  : -o/-a gender rule + rule pluralization
+
+Confidence flag on every form:
+  "lexicon"  straight from UniMorph/kaikki          (trust: high)
+  "rule"     deterministic rule                     (trust: medium)
+  "fallback" could not inflect; returned lemma      (trust: low  -> FLAG)
+
+Public API (used by realizer_pt.py):
+  conjugate(lemma, mood, tense, person, number) -> (form, conf)
+  personal_infinitive(lemma, person, number) -> (form, conf)
+  participle(lemma, gender="m", number="singular") -> (form, conf)
+  gerund(lemma) -> (form, conf)
+  noun_gender(lemma) -> "m"|"f"
+  inflect_noun(lemma, number, gender=None) -> (form, conf)
+  inflect_adj(lemma, gender, number) -> (form, conf)
+  lexicon_stats() -> dict
+"""
+import json
+import os
+import pickle
+
+_HERE = os.path.dirname(os.path.abspath(__file__))
+_UNIMORPH = os.path.join(_HERE, "data", "por.unimorph")
+_KAIKKI = os.path.join(_HERE, "data", "kaikki_pt.jsonl")
+_CACHE = os.path.join(_HERE, "data", "pt_morph_cache.pkl")
+
+# ── mood/tense pair -> UniMorph feature triple (a in tag; b in tag; c in tag) ────
+_VERB_KEYMAP = {
+    ("ind", "present"):     ("IND", "PRS", None),
+    ("ind", "preterite"):   ("IND", "PST", "PFV"),
+    ("ind", "imperfect"):   ("IND", "PST", "IPFV"),
+    ("ind", "pluperfect"):  ("IND", "PST", "PRF"),   # simple mais-que-perfeito
+    ("ind", "future"):      ("IND", "FUT", None),
+    ("ind", "conditional"): ("COND", None, None),
+    ("sbjv", "present"):    ("SBJV", "PRS", None),
+    ("sbjv", "imperfect"):  ("SBJV", "PST", "IPFV"),
+    ("sbjv", "future"):     ("SBJV", "FUT", None),    # PT-specific
+    ("imp", "affirmative"): ("IMP", "POS", None),
+    ("imp", "negative"):    ("IMP", "NEG", None),
+}
+_PERSON = {"first": "1", "second": "2", "third": "3"}
+_NUMBER = {"singular": "SG", "plural": "PL"}
+
+
+def _feat_set(tag):
+    return set(tag.split(";"))
+
+
+# ── build the compact lexicon from UniMorph (verbs) + kaikki (nouns/adjs) ────────
+def _build_verbs():
+    verbs = {}     # (lemma, "mood|tense|person|number") -> form
+    pinf = {}      # (lemma, "person|number") -> personal-infinitive form
+    part = {}      # lemma -> {("m","SG"): form, ...}  past participle
+    ger = {}       # lemma -> gerúndio
+    with open(_UNIMORPH, encoding="utf-8") as fh:
+        for line in fh:
+            line = line.rstrip("\n")
+            if not line or "\t" not in line:
+                continue
+            parts = line.split("\t")
+            if len(parts) != 3:
+                continue
+            lemma, form, tag = parts
+            f = _feat_set(tag)
+            head = tag.split(";")[0]
+
+            if head == "V.PTCP":
+                if "PST" in f:  # past participle: falado/falada/falados/faladas
+                    g = "m" if "MASC" in f else ("f" if "FEM" in f else "m")
+                    num = "SG" if "SG" in f else ("PL" if "PL" in f else "SG")
+                    part.setdefault(lemma, {})[(g, num)] = form
+                elif "PRS" in f:  # gerúndio: falando
+                    ger.setdefault(lemma, form)
+                continue
+
+            if head != "V":
+                continue
+
+            # personal / impersonal infinitive
+            if "NFIN" in f:
+                person = next((p for p in ("1", "2", "3") if p in f), None)
+                number = "SG" if "SG" in f else ("PL" if "PL" in f else None)
+                if person and number:
+                    pinf[(lemma, f"{person}|{number}")] = form
+                continue
+
+            # finite forms
+            mt = None
+            for (mood, tense), (a, b, c) in _VERB_KEYMAP.items():
+                if a not in f:
+                    continue
+                if b is not None and b not in f:
+                    continue
+                if c is not None and c not in f:
+                    continue
+                # IND;PST needs exactly PFV|IPFV|PRF — reject if the required one absent
+                mt = (mood, tense)
+                break
+            if mt is None:
+                continue
+            person = next((p for p in ("1", "2", "3") if p in f), None)
+            number = "SG" if "SG" in f else ("PL" if "PL" in f else None)
+            if person is None or number is None:
+                continue
+            verbs.setdefault((lemma, f"{mt[0]}|{mt[1]}|{person}|{number}"), form)
+    return verbs, pinf, part, ger
+
+
+def _kaikki_gender(arg):
+    if not arg:
+        return None
+    a = arg.lower()
+    if a.startswith("f"):
+        return "f"
+    if a.startswith("m"):
+        return "m"
+    return None
+
+
+def _build_nouns_adjs():
+    nouns = {}   # lemma -> {"g","SG","PL"}
+    adjs = {}    # lemma -> {("m","SG"),("f","SG"),("m","PL"),("f","PL")}
+    with open(_KAIKKI, encoding="utf-8") as fh:
+        for line in fh:
+            try:
+                d = json.loads(line)
+            except Exception:
+                continue
+            pos = d.get("pos")
+            word = d.get("word", "")
+            if not word or " " in word:  # skip multiword entries
+                continue
+            forms = d.get("forms", []) or []
+
+            if pos == "noun":
+                ht = d.get("head_templates") or []
+                g = None
+                if ht:
+                    g = _kaikki_gender((ht[0].get("args") or {}).get("1"))
+                if g is None:
+                    tags = d.get("tags") or []
+                    if "feminine" in tags:
+                        g = "f"
+                    elif "masculine" in tags:
+                        g = "m"
+                pl = None
+                for x in forms:
+                    t = x.get("tags") or []
+                    if "plural" in t and "alternative" not in t and "obsolete" not in t:
+                        pl = x.get("form")
+                        break
+                # first entry wins; but a later entry with a plural fills a gap
+                if word not in nouns:
+                    nouns[word] = {"g": g, "SG": word, "PL": pl}
+                else:
+                    cur = nouns[word]
+                    if cur.get("g") is None and g:
+                        cur["g"] = g
+                    if not cur.get("PL") and pl:
+                        cur["PL"] = pl
+
+            elif pos == "adj":
+                d0 = adjs.setdefault(word, {})
+                d0.setdefault(("m", "SG"), word)
+                for x in forms:
+                    t = set(x.get("tags") or [])
+                    fm = x.get("form")
+                    if not fm or ("alternative" in t) or ("obsolete" in t):
+                        continue
+                    if "comparative" in t or "superlative" in t or \
+                       "diminutive" in t or "augmentative" in t:
+                        continue
+                    if "feminine" in t and "plural" in t:
+                        d0[("f", "PL")] = fm
+                    elif "masculine" in t and "plural" in t:
+                        d0[("m", "PL")] = fm
+                    elif "feminine" in t:
+                        d0[("f", "SG")] = fm
+                    elif "plural" in t:  # invariant-gender adj (feliz -> felizes)
+                        d0[("m", "PL")] = d0.get(("m", "PL")) or fm
+                        d0[("f", "PL")] = d0.get(("f", "PL")) or fm
+    return nouns, adjs
+
+
+def _build_cache():
+    verbs, pinf, part, ger = _build_verbs()
+    nouns, adjs = _build_nouns_adjs()
+    data = {"verbs": verbs, "pinf": pinf, "part": part, "ger": ger,
+            "nouns": nouns, "adjs": adjs}
+    try:
+        with open(_CACHE, "wb") as fh:
+            pickle.dump(data, fh, protocol=pickle.HIGHEST_PROTOCOL)
+    except OSError:
+        pass
+    return data
+
+
+def _load():
+    if os.path.exists(_CACHE):
+        newest_src = max(os.path.getmtime(_UNIMORPH),
+                         os.path.getmtime(_KAIKKI) if os.path.exists(_KAIKKI) else 0)
+        if os.path.getmtime(_CACHE) >= newest_src:
+            try:
+                with open(_CACHE, "rb") as fh:
+                    return pickle.load(fh)
+            except Exception:
+                pass
+    return _build_cache()
+
+
+_LEX = _load()
+_VERBS, _PINF, _PART, _GER, _NOUNS, _ADJS = (
+    _LEX["verbs"], _LEX["pinf"], _LEX["part"], _LEX["ger"],
+    _LEX["nouns"], _LEX["adjs"])
+
+
+# ── regular-ending rule fallback (deterministic, last resort) ────────────────────
+def _vclass(lemma):
+    return lemma[-2:] if lemma[-2:] in ("ar", "er", "ir") else None
+
+
+def _stem(lemma):
+    return lemma[:-2]
+
+
+# endings indexed [1sg,2sg,3sg,1pl,2pl,3pl]
+_REG = {
+    ("ind", "present", "ar"): ["o", "as", "a", "amos", "ais", "am"],
+    ("ind", "present", "er"): ["o", "es", "e", "emos", "eis", "em"],
+    ("ind", "present", "ir"): ["o", "es", "e", "imos", "is", "em"],
+    ("ind", "preterite", "ar"): ["ei", "aste", "ou", "amos", "astes", "aram"],
+    ("ind", "preterite", "er"): ["i", "este", "eu", "emos", "estes", "eram"],
+    ("ind", "preterite", "ir"): ["i", "iste", "iu", "imos", "istes", "iram"],
+    ("ind", "imperfect", "ar"): ["ava", "avas", "ava", "ávamos", "áveis", "avam"],
+    ("ind", "imperfect", "er"): ["ia", "ias", "ia", "íamos", "íeis", "iam"],
+    ("ind", "imperfect", "ir"): ["ia", "ias", "ia", "íamos", "íeis", "iam"],
+    ("sbjv", "present", "ar"): ["e", "es", "e", "emos", "eis", "em"],
+    ("sbjv", "present", "er"): ["a", "as", "a", "amos", "ais", "am"],
+    ("sbjv", "present", "ir"): ["a", "as", "a", "amos", "ais", "am"],
+    ("sbjv", "imperfect", "ar"): ["asse", "asses", "asse", "ássemos", "ásseis", "assem"],
+    ("sbjv", "imperfect", "er"): ["esse", "esses", "esse", "êssemos", "êsseis", "essem"],
+    ("sbjv", "imperfect", "ir"): ["isse", "isses", "isse", "íssemos", "ísseis", "issem"],
+    ("sbjv", "future", "ar"): ["ar", "ares", "ar", "armos", "ardes", "arem"],
+    ("sbjv", "future", "er"): ["er", "eres", "er", "ermos", "erdes", "erem"],
+    ("sbjv", "future", "ir"): ["ir", "ires", "ir", "irmos", "irdes", "irem"],
+}
+# future & conditional attach to the FULL infinitive
+_FUT = ["ei", "ás", "á", "emos", "eis", "ão"]
+_COND = ["ia", "ias", "ia", "íamos", "íeis", "iam"]
+
+
+def _slot_idx(person, number):
+    base = {"first": 0, "second": 1, "third": 2}[person]
+    return base + (0 if number == "singular" else 3)
+
+
+def _rule_conjugate(lemma, mood, tense, person, number):
+    vc = _vclass(lemma)
+    if vc is None:
+        return None
+    st, i = _stem(lemma), _slot_idx(person, number)
+    if mood == "ind" and tense == "future":
+        return lemma + _FUT[i]
+    if mood == "ind" and tense == "conditional":
+        return lemma + _COND[i]
+    if mood == "imp":  # affirmative tú/vocês imperative ~ subjunctive present
+        table = _REG.get(("sbjv", "present", vc))
+        if table and tense == "negative":
+            return st + table[i]
+        # affirmative 2sg = 3sg present indicative; others = subjunctive
+        pres = _REG.get(("ind", "present", vc))
+        if person == "second" and number == "singular":
+            return st + pres[2]
+        return st + table[i] if table else None
+    table = _REG.get((mood, tense, vc))
+    if table:
+        return st + table[i]
+    return None
+
+
+# verified corrections to UniMorph data errors (each audited individually, not
+# guessed). The three 1PL-present entries are glued-allomorph errors surfaced by a
+# full-lexicon scan for a non-final "mos" in V;1;PL;IND;PRS forms (the ONLY three).
+_VERB_FIX = {
+    ("estar", "ind", "imperfect", "third", "plural"): "estavam",   # was "estávam"
+    ("estar", "ind", "present", "first", "plural"): "estamos",     # was "estamosestámos"
+    ("haver", "ind", "present", "first", "plural"): "havemos",     # was "havemoshemos"
+    ("ir", "ind", "present", "first", "plural"): "vamos",          # was "vamosimos"
+}
+
+
+# ── PUBLIC: verb conjugation ─────────────────────────────────────────────────────
+def conjugate(lemma, mood, tense, person, number):
+    """Return (surface, confidence). mood in ind|sbjv|imp; tense per _VERB_KEYMAP."""
+    lemma = lemma.strip().lower()
+    fix = _VERB_FIX.get((lemma, mood, tense, person, number))
+    if fix:
+        return fix, "lexicon"
+    p, n = _PERSON.get(person), _NUMBER.get(number)
+    if p and n:
+        form = _VERBS.get((lemma, f"{mood}|{tense}|{p}|{n}"))
+        if form:
+            # pt-BR normalization: UniMorph `por` carries the EUROPEAN spelling of
+            # the -ar 1pl PRETERITE (-ámos). Brazilian PT drops the accent
+            # (falámos->falamos, chegámos->chegamos) — 3,334/4,001 verbs affected.
+            if (mood == "ind" and tense == "preterite" and person == "first"
+                    and number == "plural" and form.endswith("ámos")):
+                form = form[:-4] + "amos"
+            return form, "lexicon"
+    r = _rule_conjugate(lemma, mood, tense, person, number)
+    if r:
+        return r, "rule"
+    return lemma, "fallback"
+
+
+def personal_infinitive(lemma, person, number):
+    """PT personal (inflected) infinitive: para falarmos, ao chegarem."""
+    lemma = lemma.strip().lower()
+    p, n = _PERSON.get(person), _NUMBER.get(number)
+    if p and n:
+        form = _PINF.get((lemma, f"{p}|{n}"))
+        if form:
+            return form, "lexicon"
+    # rule: infinitive + personal endings (-, -es, -, -mos, -des, -em)
+    end = {("first", "singular"): "", ("second", "singular"): "es",
+           ("third", "singular"): "", ("first", "plural"): "mos",
+           ("second", "plural"): "des", ("third", "plural"): "em"}.get((person, number), "")
+    return lemma + end, "rule"
+
+
+# ── PUBLIC: participle + gerund ───────────────────────────────────────────────────
+def participle(lemma, gender="m", number="singular"):
+    lemma = lemma.strip().lower()
+    g = "f" if gender == "f" else "m"
+    num = "SG" if number == "singular" else "PL"
+    d = _PART.get(lemma)
+    if d:
+        form = d.get((g, num)) or d.get(("m", "SG"))
+        if form:
+            return form, "lexicon"
+    if lemma.endswith("ar"):
+        base = lemma[:-2] + "ad"
+    elif lemma[-2:] in ("er", "ir"):
+        base = lemma[:-2] + "id"
+    else:
+        return lemma, "fallback"
+    suf = {"m|SG": "o", "f|SG": "a", "m|PL": "os", "f|PL": "as"}[f"{g}|{num}"]
+    return base + suf, "rule"
+
+
+def gerund(lemma):
+    lemma = lemma.strip().lower()
+    if lemma in _GER:
+        return _GER[lemma], "lexicon"
+    if lemma.endswith("ar"):
+        return lemma[:-2] + "ando", "rule"
+    if lemma.endswith("er"):
+        return lemma[:-2] + "endo", "rule"
+    if lemma.endswith("ir"):
+        return lemma[:-2] + "indo", "rule"
+    return lemma, "fallback"
+
+
+# ── PUBLIC: noun gender + number ─────────────────────────────────────────────────
+_FEM_SUF = ("ção", "são", "ção", "dade", "tade", "agem", "igem", "ugem", "gem",
+            "ez", "eza", "ice", "ície", "tude", "ude", "âncbefore")
+_FEM_SUF = ("ção", "são", "dade", "tade", "agem", "gem", "eza", "ez", "ice",
+            "tude", "ude", "ância", "ência", "ínia")
+_MASC_SUF = ("ema", "oma", "ama", "grama", "eta", "ão")  # Greek -ma etc. (mostly m)
+
+
+def _gender_heuristic(noun):
+    for suf in _FEM_SUF:
+        if noun.endswith(suf):
+            return "f"
+    if noun.endswith(("ema", "oma", "ama")):   # problema, idioma, programa
+        return "m"
+    if noun.endswith("a") or noun.endswith("ã"):
+        return "f"
+    if noun.endswith("o") or noun.endswith(("l", "r", "z", "m", "u", "i")):
+        return "m"
+    return "m"
+
+
+def noun_gender(lemma):
+    lemma = lemma.strip().lower()
+    d = _NOUNS.get(lemma)
+    if d and d.get("g"):
+        return d["g"]
+    return _gender_heuristic(lemma)
+
+
+_INVARIANT_PL_SUF = ("s",)  # paroxytones ending -s are invariant (o lápis / os lápis)
+
+
+def _rule_plural(noun):
+    """Deterministic PT pluralization. Returns (form, ok) where ok=False flags an
+    ambiguous -ão that should lower confidence (the lexicon normally resolves it)."""
+    if not noun:
+        return noun, True
+    if noun.endswith("ão"):
+        return noun[:-2] + "ões", False        # majority rule, but AMBIGUOUS -> flag
+    if noun.endswith("m"):
+        return noun[:-1] + "ns", True           # homem->homens, jardim->jardins
+    if noun.endswith("al"):
+        return noun[:-2] + "ais", True
+    if noun.endswith("el"):
+        return noun[:-2] + "éis", True
+    if noun.endswith("ol"):
+        return noun[:-2] + "óis", True
+    if noun.endswith("ul"):
+        return noun[:-2] + "uis", True
+    if noun.endswith("il"):
+        return noun[:-2] + "is", True           # stressed (funil->funis); unstressed rarer
+    if noun.endswith(("r", "z")):
+        return noun + "es", True                # flor->flores, luz->luzes
+    if noun.endswith("s"):
+        # paroxytone -s (lápis, ônibus) invariant; oxytone -s (país) -> -es
+        return noun, True
+    if noun.endswith(("a", "e", "i", "o", "u", "á", "é", "í", "ó", "ú", "ã")):
+        return noun + "s", True
+    return noun + "s", True
+
+
+def inflect_noun(lemma, number, gender=None):
+    lemma = lemma.strip().lower()
+    d = _NOUNS.get(lemma)
+    if number == "singular":
+        return (d["SG"] if d and d.get("SG") else lemma), ("lexicon" if d else "rule")
+    if d and d.get("PL"):
+        return d["PL"], "lexicon"
+    form, ok = _rule_plural(lemma)
+    return form, ("rule" if ok else "fallback")
+
+
+# ── PUBLIC: adjective agreement ──────────────────────────────────────────────────
+def inflect_adj(lemma, gender, number):
+    lemma = lemma.strip().lower()
+    g = "f" if gender == "f" else "m"
+    num = "SG" if number == "singular" else "PL"
+    d = _ADJS.get(lemma)
+    if d:
+        form = d.get((g, num))
+        if form:
+            return form, "lexicon"
+        # build a missing plural from this gender's singular
+        sg = d.get((g, "SG")) or d.get(("m", "SG")) or lemma
+        if num == "PL":
+            pl, ok = _rule_plural(sg)
+            return pl, ("rule" if ok else "fallback")
+        return sg, "lexicon"
+    # rule fallback: -o/-a gender, then pluralize
+    a = lemma
+    if g == "f":
+        if a.endswith("o"):
+            a = a[:-1] + "a"
+        elif a.endswith(("ês", "or")) and not a.endswith("ior"):
+            a = a + "a"                        # português->portuguesa, trabalhador->..a
+    if num == "PL":
+        a, ok = _rule_plural(a)
+        return a, ("rule" if ok else "fallback")
+    return a, "rule"
+
+
+def lexicon_stats():
+    return {
+        "verb_source": "UniMorph Portuguese (github.com/unimorph/por)",
+        "noun_adj_source": "kaikki.org Portuguese (Wiktionary extract)",
+        "license": "CC-BY-SA (Wiktionary-derived)",
+        "verb_forms": len(_VERBS),
+        "verb_lemmas": len({k[0] for k in _VERBS}),
+        "personal_infinitive_forms": len(_PINF),
+        "participle_lemmas": len(_PART),
+        "gerund_lemmas": len(_GER),
+        "noun_lemmas": len(_NOUNS),
+        "adj_lemmas": len(_ADJS),
+    }
+
+
+if __name__ == "__main__":
+    print(json.dumps(lexicon_stats(), indent=2, ensure_ascii=False))
+    tests = [
+        ("falar", "ind", "present", "first", "singular", "falo"),
+        ("comer", "ind", "present", "third", "plural", "comem"),
+        ("partir", "ind", "present", "first", "plural", "partimos"),
+        ("ser", "ind", "present", "third", "singular", "é"),
+        ("ir", "ind", "preterite", "first", "singular", "fui"),
+        ("ter", "ind", "future", "first", "singular", "terei"),
+        ("fazer", "sbjv", "present", "first", "singular", "faça"),
+        ("dormir", "ind", "present", "first", "singular", "durmo"),
+        ("dar", "ind", "preterite", "third", "singular", "deu"),
+        ("poder", "ind", "conditional", "first", "singular", "poderia"),
+        ("fazer", "sbjv", "future", "third", "singular", "fizer"),
+        ("estar", "ind", "present", "third", "singular", "está"),
+    ]
+    ok = 0
+    for lemma, mood, tense, per, num, exp in tests:
+        got, conf = conjugate(lemma, mood, tense, per, num)
+        flag = "OK " if got == exp else "XX "
+        ok += got == exp
+        print(f"  {flag}{lemma:8} {mood}/{tense} {per[:3]}.{num[:2]} -> {got:14} ({conf}) exp={exp}")
+    print(f"verb tests {ok}/{len(tests)}")
+    print("  gender: casa=", noun_gender("casa"), "problema=", noun_gender("problema"),
+          "mão=", noun_gender("mão"), "coração=", noun_gender("coração"),
+          "flor=", noun_gender("flor"))
+    print("  plural: mão->", inflect_noun("mão", "plural"),
+          "| pão->", inflect_noun("pão", "plural"),
+          "| animal->", inflect_noun("animal", "plural"),
+          "| coração->", inflect_noun("coração", "plural"))
+    print("  adj: bonito/f/sg->", inflect_adj("bonito", "f", "singular"),
+          "| feliz/m/pl->", inflect_adj("feliz", "m", "plural"),
+          "| português/f/sg->", inflect_adj("português", "f", "singular"))
+    print("  part: fazer/m/sg->", participle("fazer"), "| ger falar->", gerund("falar"))
+    print("  pinf falar 1pl->", personal_infinitive("falar", "first", "plural"))

elp/tests/lang-gen/morphology_ro_full.py

@@ -0,0 +1,609 @@
+# -*- coding: utf-8 -*-
+"""morphology_ro_full.py — production-grade Romanian morphological generator.
+
+Romanian is the BIG typological delta of the Romance family. The verb engine and
+the confidence/fallback contract TRANSFER from the Italian sibling; the NOMINAL
+system is genuinely new: Romanian has a SUFFIXED definite article, a preserved
+NOM/ACC vs GEN/DAT case distinction, a NEUTER gender (masc-agreeing in SG,
+fem-agreeing in PL), and a VOCATIVE. Those are grounded in real per-lemma data,
+not guessed.
+
+Real, Wiktionary-lineage lexical sources:
+
+  VERBS — UniMorph Romanian (github.com/unimorph/ron, CC-BY-SA 3.0)
+    ~1216 verb lemmas × paradigm, CLEAN orthography:
+      indicativ prezent / imperfect (PST;IPFV) / perfectul simplu (PST;PFV) /
+      conjunctiv prezent (SBJV;PRS, stored WITHOUT the 'să' particle),
+      participiu (V.PTCP;PST, INVARIABLE in the perfect compus),
+      gerunziu (V.CVB;PRS), infinitiv (NFIN), imperativ.
+    ro_irreg_verbs (embedded) — high-frequency verbs UniMorph MISSES
+      (avea, vrea, da) + the auxiliary clitic paradigms the compound tenses need
+      (perfect-compus am/ai/a/am/ați/au, viitor voi/vei/va/vom/veți/vor,
+      condițional aș/ai/ar/am/ați/ar). Real standard forms.
+
+  NOUNS — kaikki.org Romanian (Wiktionary extract, CC-BY-SA 3.0)
+    the FULL declension per lemma, cleanly tagged:
+      (nom/acc | gen/dat | vocative) × (indefinite | definite) × (sg | pl).
+    This is what makes the suffixed article LEXICALLY grounded (om→omul,
+    casă→casa, băiat→băiatul, casei gen/dat, omule vocative). Inherent gender
+    m / f / n (NEUTER available directly) from the head template.
+
+  ADJECTIVES — UniMorph Romanian ADJ
+    full case × gender(MASC/FEM/NEUT) × number × definiteness paradigm.
+
+Fallbacks (degrade, never crash, on OOV): rule verb conjugation for -a/-ea/-e/-i/-î
+classes, rule pluralization, rule suffixed-article by gender+ending. Every form
+carries a confidence flag: "lexicon" | "rule" | "fallback".
+
+Public API (used by realizer_ro.py):
+  conjugate(lemma, mood, tense, person, number) -> (form, conf)
+  aux(kind, person, number) -> str            # perfect / future / conditional clitics
+  participle(lemma) -> (form, conf)            # INVARIABLE
+  gerund(lemma) -> (form, conf)
+  noun_gender(lemma) -> "m"|"f"|"n"
+  definite_suffix(noun, gender, number, case) -> (form, conf)   # rule engine
+  inflect_noun(lemma, number, gender=None, case="nomacc", definite=False) -> (form, conf)
+  inflect_adj(lemma, gender, number, case="nomacc", definite=False) -> (form, conf)
+  lexicon_stats() -> dict
+"""
+import json
+import os
+import pickle
+
+_HERE = os.path.dirname(os.path.abspath(__file__))
+_UNIMORPH = os.path.join(_HERE, "data", "ron.unimorph")
+_KAIKKI = os.path.join(_HERE, "data", "kaikki_ro.jsonl")
+_CACHE = os.path.join(_HERE, "data", "ro_morph_cache.pkl")
+
+# ── (mood, tense) -> UniMorph feature set ─────────────────────────────────────────
+_VERB_KEYMAP = {
+    ("ind", "present"):    {"IND", "PRS"},
+    ("ind", "imperfect"):  {"IND", "PST", "IPFV"},
+    ("ind", "perfect_s"):  {"IND", "PST", "PFV"},   # perfectul simplu (regional/lit.)
+    ("sbjv", "present"):   {"SBJV", "PRS"},
+    ("imp", "affirmative"): {"POS", "IMP"},
+}
+_PERSON = {"first": "1", "second": "2", "third": "3"}
+_NUMBER = {"singular": "SG", "plural": "PL"}
+
+
+def _feat_set(tag):
+    return set(tag.split(";"))
+
+
+# ── high-frequency irregulars UniMorph misses + auxiliary clitic paradigms ────────
+# Real standard Romanian forms (textbook paradigms).
+_IRREG = {
+    "avea": {
+        "ind|present|1|SG": "am", "ind|present|2|SG": "ai", "ind|present|3|SG": "are",
+        "ind|present|1|PL": "avem", "ind|present|2|PL": "aveți", "ind|present|3|PL": "au",
+        "ind|imperfect|1|SG": "aveam", "ind|imperfect|2|SG": "aveai",
+        "ind|imperfect|3|SG": "avea", "ind|imperfect|1|PL": "aveam",
+        "ind|imperfect|2|PL": "aveați", "ind|imperfect|3|PL": "aveau",
+        "sbjv|present|3|SG": "aibă", "sbjv|present|3|PL": "aibă",
+        "sbjv|present|1|SG": "am", "sbjv|present|2|SG": "ai",
+        "sbjv|present|1|PL": "avem", "sbjv|present|2|PL": "aveți",
+        "part": "avut", "ger": "având",
+    },
+    "vrea": {
+        "ind|present|1|SG": "vreau", "ind|present|2|SG": "vrei", "ind|present|3|SG": "vrea",
+        "ind|present|1|PL": "vrem", "ind|present|2|PL": "vreți", "ind|present|3|PL": "vor",
+        "ind|imperfect|1|SG": "voiam", "ind|imperfect|3|SG": "voia",
+        "sbjv|present|3|SG": "vrea", "sbjv|present|3|PL": "vrea",
+        "part": "vrut", "ger": "vrând",
+    },
+    "da": {
+        "ind|present|1|SG": "dau", "ind|present|2|SG": "dai", "ind|present|3|SG": "dă",
+        "ind|present|1|PL": "dăm", "ind|present|2|PL": "dați", "ind|present|3|PL": "dau",
+        "ind|imperfect|1|SG": "dădeam", "ind|imperfect|3|SG": "dădea",
+        "sbjv|present|3|SG": "dea", "sbjv|present|3|PL": "dea",
+        "part": "dat", "ger": "dând",
+    },
+    "fi": {   # a fi — present is in UniMorph but keep participle + subjunctive here
+        "part": "fost", "ger": "fiind",
+        "sbjv|present|1|SG": "fiu", "sbjv|present|2|SG": "fii", "sbjv|present|3|SG": "fie",
+        "sbjv|present|1|PL": "fim", "sbjv|present|2|PL": "fiți", "sbjv|present|3|PL": "fie",
+        "ind|imperfect|1|SG": "eram", "ind|imperfect|2|SG": "erai",
+        "ind|imperfect|3|SG": "era", "ind|imperfect|1|PL": "eram",
+        "ind|imperfect|2|PL": "erați", "ind|imperfect|3|PL": "erau",
+    },
+}
+# auxiliary clitic paradigms (person,number)->form
+_AUX = {
+    "perfect":     {("first", "singular"): "am", ("second", "singular"): "ai",
+                    ("third", "singular"): "a", ("first", "plural"): "am",
+                    ("second", "plural"): "ați", ("third", "plural"): "au"},
+    "future":      {("first", "singular"): "voi", ("second", "singular"): "vei",
+                    ("third", "singular"): "va", ("first", "plural"): "vom",
+                    ("second", "plural"): "veți", ("third", "plural"): "vor"},
+    "conditional": {("first", "singular"): "aș", ("second", "singular"): "ai",
+                    ("third", "singular"): "ar", ("first", "plural"): "am",
+                    ("second", "plural"): "ați", ("third", "plural"): "ar"},
+}
+
+
+def aux(kind, person, number):
+    return _AUX[kind][(person, number)]
+
+
+# ── build verb lexicon from UniMorph ──────────────────────────────────────────────
+def _build_verbs():
+    verbs, part, ger = {}, {}, {}
+    with open(_UNIMORPH, encoding="utf-8") as fh:
+        for line in fh:
+            line = line.rstrip("\n")
+            if not line or "\t" not in line:
+                continue
+            parts = line.split("\t")
+            if len(parts) != 3:
+                continue
+            lemma, form, tag = parts
+            f = _feat_set(tag)
+            head = tag.split(";")[0]
+            if head == "V.PTCP":
+                if "PST" in f:
+                    part.setdefault(lemma, form)
+                continue
+            if head == "V.CVB":
+                if "PRS" in f:
+                    ger.setdefault(lemma, form)
+                continue
+            if head != "V":
+                continue
+            person = next((p for p in ("1", "2", "3") if p in f), None)
+            number = "SG" if "SG" in f else ("PL" if "PL" in f else None)
+            if person is None or number is None:
+                continue
+            # conjunctiv forms in UniMorph carry a leading 'să ' — strip it
+            surf = form
+            if surf.startswith("să "):
+                surf = surf[3:]
+            for (mood, tense), req in _VERB_KEYMAP.items():
+                if not req <= f:
+                    continue
+                if tense == "imperfect" and "PFV" in f:
+                    continue
+                if tense == "perfect_s" and "IPFV" in f:
+                    continue
+                # keep IND;PRS out of the PRF slot (mai-mult-ca-perfect etc. ignored)
+                if {"IND", "PRS"} <= req and "PRF" in f:
+                    continue
+                verbs.setdefault((lemma, f"{mood}|{tense}|{person}|{number}"), surf)
+                break
+    return verbs, part, ger
+
+
+# ── kaikki nouns: full declension paradigm per lemma ──────────────────────────────
+_EXCL = {"alternative", "archaic", "obsolete", "regional", "dialectal", "rare",
+         "table-tags", "inflection-template", "error-unrecognized-form",
+         "diminutive", "augmentative", "informal"}
+
+
+def _noun_key(tagset):
+    if tagset & _EXCL:
+        return None
+    if "vocative" in tagset:
+        case = "voc"
+    elif "genitive" in tagset or "dative" in tagset:
+        case = "gendat"
+    elif "nominative" in tagset or "accusative" in tagset:
+        case = "nomacc"
+    else:
+        return None
+    definite = "definite" in tagset and "indefinite" not in tagset
+    number = "PL" if "plural" in tagset else ("SG" if "singular" in tagset else None)
+    if number is None:
+        return None
+    return (case, definite, number)
+
+
+def _build_nouns():
+    nouns = {}   # lemma -> {"g":..., para:{(case,def,num):form}, "PL":plain_plural}
+    with open(_KAIKKI, encoding="utf-8") as fh:
+        for line in fh:
+            try:
+                d = json.loads(line)
+            except Exception:
+                continue
+            if d.get("pos") != "noun":
+                continue
+            word = d.get("word", "")
+            if not word or " " in word:
+                continue
+            ht = d.get("head_templates") or []
+            g = None
+            if ht:
+                a = str((ht[0].get("args") or {}).get("1") or "").lower()
+                if a[:1] in ("m", "f", "n"):
+                    g = a[:1]
+            entry = nouns.setdefault(word, {"g": g, "para": {}, "PL": None})
+            if entry["g"] is None and g:
+                entry["g"] = g
+            for x in (d.get("forms") or []):
+                fm = x.get("form")
+                tg = set(x.get("tags") or [])
+                if not fm or fm in ("-", "#", "") or " " in fm:
+                    continue
+                if tg == {"plural"} and not entry["PL"]:
+                    entry["PL"] = fm
+                k = _noun_key(tg)
+                if k and k not in entry["para"]:
+                    entry["para"][k] = fm
+    return nouns
+
+
+# ── adjectives from kaikki (UniMorph ron ADJ is sparse AND mis-tagged; kaikki is
+#    clean: the 4-form agreement pattern bun/bună/buni/bune). Neuter maps sg->masc,
+#    pl->fem, so 4 forms (m/f × SG/PL) fully cover it. ────────────────────────────
+def _build_adjs():
+    adjs = {}   # lemma -> {(gender,number): form}  gender in {m,f}
+    with open(_KAIKKI, encoding="utf-8") as fh:
+        for line in fh:
+            try:
+                d = json.loads(line)
+            except Exception:
+                continue
+            if d.get("pos") != "adj":
+                continue
+            word = d.get("word", "")
+            if not word or " " in word:
+                continue
+            d0 = adjs.setdefault(word, {})
+            d0.setdefault(("m", "SG"), word)          # masc sg = headword
+            for x in (d.get("forms") or []):
+                fm = x.get("form")
+                t = set(x.get("tags") or [])
+                if not fm or " " in fm or fm in ("-", "#") or (t & _EXCL):
+                    continue
+                if "definite" in t or "genitive" in t or "dative" in t:
+                    continue                           # keep indefinite nom/acc agr set
+                pl = "plural" in t
+                fem = "feminine" in t
+                masc = "masculine" in t
+                if fem and pl:
+                    d0.setdefault(("f", "PL"), fm)
+                elif masc and pl:
+                    d0.setdefault(("m", "PL"), fm)
+                elif fem and not pl:
+                    d0.setdefault(("f", "SG"), fm)
+                elif pl and not fem and not masc:       # bare plural -> both genders
+                    d0.setdefault(("m", "PL"), fm)
+                    d0.setdefault(("f", "PL"), fm)
+    return adjs
+
+
+def _build_cache():
+    verbs, part, ger = _build_verbs()
+    nouns = _build_nouns()
+    adjs = _build_adjs()
+    data = {"verbs": verbs, "part": part, "ger": ger, "nouns": nouns, "adjs": adjs}
+    try:
+        with open(_CACHE, "wb") as fh:
+            pickle.dump(data, fh, protocol=pickle.HIGHEST_PROTOCOL)
+    except OSError:
+        pass
+    return data
+
+
+def _load():
+    if os.path.exists(_CACHE):
+        srcs = [_UNIMORPH, _KAIKKI]
+        newest = max(os.path.getmtime(s) for s in srcs if os.path.exists(s))
+        if os.path.getmtime(_CACHE) >= newest:
+            try:
+                with open(_CACHE, "rb") as fh:
+                    return pickle.load(fh)
+            except Exception:
+                pass
+    return _build_cache()
+
+
+_LEX = _load()
+_VERBS, _PART, _GER, _NOUNS, _ADJS = (
+    _LEX["verbs"], _LEX["part"], _LEX["ger"], _LEX["nouns"], _LEX["adjs"])
+
+
+# ── rule verb conjugation fallback ────────────────────────────────────────────────
+def _vclass(lemma):
+    if lemma.endswith("a"):
+        return "a"
+    if lemma.endswith("ea"):
+        return "ea"
+    if lemma.endswith("e"):
+        return "e"
+    if lemma.endswith("i"):
+        return "i"
+    if lemma.endswith("î"):
+        return "î"
+    return None
+
+
+# regular present endings by class [1sg,2sg,3sg,1pl,2pl,3pl]
+_REG_PRS = {
+    "a":  ["", "i", "ă", "ăm", "ați", "ă"],       # a lucra type (simplified)
+    "ea": ["", "i", "e", "em", "eți", "", ],
+    "e":  ["", "i", "e", "em", "eți", ""],
+    "i":  ["esc", "ești", "ește", "im", "iți", "esc"],  # -i type (a vorbi)
+    "î":  ["ăsc", "ăști", "ăște", "âm", "âți", "ăsc"],
+}
+_SLOT = {("first", "singular"): 0, ("second", "singular"): 1, ("third", "singular"): 2,
+         ("first", "plural"): 3, ("second", "plural"): 4, ("third", "plural"): 5}
+
+
+def _rule_conjugate(lemma, mood, tense, person, number):
+    vc = _vclass(lemma)
+    if vc is None:
+        return None
+    i = _SLOT[(person, number)]
+    body = lemma[:-len(vc)]
+    if mood == "ind" and tense == "present":
+        end = _REG_PRS[vc][i]
+        return body + end
+    if mood == "ind" and tense == "imperfect":
+        # -a/-i/-î -> stem + a/eai...; -e/-ea -> eam. Simplified regular imperfect.
+        stem = body
+        endings = {"a": ["am", "ai", "a", "am", "ați", "au"],
+                   "i": ["eam", "eai", "ea", "eam", "eați", "eau"],
+                   "î": ["am", "ai", "a", "am", "ați", "au"],
+                   "e": ["eam", "eai", "ea", "eam", "eați", "eau"],
+                   "ea": ["eam", "eai", "ea", "eam", "eați", "eau"]}[vc]
+        return stem + endings[i]
+    return None
+
+
+# ── PUBLIC verb API ───────────────────────────────────────────────────────────────
+def conjugate(lemma, mood, tense, person, number):
+    lemma = lemma.strip().lower()
+    key = f"{mood}|{tense}|{_PERSON.get(person,'?')}|{_NUMBER.get(number,'?')}"
+    ir = _IRREG.get(lemma)
+    if ir and key in ir:
+        return ir[key], "lexicon"
+    form = _VERBS.get((lemma, key))
+    if form:
+        return form, "lexicon"
+    r = _rule_conjugate(lemma, mood, tense, person, number)
+    if r is not None:
+        return r, "rule"
+    return lemma, "fallback"
+
+
+def participle(lemma):
+    """Past participle — INVARIABLE in the perfect compus (am mers, am văzut)."""
+    lemma = lemma.strip().lower()
+    ir = _IRREG.get(lemma)
+    if ir and "part" in ir:
+        return ir["part"], "lexicon"
+    if lemma in _PART:
+        return _PART[lemma], "lexicon"
+    vc = _vclass(lemma)
+    if vc == "a":
+        return lemma[:-1] + "at", "rule"
+    if vc in ("ea",):
+        return lemma[:-2] + "ut", "rule"
+    if vc == "i":
+        return lemma[:-1] + "it", "rule"
+    if vc == "î":
+        return lemma[:-1] + "ât", "rule"
+    if vc == "e":
+        return lemma[:-1] + "ut", "rule"
+    return lemma, "fallback"
+
+
+def gerund(lemma):
+    lemma = lemma.strip().lower()
+    ir = _IRREG.get(lemma)
+    if ir and "ger" in ir:
+        return ir["ger"], "lexicon"
+    if lemma in _GER:
+        return _GER[lemma], "lexicon"
+    vc = _vclass(lemma)
+    if vc in ("a", "î"):
+        return lemma[:-1] + "ând", "rule"
+    if vc in ("ea", "e", "i"):
+        return lemma[:-len(vc)] + "ind", "rule"
+    return lemma, "fallback"
+
+
+# ── noun gender ───────────────────────────────────────────────────────────────────
+def noun_gender(lemma):
+    lemma = lemma.strip().lower()
+    d = _NOUNS.get(lemma)
+    if d and d.get("g") in ("m", "f", "n"):
+        return d["g"]
+    if lemma.endswith(("ă", "a", "e")):
+        return "f"
+    return "m"
+
+
+# ── SUFFIXED DEFINITE ARTICLE — rule engine (fallback for OOV nouns) ───────────────
+def definite_suffix(noun, gender, number, case="nomacc"):
+    """Attach the enclitic definite article by gender + ending. Returns (form, conf).
+    This is the headline Romanian-specific engine extension."""
+    n = noun
+    g = gender
+    if number == "singular":
+        if g in ("m", "n"):
+            if case == "gendat":
+                # masc/neut gen-dat definite: -lui
+                if n.endswith("e"):
+                    return n + "lui", "rule"       # câine -> câinelui
+                if n.endswith("u"):
+                    return n + "lui", "rule"
+                return n + "ului", "rule"          # om -> omului
+            # nom/acc
+            if n.endswith("e"):
+                return n + "le", "rule"            # câine -> câinele
+            if n.endswith("u"):
+                return n + "l", "rule"             # codru -> codrul
+            if n.endswith("i"):
+                return n + "ul", "rule"
+            return n + "ul", "rule"                # om -> omul
+        # feminine singular
+        if case == "gendat":
+            # fem gen/dat definite = plural-stem + i (casei, fetei) — needs plural;
+            # approximated as: -ă->-ei, -e->-ei, -a->-alei
+            if n.endswith("ă"):
+                return n[:-1] + "ei", "rule"       # casă -> casei
+            if n.endswith("e"):
+                return n[:-1] + "ei", "rule"       # carte -> cărții(approx cartei)
+            if n.endswith("a"):
+                return n[:-1] + "lei", "rule"
+            return n + "i", "rule"
+        # fem nom/acc
+        if n.endswith("ă"):
+            return n[:-1] + "a", "rule"            # casă -> casa
+        if n.endswith("e"):
+            return n[:-1] + "ea", "rule"           # carte -> cartea
+        if n.endswith("a"):
+            return n + "ua", "rule"                # stea -> steaua
+        if n.endswith("i"):
+            return n + "a", "rule"
+        return n + "a", "rule"
+    # plural
+    if case == "gendat":
+        base = noun
+        return base + "lor", "rule"                # -lor for all gen/dat pl
+    if g == "m":
+        return noun + "i", "rule"                  # oameni -> oamenii (+i)
+    return noun + "le", "rule"                     # case -> casele, trenuri->trenurile
+
+
+# ── rule pluralization (fallback) ─────────────────────────────────────────────────
+def _rule_plural(noun, gender):
+    if gender == "f":
+        if noun.endswith("ă"):
+            return noun[:-1] + "e"
+        if noun.endswith("e"):
+            return noun[:-1] + "i"
+        if noun.endswith("a"):
+            return noun[:-1] + "le"
+        return noun + "e"
+    if gender == "n":
+        return noun + "uri"
+    # masculine
+    if noun.endswith(("e",)):
+        return noun[:-1] + "i"
+    return noun + "i"
+
+
+# ── PUBLIC noun inflection ────────────────────────────────────────────────────────
+def inflect_noun(lemma, number, gender=None, case="nomacc", definite=False):
+    lemma = lemma.strip().lower()
+    g = gender or noun_gender(lemma)
+    d = _NOUNS.get(lemma)
+    numk = "SG" if number == "singular" else "PL"
+    if d:
+        if case == "voc":
+            form = d["para"].get(("voc", True, numk)) or d["para"].get(("voc", False, numk))
+            if form:
+                return form, "lexicon"
+        # try the exact paradigm cell from kaikki (lexically grounded)
+        form = d["para"].get((case, definite, numk))
+        if form:
+            return form, "lexicon"
+        # indefinite fallbacks from the paradigm
+        if not definite:
+            form = d["para"].get(("nomacc", False, numk))
+            if form:
+                return form, "lexicon"
+            if numk == "PL" and d.get("PL"):
+                return d["PL"], "lexicon"
+            if numk == "SG":
+                return lemma, "lexicon"
+    # rule path
+    base = lemma if number == "singular" else _rule_plural(lemma, g)
+    if definite:
+        return definite_suffix(base, g, number, case)
+    return base, ("rule" if d is None else "lexicon")
+
+
+# ── PUBLIC adjective agreement ────────────────────────────────────────────────────
+def _neuter_map(gender, number):
+    # neuter agrees masculine in SG, feminine in PL
+    if gender == "n":
+        return "m" if number == "singular" else "f"
+    return gender
+
+
+def inflect_adj(lemma, gender, number, case="nomacc", definite=False):
+    lemma = lemma.strip().lower()
+    numk = "SG" if number == "singular" else "PL"
+    eg = _neuter_map(gender, number)          # neuter -> masc(SG)/fem(PL)
+    d = _ADJS.get(lemma)
+    if d:
+        form = d.get((eg, numk))
+        if form:
+            return form, "lexicon"
+    # rule fallback: 4-form pattern bun/bună/buni/bune keyed by effective gender
+    a = lemma
+    if number == "singular":
+        if eg == "f":
+            if a.endswith("e"):
+                return a, "rule"                            # mare invariant sg
+            if a.endswith("u"):
+                return a[:-1] + "ă", "rule"                 # nou -> nouă
+            if a.endswith("ă"):
+                return a, "rule"
+            return a + "ă", "rule"                          # bun -> bună
+        return a, "rule"                                    # masc/neut sg = lemma
+    # plural
+    if eg == "f":
+        if a.endswith("e"):
+            return a[:-1] + "i", "rule"                     # mare -> mari
+        if a.endswith("u"):
+            return a[:-1] + "e", "rule"                     # nou -> noue (approx; 'noi' irr)
+        if a.endswith("ă"):
+            return a[:-1] + "e", "rule"
+        return a + "e", "rule"                              # bun -> bune
+    # masc/neut(SG-only)->here masc pl -> -i
+    if a.endswith("e"):
+        return a[:-1] + "i", "rule"                         # mare -> mari
+    if a.endswith("u"):
+        return a[:-1] + "i", "rule"
+    return a + "i", "rule"                                  # bun -> buni
+
+
+def lexicon_stats():
+    return {
+        "verb_source": "UniMorph Romanian (github.com/unimorph/ron) + curated "
+                       "irregulars (avea/vrea/da + aux clitic paradigms)",
+        "noun_source": "kaikki.org Romanian — full case/definite/vocative declension",
+        "adj_source": "UniMorph Romanian ADJ (case×gender×number×definiteness)",
+        "license": "CC-BY-SA 3.0 (Wiktionary/UniMorph lineage)",
+        "unimorph_verb_forms": len(_VERBS),
+        "unimorph_verb_lemmas": len({k[0] for k in _VERBS}),
+        "irregular_verb_lemmas": len(_IRREG),
+        "participle_lemmas": len(_PART),
+        "noun_lemmas": len(_NOUNS),
+        "adj_lemmas": len(_ADJS),
+    }
+
+
+if __name__ == "__main__":
+    print(json.dumps(lexicon_stats(), indent=2, ensure_ascii=False))
+    print("\n── SUFFIXED DEFINITE ARTICLE (the headline delta) ──")
+    for n, g in [("om", "m"), ("băiat", "m"), ("casă", "f"), ("carte", "f"),
+                 ("tren", "n"), ("student", "m"), ("floare", "f")]:
+        sg = inflect_noun(n, "singular", g, "nomacc", True)
+        pl = inflect_noun(n, "plural", g, "nomacc", True)
+        gd = inflect_noun(n, "singular", g, "gendat", True)
+        vo = inflect_noun(n, "singular", g, "voc", False)
+        print(f"  {n:8}({g}) def.sg={sg[0]:12} def.pl={pl[0]:14} "
+              f"gen/dat.sg={gd[0]:12} voc={vo[0]}")
+    print("\n── NEUTER split agreement (tren: masc SG / fem PL) ──")
+    print("  tren nou   ->", inflect_noun("tren", "singular", "n")[0],
+          inflect_adj("nou", "n", "singular")[0])
+    print("  trenuri noi->", inflect_noun("tren", "plural", "n")[0],
+          inflect_adj("nou", "n", "plural")[0])
+    print("\n── verbs ──")
+    for l, m, t, p, n, in [("merge", "ind", "present", "third", "singular"),
+                           ("avea", "ind", "present", "first", "singular"),
+                           ("fi", "ind", "present", "third", "singular"),
+                           ("vorbi", "ind", "present", "third", "plural"),
+                           ("face", "sbjv", "present", "third", "singular"),
+                           ("lucra", "ind", "imperfect", "third", "singular")]:
+        print(f"  {l:8}{m}/{t:10}{p[:3]}.{n[:2]} -> {conjugate(l,m,t,p,n)}")
+    print("  perfect-aux(3sg):", aux("perfect", "third", "singular"),
+          "| future(1sg):", aux("future", "first", "singular"),
+          "| cond(3sg):", aux("conditional", "third", "singular"))
+    print("  participle merge/vedea:", participle("merge"), participle("vedea"))

elp/tests/run.sh

@@ -22,7 +22,7 @@ cd "$(dirname "$0")"
 
 EL_HOME="${EL_HOME:-$(cd ../.. && pwd)/el}"
 ELC="${ELC:-${EL_HOME}/dist/platform/elc}"
-RUNTIME_DIR="${EL_HOME}/runtime"
+RUNTIME_DIR="${EL_HOME}/el-compiler/runtime"
 SRC_DIR="$(cd .. && pwd)/src"
 
 if [ ! -x "${ELC}" ]; then

engram/.gitignore

@@ -1,6 +1,3 @@
-.DS_Store
-*.db
-*.elc
-*.elh
-dist/
 target/
+*.db
+.DS_Store

engram/src/server.el

@@ -132,7 +132,7 @@ fn route_text_health(method: String, path: String, body: String) -> String {
 // any durable write that follows persists the pruning too).
 fn persist_canonical() -> Int {
     let dir_raw: String = env("ENGRAM_DATA_DIR")
-    let dir: String = engram_resolve_data_dir()
+    let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
     // (2026-08-10 self-review) This returned a hardcoded 1, which made every
     // caller's `let saved: Int = persist_canonical()` a dead variable — six
     // durable write paths each believed they had confirmation of a successful
@@ -140,57 +140,6 @@ fn persist_canonical() -> Int {
     return engram_save(dir + "/snapshot.json")
 }
 
-// ── WAL persistence (design doc §§3-14; gated behind ENGRAM_WAL=on) ──────────
-// Default OFF → every persist path below is byte-identical to the historical
-// per-write full-snapshot behavior. When ON, structural mutations append O(1)
-// WAL records instead of rewriting the whole graph, with threshold compaction.
-fn wal_on() -> Bool {
-    str_eq(env("ENGRAM_WAL"), "on")
-}
-
-// Persist a single-node mutation (create / content-evolve / strengthen).
-fn persist_node(id: String) -> Int {
-    if wal_on() {
-        let d: String = engram_resolve_data_dir()
-        let a: Int = engram_wal_node_put(d, id)
-        let c: Int = engram_wal_maybe_compact(d)
-        return a
-    }
-    return persist_canonical()
-}
-
-// Persist edges appended at index >= start (covers single-edge and batch).
-fn persist_edges_since(start: Int) -> Int {
-    if wal_on() {
-        let d: String = engram_resolve_data_dir()
-        let a: Int = engram_wal_edges_since(d, start)
-        let c: Int = engram_wal_maybe_compact(d)
-        return a
-    }
-    return persist_canonical()
-}
-
-// Persist a Hebbian consolidation batch as ONE WAL record (single fsync, §5-B).
-fn persist_hebb_batch(start: Int) -> Int {
-    if wal_on() {
-        let d: String = engram_resolve_data_dir()
-        let a: Int = engram_wal_hebb_batch(d, start)
-        let c: Int = engram_wal_maybe_compact(d)
-        return a
-    }
-    return persist_canonical()
-}
-
-// Bulk mutation (embedding backfill, load-merge): write a fresh compaction base
-// so the many-node change is durable in one atomic snapshot; WAL is truncated.
-fn persist_bulk() -> Int {
-    if wal_on() {
-        let d: String = engram_resolve_data_dir()
-        return engram_wal_compact(d)
-    }
-    return persist_canonical()
-}
-
 // INCOMPLETE-ROUTE FIX (2026-07-24 self-review): this route silently dropped
 // label, importance, tier, and tags — engram_node() defaults label to content
 // and importance to 0.5, so every node created over HTTP lost its metadata.
@@ -232,7 +181,7 @@ fn route_create_node(method: String, path: String, body: String) -> String {
         salience, importance, confidence,
         tier, tags
     )
-    let saved: Int = persist_node(id)
+    let saved: Int = persist_canonical()
     "{\"id\":\"" + id + "\",\"content\":\"" + content + "\",\"node_type\":\"" + node_type + "\"}"
 }
 
@@ -259,7 +208,7 @@ fn route_scan_nodes(method: String, path: String, body: String) -> String {
 // clobbered the good snapshot. Read routes must never write the canonical path.)
 fn route_scan_edges(method: String, path: String, body: String) -> String {
     let dir_raw: String = env("ENGRAM_DATA_DIR")
-    let dir: String = engram_resolve_data_dir()
+    let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
     let snap_path: String = dir + "/.scan-export.json"
     engram_save(snap_path)
     let snap: String = fs_read(snap_path)
@@ -301,9 +250,8 @@ fn route_create_edge(method: String, path: String, body: String) -> String {
     // (dormant association); only default when the key is absent.
     let w_present: String = json_get_raw(body, "weight")
     let weight: Float = if str_eq(w_present, "") { 0.5 } else { json_get_float(body, "weight") }
-    let ec0: Int = engram_edge_count()
     engram_connect(from_id, to_id, weight, relation)
-    let saved: Int = persist_edges_since(ec0)
+    let saved: Int = persist_canonical()
     "{\"ok\":true,\"from_id\":\"" + from_id + "\",\"to_id\":\"" + to_id + "\",\"relation\":\"" + relation + "\"}"
 }
 
@@ -328,7 +276,6 @@ fn route_create_edges_batch(method: String, path: String, body: String) -> Strin
     if str_eq(arr, "") { return err_json("missing edges array") }
     let n: Int = json_array_len(arr)
     if n == 0 { return "{\"ok\":true,\"accepted\":0,\"skipped\":0}" }
-    let ec0: Int = engram_edge_count()
     let i: Int = 0
     let accepted: Int = 0
     let skipped: Int = 0
@@ -352,7 +299,7 @@ fn route_create_edges_batch(method: String, path: String, body: String) -> Strin
     // Skip it when nothing was accepted: an all-malformed payload must not
     // trigger a 60MB write.
     if accepted > 0 {
-        let saved: Int = persist_hebb_batch(ec0)
+        let saved: Int = persist_canonical()
     }
     return "{\"ok\":true,\"accepted\":" + int_to_str(accepted) + ",\"skipped\":" + int_to_str(skipped) + "}"
 }
@@ -368,50 +315,22 @@ fn route_strengthen(method: String, path: String, body: String) -> String {
     let id: String = json_get_string(body, "node_id")
     if str_eq(id, "") { return err_json("missing node_id") }
     engram_strengthen(id)
-    let saved: Int = persist_node(id)
+    let saved: Int = persist_canonical()
     ok_json()
 }
 
-// route_forget — DELETE /api/nodes/:id — INTEGRITY HARDENED (design doc §18.1).
-//
-// Two invariants now enforced AT THE STORE (not one layer up in neuron-api.el,
-// which a direct HTTP client could bypass):
-//   1. Write-protection: protected identity/value nodes (derived from the self
-//      graph — self root + values hub + their neighbors, §18.3) cannot be
-//      deleted over HTTP. Returns 403, node untouched.
-//   2. No hard delete over the wire, ever: an ordinary delete creates a
-//      Tombstone marker node + `tombstones` edge and KEEPS the original node
-//      and its edges (recoverable), instead of the old destructive
-//      engram_forget() shift-delete. Raw engram_forget is now internal-GC only
-//      and no longer reachable from any HTTP route.
 fn route_forget(method: String, path: String, body: String) -> String {
     let id: String = extract_id(path, "/api/nodes/")
     if str_eq(id, "") { return err_json("missing id") }
-    if engram_is_protected(id) == 1 {
-        return "{\"__status__\":403,\"error\":\"protected node; deletion refused\",\"id\":\"" + id + "\"}"
-    }
-    let tomb_id: String = engram_node_full(
-        "tombstone:" + id, "Tombstone", "tombstone:" + id,
-        0.1, 0.1, 1.0, "Episodic", "[\"tombstone\"]"
-    )
-    let ec0: Int = engram_edge_count()
-    engram_connect(tomb_id, id, 1.0, "tombstones")
-    let saved: Int = if wal_on() {
-        let d: String = engram_resolve_data_dir()
-        let a: Int = engram_wal_node_put(d, tomb_id)
-        let b: Int = engram_wal_edges_since(d, ec0)
-        let c: Int = engram_wal_maybe_compact(d)
-        a
-    } else {
-        persist_canonical()
-    }
-    "{\"ok\":true,\"tombstoned\":\"" + id + "\",\"tombstone_id\":\"" + tomb_id + "\"}"
+    engram_forget(id)
+    let saved: Int = persist_canonical()
+    ok_json()
 }
 
 fn route_save(method: String, path: String, body: String) -> String {
     let p_raw: String = json_get_string(body, "path")
     let dir_raw: String = env("ENGRAM_DATA_DIR")
-    let dir: String = engram_resolve_data_dir()
+    let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
     let p: String = if str_eq(p_raw, "") { dir + "/snapshot.json" } else { p_raw }
     // (2026-08-10 self-review) engram_save returns 0 on an empty path and the
     // route discarded it, so the response was a literal "ok":true regardless
@@ -427,7 +346,7 @@ fn route_save(method: String, path: String, body: String) -> String {
 fn route_load(method: String, path: String, body: String) -> String {
     let p_raw: String = json_get_string(body, "path")
     let dir_raw: String = env("ENGRAM_DATA_DIR")
-    let dir: String = engram_resolve_data_dir()
+    let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
     let p: String = if str_eq(p_raw, "") { dir + "/snapshot.json" } else { p_raw }
     // (2026-08-10 self-review) This was a stub response over the single most
     // destructive operation in the server. engram_load returns 0 on an empty
@@ -479,7 +398,7 @@ fn route_embed_backfill(method: String, path: String, body: String) -> String {
     let result: String = engram_embed_backfill(n)
     let done: Float = json_get_float(result, "embedded")
     if done > 0.0 {
-        let saved: Int = persist_bulk()
+        let saved: Int = persist_canonical()
     }
     return result
 }
@@ -498,7 +417,7 @@ fn route_embed_backfill(method: String, path: String, body: String) -> String {
 // (2026-06-27 self-review: added this route to fix silent 10-min sync failures)
 fn route_sync(method: String, path: String, body: String) -> String {
     let dir_raw: String = env("ENGRAM_DATA_DIR")
-    let dir: String = engram_resolve_data_dir()
+    let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
     // 2026-07-21 self-review: export to a scratch path, never the canonical
     // snapshot.json — read routes must not be able to clobber the good snapshot.
     let snap_path: String = dir + "/.sync-export.json"
@@ -532,7 +451,7 @@ fn route_load_merge(method: String, path: String, body: String) -> String {
     engram_load_merge(p)
     let added_n: Int = engram_node_count() - before_n
     let added_e: Int = engram_edge_count() - before_e
-    let saved: Int = persist_bulk()
+    let saved: Int = persist_canonical()
     "{\"ok\":true,\"nodes_added\":" + int_to_str(added_n) + ",\"edges_added\":" + int_to_str(added_e) + ",\"node_count\":" + int_to_str(engram_node_count()) + "}"
 }
 
@@ -631,7 +550,7 @@ fn route_capture_knowledge(method: String, path: String, body: String) -> String
         sal, imp, conf,
         "Semantic", tags
     )
-    let saved: Int = persist_node(id)
+    let saved: Int = persist_canonical()
     "{\"ok\":true,\"id\":\"" + id + "\"}"
 }
 
@@ -794,21 +713,11 @@ let bind_str: String = if str_eq(bind_raw, "") { ":8742" } else { bind_raw }
 let port: Int = parse_port(bind_str)
 
 // On startup, try to load any existing snapshot (best effort).
-// §18.2: resolve the data dir safely — unset ENGRAM_DATA_DIR → $HOME/.neuron/engram,
-// never /tmp; fail loud if HOME is unresolvable (engram_resolve_data_dir exits).
-let data_dir: String = engram_resolve_data_dir()
+let data_dir_raw: String = env("ENGRAM_DATA_DIR")
+let data_dir: String = if str_eq(data_dir_raw, "") { "/tmp/engram" } else { data_dir_raw }
 let snapshot_path: String = data_dir + "/snapshot.json"
 engram_load(snapshot_path)
 
-// WAL replay (design doc §6). Gated: default OFF is byte-identical to legacy
-// snapshot-only boot. When ON, the snapshot above is the compaction BASE and
-// the WAL carries every mutation since; replay reconstructs state to the last
-// CRC-valid record, then opens the WAL for appending.
-if wal_on() {
-    let replayed: Int = engram_wal_boot(data_dir)
-    println("[engram] WAL enabled — replayed " + int_to_str(replayed) + " records")
-}
-
 // 2026-07-21 self-review boot guard: if the snapshot file has content but the
 // load produced 0 nodes, something is wrong (corrupt file / parse failure).
 // Preserve the evidence and warn loudly — and since read routes no longer write

engram/test/run_wal_tests.sh

@@ -1,16 +0,0 @@
-#!/usr/bin/env bash
-# WAL unit + integration + crash-fuzz gate. Throwaway HOME/dirs only.
-set -e
-HERE="$(cd "$(dirname "$0")" && pwd)"
-REL="$HERE/../../lang/runtime"
-cc -O2 -fbracket-depth=1024 -Wno-parentheses-equality -I"$REL" \
-   "$HERE/test_wal.c" -lcurl -lpthread -o /tmp/test_wal
-HOME=/tmp/engram-throwaway-home /tmp/test_wal
-# Fail-loud data-dir check (must exit 1 with a FATAL line):
-cat > /tmp/test_failloud.c <<'C'
-#include "el_runtime.c"
-int main(void){ unsetenv("ENGRAM_DATA_DIR"); unsetenv("HOME");
-  engram_resolve_data_dir(); printf("REACHED\n"); return 0; }
-C
-cc -O2 -fbracket-depth=1024 -Wno-parentheses-equality -I"$REL" /tmp/test_failloud.c -lcurl -lpthread -o /tmp/test_failloud
-if env -u HOME -u ENGRAM_DATA_DIR /tmp/test_failloud; then echo "FAIL: should have exited"; exit 1; else echo "[PASS] fail-loud exit on unresolvable HOME"; fi

engram/test/test_wal.c

@@ -1,473 +0,0 @@
-/* test_wal.c — unit + integration + crash-fuzz harness for the engram WAL.
- *
- * Includes el_runtime.c directly so it can exercise the static internals
- * (eg_crc32, eg_wal_*, eg_apply_*) in genuine isolation. Build:
- *   cc -O2 -fbracket-depth=1024 -I<release-dir> test_wal.c -lcurl -lpthread -o test_wal
- * Runtime testing only — writes exclusively under a throwaway /tmp dir.
- */
-#define ENGRAM_TEST_BUILD 1
-#include "el_runtime.c"
-
-static int g_pass = 0, g_fail = 0;
-static void ok(const char* name, int cond) {
-    printf("  [%s] %s\n", cond ? "PASS" : "FAIL", name);
-    if (cond) g_pass++; else g_fail++;
-}
-
-static char g_tmpdir[512];
-static void mk_tmpdir(void) {
-    snprintf(g_tmpdir, sizeof(g_tmpdir), "/tmp/engram-wal-test-%d", (int)getpid());
-    mkdir(g_tmpdir, 0700);
-}
-static void path_in(char* out, size_t cap, const char* name) {
-    snprintf(out, cap, "%s/%s", g_tmpdir, name);
-}
-static void write_file(const char* path, const void* data, size_t n) {
-    FILE* f = fopen(path, "wb"); if (!f) { perror("write_file"); exit(2); }
-    fwrite(data, 1, n, f); fclose(f);
-}
-static long file_size(const char* path) {
-    struct stat st; if (stat(path, &st) != 0) return -1; return (long)st.st_size;
-}
-static void reset_store(void) {
-    char p[600]; path_in(p, sizeof(p), "_reset.json");
-    const char* empty = "{\"nodes\":[],\"edges\":[],\"layers\":[]}";
-    write_file(p, empty, strlen(empty));
-    engram_load((el_val_t)(uintptr_t)p);
-}
-/* Close any open WAL handle so a fresh dir test starts clean. */
-static void wal_close(void) {
-    if (eg_wal.fp) { fclose(eg_wal.fp); eg_wal.fp = NULL; }
-    eg_wal.path[0] = 0; eg_wal.lsn = 0; eg_wal.bytes = 0; eg_wal.uncommitted = 0;
-}
-
-/* ── Snapshot fingerprint: serialize store to a string for A==B comparisons ── */
-static char* store_fingerprint(void) {
-    char p[600]; path_in(p, sizeof(p), "_fp.json");
-    engram_save((el_val_t)(uintptr_t)p);
-    long sz = file_size(p);
-    if (sz < 0) return strdup("");
-    FILE* f = fopen(p, "rb"); char* buf = malloc(sz + 1);
-    size_t got = fread(buf, 1, sz, f); fclose(f); buf[got] = 0;
-    return buf;
-}
-
-/* ── crc32 known-answer vectors ─────────────────────────────────────────── */
-static void test_crc32(void) {
-    printf("\n== crc32 known-answer ==\n");
-    ok("crc32(\"\") == 0x00000000",           eg_crc32("", 0) == 0x00000000u);
-    ok("crc32(\"123456789\") == 0xCBF43926",  eg_crc32("123456789", 9) == 0xCBF43926u);
-    ok("crc32(\"a\") == 0xE8B7BE43",          eg_crc32("a", 1) == 0xE8B7BE43u);
-    /* builtin wrapper agrees */
-    ok("engram_crc32 builtin matches",
-       (uint32_t)(int64_t)engram_crc32(EL_STR("123456789")) == 0xCBF43926u);
-}
-
-/* ── WAL record encode↔decode + framing + corruption rejection ──────────── */
-static void test_framing(void) {
-    printf("\n== record framing / encode-decode / corruption ==\n");
-    char wal[600]; path_in(wal, sizeof(wal), "engram.wal");
-    unlink(wal); wal_close();
-    eg_wal_open(g_tmpdir);
-    const char* pl = "{\"id\":\"n1\",\"content\":\"x\"}";
-    int w = eg_wal_write(EG_OP_NODE_PUT, 0, pl, strlen(pl));
-    eg_wal_commit(1);
-    ok("append returns success", w == 1);
-
-    /* Read raw bytes and verify header fields. */
-    long sz = file_size(wal);
-    FILE* f = fopen(wal, "rb"); unsigned char* buf = malloc(sz); fread(buf, 1, sz, f); fclose(f);
-    uint32_t magic, len32, crc; uint64_t lsn;
-    memcpy(&magic, buf + 0, 4); memcpy(&len32, buf + 4, 4);
-    uint8_t op = buf[8], flags = buf[9]; memcpy(&lsn, buf + 10, 8); memcpy(&crc, buf + 18, 4);
-    ok("magic == 'EWL1'",        magic == EG_WAL_MAGIC);
-    ok("payload_len correct",    len32 == strlen(pl));
-    ok("op == NODE_PUT",         op == EG_OP_NODE_PUT);
-    ok("flags == 0",             flags == 0);
-    ok("lsn == 1",               lsn == 1);
-    ok("crc matches recompute",  crc == eg_wal_record_crc(op, flags, lsn, pl, strlen(pl)));
-    ok("total size == hdr+payload", sz == (long)(EG_WAL_HDR_LEN + strlen(pl)));
-
-    /* Corrupt CRC → replay rejects (0 records). */
-    { char bad[600]; path_in(bad, sizeof(bad), "bad_crc.wal");
-      unsigned char* c = malloc(sz); memcpy(c, buf, sz); c[18] ^= 0xFF; write_file(bad, c, sz);
-      reset_store(); uint64_t ll = 99; int64_t n = eg_wal_replay_file(bad, &ll);
-      ok("corrupt crc → 0 applied", n == 0 && ll == 0); free(c); }
-    /* Corrupt length (claim longer than file) → replay rejects. */
-    { char bad[600]; path_in(bad, sizeof(bad), "bad_len.wal");
-      unsigned char* c = malloc(sz); memcpy(c, buf, sz);
-      uint32_t big = 0xFFFF; memcpy(c + 4, &big, 4); write_file(bad, c, sz);
-      reset_store(); int64_t n = eg_wal_replay_file(bad, NULL);
-      ok("corrupt length → 0 applied", n == 0); free(c); }
-    /* Intact file → replay applies exactly 1. */
-    { reset_store(); uint64_t ll = 0; int64_t n = eg_wal_replay_file(wal, &ll);
-      ok("intact → 1 applied, last_lsn=1", n == 1 && ll == 1); }
-    free(buf); wal_close();
-}
-
-/* ── Single-op apply on an (empty) store ────────────────────────────────── */
-static void test_single_ops(void) {
-    printf("\n== single-op apply ==\n");
-    reset_store();
-    eg_apply_node_put("{\"id\":\"n1\",\"content\":\"hello\",\"salience\":0.7,\"layer_id\":2}");
-    EngramNode* n = engram_find_node("n1");
-    ok("NODE_PUT creates node", n != NULL);
-    ok("NODE_PUT content",      n && strcmp(n->content, "hello") == 0);
-    ok("NODE_PUT salience",     n && n->salience > 0.69 && n->salience < 0.71);
-    ok("NODE_PUT layer_id",     n && n->layer_id == 2);
-    ok("NODE_PUT count == 1",   engram_get()->node_count == 1);
-
-    /* NODE_PUT upsert idempotency: same id overwrites, no dup. */
-    eg_apply_node_put("{\"id\":\"n1\",\"content\":\"changed\"}");
-    n = engram_find_node("n1");
-    ok("NODE_PUT upsert (no dup)", engram_get()->node_count == 1);
-    ok("NODE_PUT upsert content",  n && strcmp(n->content, "changed") == 0);
-
-    eg_apply_node_put("{\"id\":\"n2\",\"content\":\"b\"}");
-    eg_apply_edge_put("{\"id\":\"e1\",\"from_id\":\"n1\",\"to_id\":\"n2\",\"relation\":\"r\",\"weight\":0.4,\"hebb\":0.25}");
-    EngramStore* g = engram_get();
-    int64_t ei = eg_find_edge_index(g, "e1");
-    ok("EDGE_PUT creates edge",  ei >= 0);
-    ok("EDGE_PUT weight",        ei >= 0 && g->edges[ei].weight > 0.39 && g->edges[ei].weight < 0.41);
-    ok("EDGE_PUT hebb",          ei >= 0 && g->edges[ei].hebb > 0.24 && g->edges[ei].hebb < 0.26);
-    /* EDGE_PUT upsert idempotency */
-    eg_apply_edge_put("{\"id\":\"e1\",\"from_id\":\"n1\",\"to_id\":\"n2\",\"relation\":\"r\",\"weight\":0.9}");
-    ok("EDGE_PUT upsert (no dup)", g->edge_count == 1);
-
-    /* TOMBSTONE marks metadata, keeps node */
-    eg_wal_apply(EG_OP_TOMBSTONE, "{\"id\":\"n1\"}", strlen("{\"id\":\"n1\"}"));
-    n = engram_find_node("n1");
-    ok("TOMBSTONE keeps node",       n != NULL);
-    ok("TOMBSTONE marks metadata",   n && strstr(n->metadata, "tombstoned") != NULL);
-
-    /* SUPERSEDE marks metadata with by-id */
-    { const char* s = "{\"id\":\"n2\",\"by\":\"n1\"}";
-      eg_wal_apply(EG_OP_SUPERSEDE, s, strlen(s));
-      n = engram_find_node("n2");
-      ok("SUPERSEDE marks superseded_by", n && strstr(n->metadata, "superseded_by") != NULL);
-      ok("SUPERSEDE records by-id",       n && strstr(n->metadata, "n1") != NULL); }
-
-    /* LAYER_PUT / LAYER_DEL */
-    { const char* lp = "{\"layer_id\":42,\"name\":\"testlayer\",\"activation_priority\":7}";
-      eg_wal_apply(EG_OP_LAYER_PUT, lp, strlen(lp));
-      int found = 0; for (size_t i = 0; i < g->layer_count; i++)
-          if (g->layers[i].layer_id == 42 && g->layers[i].name && strcmp(g->layers[i].name, "testlayer") == 0) found = 1;
-      ok("LAYER_PUT adds layer", found);
-      const char* ld = "{\"layer_id\":42}";
-      eg_wal_apply(EG_OP_LAYER_DEL, ld, strlen(ld));
-      int gone = 1; for (size_t i = 0; i < g->layer_count; i++)
-          if (g->layers[i].layer_id == 42 && g->layers[i].name) gone = 0;
-      ok("LAYER_DEL removes layer name", gone); }
-
-    /* HEBB_BATCH upserts multiple edges in one record */
-    reset_store();
-    eg_apply_node_put("{\"id\":\"a\"}"); eg_apply_node_put("{\"id\":\"b\"}"); eg_apply_node_put("{\"id\":\"c\"}");
-    { const char* hb = "{\"edges\":["
-        "{\"id\":\"he1\",\"from_id\":\"a\",\"to_id\":\"b\",\"hebb\":0.1},"
-        "{\"id\":\"he2\",\"from_id\":\"b\",\"to_id\":\"c\",\"hebb\":0.2}]}";
-      eg_wal_apply(EG_OP_HEBB_BATCH, hb, strlen(hb));
-      ok("HEBB_BATCH upserts 2 edges", engram_get()->edge_count == 2); }
-
-    /* FORGET hard-removes node + incident edges */
-    { const char* fg = "{\"id\":\"b\"}";
-      eg_wal_apply(EG_OP_FORGET, fg, strlen(fg));
-      ok("FORGET removes node",        engram_find_node("b") == NULL);
-      ok("FORGET removes incident edges", engram_get()->edge_count == 0); }
-}
-
-/* ── Replay idempotency: apply file twice == once ───────────────────────── */
-static void test_replay_idempotent(void) {
-    printf("\n== replay idempotency ==\n");
-    reset_store(); wal_close();
-    char wal[600]; path_in(wal, sizeof(wal), "engram.wal"); unlink(wal);
-    eg_wal_open(g_tmpdir);
-    eg_apply_node_put("{\"id\":\"x\"}");
-    engram_wal_node_put(EL_STR(g_tmpdir), EL_STR("x"));
-    eg_apply_node_put("{\"id\":\"y\"}");
-    engram_wal_node_put(EL_STR(g_tmpdir), EL_STR("y"));
-    eg_wal_commit(1);
-    reset_store();
-    eg_wal_replay_file(wal, NULL);
-    int64_t after1 = engram_get()->node_count;
-    eg_wal_replay_file(wal, NULL);            /* replay AGAIN */
-    int64_t after2 = engram_get()->node_count;
-    ok("replay once == 2 nodes", after1 == 2);
-    ok("replay twice == replay once (idempotent)", after2 == after1);
-    wal_close();
-}
-
-/* ── hebb + emb serialize round-trip ────────────────────────────────────── */
-static void test_hebb_emb_roundtrip(void) {
-    printf("\n== hebb + emb serialize round-trip ==\n");
-    reset_store();
-    /* hebb via edge emit→parse */
-    eg_apply_node_put("{\"id\":\"p\"}"); eg_apply_node_put("{\"id\":\"q\"}");
-    eg_apply_edge_put("{\"id\":\"eh\",\"from_id\":\"p\",\"to_id\":\"q\",\"hebb\":0.123456}");
-    EngramStore* g = engram_get();
-    int64_t ei = eg_find_edge_index(g, "eh");
-    JsonBuf b; jb_init(&b); engram_emit_edge_json(&b, &g->edges[ei]);
-    char* ej = strndup(b.buf, b.len); free(b.buf);
-    ok("emit edge carries hebb", strstr(ej, "\"hebb\"") != NULL);
-    eg_apply_edge_put(ej);   /* re-parse */
-    ei = eg_find_edge_index(g, "eh");
-    ok("hebb survives emit→parse (%.6g)", g->edges[ei].hebb > 0.1234 && g->edges[ei].hebb < 0.1235);
-    free(ej);
-
-    /* emb via node emit(include_emb=1)→parse, bit-exact at %.4g. The runtime
-     * requires dim>=8 (garbage guard), so use 8 dyadic-rational values that
-     * survive %.4g round-trip exactly. */
-    eg_apply_node_put("{\"id\":\"ez\",\"emb\":\"0.5,-0.25,0.125,1,-0.0625,0.75,-1,0.375\"}");
-    EngramNode* n = engram_find_node("ez");
-    ok("emb parsed dim==8", n && n->emb_dim == 8);
-    float e0 = n->emb[0], e1 = n->emb[1], e2 = n->emb[2], e3 = n->emb[3];
-    JsonBuf nb; jb_init(&nb); engram_emit_node_json(&nb, n, 1);
-    char* nj = strndup(nb.buf, nb.len); free(nb.buf);
-    ok("emit node carries emb", strstr(nj, "\"emb\"") != NULL);
-    eg_apply_node_put(nj); free(nj);
-    n = engram_find_node("ez");
-    ok("emb[0]==0.5 exact",   n->emb[0] == e0 && e0 == 0.5f);
-    ok("emb[1]==-0.25 exact", n->emb[1] == e1 && e1 == -0.25f);
-    ok("emb[2]==0.125 exact", n->emb[2] == e2 && e2 == 0.125f);
-    ok("emb[3]==1 exact",     n->emb[3] == e3 && e3 == 1.0f);
-}
-
-/* ── data-dir resolution (§18.2) ────────────────────────────────────────── */
-static void test_data_dir(void) {
-    printf("\n== data-dir resolution ==\n");
-    setenv("ENGRAM_DATA_DIR", "/data/explicit", 1);
-    ok("explicit ENGRAM_DATA_DIR honored",
-       strcmp(EL_CSTR(engram_resolve_data_dir()), "/data/explicit") == 0);
-    unsetenv("ENGRAM_DATA_DIR");
-    char fakehome[600]; snprintf(fakehome, sizeof(fakehome), "%s/home", g_tmpdir);
-    mkdir(fakehome, 0700);
-    setenv("HOME", fakehome, 1);
-    char expect[700]; snprintf(expect, sizeof(expect), "%s/.neuron/engram", fakehome);
-    const char* got = EL_CSTR(engram_resolve_data_dir());
-    ok("unset → $HOME/.neuron/engram", strcmp(got, expect) == 0);
-    ok("resolved dir is NOT /tmp/engram", strcmp(got, "/tmp/engram") != 0);
-    ok("resolved dir was created", file_size(expect) >= 0 || 1); /* mkdir ran */
-    /* HOME-unresolvable fail-loud path is verified out-of-process (calls exit). */
-    printf("  [NOTE] HOME-unresolvable → exit(1) verified via subprocess (see run script)\n");
-}
-
-/* ── protected-set derivation (§18.1/18.3) ──────────────────────────────── */
-static void build_self_graph(int n_identity, int n_values) {
-    reset_store();
-    eg_apply_node_put("{\"id\":\"" EG_SELF_ROOT "\",\"content\":\"self\"}");
-    eg_apply_node_put("{\"id\":\"" EG_VALUES_HUB "\",\"content\":\"values-hub\"}");
-    char buf[256];
-    for (int i = 0; i < n_identity; i++) {
-        snprintf(buf, sizeof(buf), "{\"id\":\"id-%d\"}", i); eg_apply_node_put(buf);
-        snprintf(buf, sizeof(buf), "{\"id\":\"eid-%d\",\"from_id\":\"" EG_SELF_ROOT "\",\"to_id\":\"id-%d\"}", i, i);
-        eg_apply_edge_put(buf);
-    }
-    for (int i = 0; i < n_values; i++) {
-        snprintf(buf, sizeof(buf), "{\"id\":\"val-%d\"}", i); eg_apply_node_put(buf);
-        snprintf(buf, sizeof(buf), "{\"id\":\"eval-%d\",\"from_id\":\"" EG_VALUES_HUB "\",\"to_id\":\"val-%d\"}", i, i);
-        eg_apply_edge_put(buf);
-    }
-    /* an ordinary, unconnected node */
-    eg_apply_node_put("{\"id\":\"ordinary-1\"}");
-}
-static int count_occurrences(const char* hay, const char* needle) {
-    int c = 0; const char* p = hay;
-    while ((p = strstr(p, needle))) { c++; p += strlen(needle); }
-    return c;
-}
-static void test_protected(void) {
-    printf("\n== protected-set derivation ==\n");
-    build_self_graph(7, 13);
-    const char* pj = EL_CSTR(engram_protected_json());
-    ok("self root protected",  eg_is_protected(EG_SELF_ROOT));
-    ok("values hub protected", eg_is_protected(EG_VALUES_HUB));
-    ok("a value node protected",    eg_is_protected("val-5"));
-    ok("an identity node protected", eg_is_protected("id-3"));
-    ok("ordinary node NOT protected", !eg_is_protected("ordinary-1"));
-    ok("missing node NOT protected",  !eg_is_protected("nope-xyz"));
-    ok("derived set has 13 values",  count_occurrences(pj, "\"val-") == 13);
-    ok("derived set has 7 identity", count_occurrences(pj, "\"id-")  == 7);
-    ok("ordinary not in derived set", strstr(pj, "ordinary-1") == NULL);
-}
-
-/* ── Replay parity: WAL round-trip == direct apply ──────────────────────── */
-static void rand_node_json(char* out, size_t cap, int id) {
-    snprintf(out, cap, "{\"id\":\"pn-%d\",\"content\":\"c%d\",\"salience\":%.3f,\"importance\":%.3f}",
-             id, id, (rand() % 1000) / 1000.0, (rand() % 1000) / 1000.0);
-}
-static void test_replay_parity(void) {
-    printf("\n== replay parity (WAL round-trip vs direct apply) ==\n");
-    srand(1234);
-    /* Build a random op stream. */
-    #define NOPS 200
-    char ops[NOPS][256]; uint8_t opcode[NOPS]; int nops = 0;
-    int nodes_created = 0;
-    for (int i = 0; i < NOPS; i++) {
-        int r = rand() % 10;
-        if (r < 6 || nodes_created < 3) {
-            rand_node_json(ops[nops], sizeof(ops[0]), nodes_created);
-            opcode[nops] = EG_OP_NODE_PUT; nodes_created++; nops++;
-        } else if (r < 8) { /* edge between two existing nodes */
-            int a = rand() % nodes_created, b = rand() % nodes_created;
-            snprintf(ops[nops], sizeof(ops[0]),
-                "{\"id\":\"pe-%d\",\"from_id\":\"pn-%d\",\"to_id\":\"pn-%d\",\"weight\":0.5}", i, a, b);
-            opcode[nops] = EG_OP_EDGE_PUT; nops++;
-        } else { /* upsert (overwrite) an existing node */
-            int a = rand() % nodes_created;
-            snprintf(ops[nops], sizeof(ops[0]), "{\"id\":\"pn-%d\",\"content\":\"upd%d\"}", a, i);
-            opcode[nops] = EG_OP_NODE_PUT; nops++;
-        }
-    }
-    /* Oracle: apply directly. */
-    reset_store();
-    for (int i = 0; i < nops; i++) eg_wal_apply(opcode[i], ops[i], strlen(ops[i]));
-    char* oracle = store_fingerprint();
-
-    /* WAL path: write each op to a fresh WAL, then replay into a reset store. */
-    wal_close();
-    char wal[600]; path_in(wal, sizeof(wal), "parity.wal"); unlink(wal);
-    /* point eg_wal at the parity file by opening a dir handle then overriding */
-    reset_store();
-    { FILE* f = fopen(wal, "wb"); fclose(f); }
-    eg_wal.fp = fopen(wal, "ab"); snprintf(eg_wal.path, sizeof(eg_wal.path), "%s", wal);
-    eg_wal.lsn = 0; eg_wal.bytes = 0;
-    for (int i = 0; i < nops; i++) eg_wal_write(opcode[i], 0, ops[i], strlen(ops[i]));
-    eg_wal_commit(1); wal_close();
-    reset_store();
-    eg_wal_replay_file(wal, NULL);
-    char* replayed = store_fingerprint();
-
-    ok("WAL replay fingerprint == direct-apply oracle", strcmp(oracle, replayed) == 0);
-    if (strcmp(oracle, replayed) != 0) {
-        printf("    oracle  len=%zu\n    replay  len=%zu\n", strlen(oracle), strlen(replayed));
-    }
-    free(oracle); free(replayed);
-}
-
-/* ── Torn-tail fuzz: truncate at EVERY offset; never crash, recover to last
- *    intact record ─────────────────────────────────────────────────────── */
-static int count_full_records(const unsigned char* buf, long len) {
-    long off = 0; int n = 0;
-    while (off + EG_WAL_HDR_LEN <= len) {
-        uint32_t magic, len32; memcpy(&magic, buf + off, 4);
-        if (magic != EG_WAL_MAGIC) break;
-        memcpy(&len32, buf + off + 4, 4);
-        if (off + EG_WAL_HDR_LEN + len32 > len) break;
-        n++; off += EG_WAL_HDR_LEN + len32;
-    }
-    return n;
-}
-static void test_torn_tail(void) {
-    printf("\n== torn-tail fuzz (truncate at every byte offset) ==\n");
-    wal_close();
-    char wal[600]; path_in(wal, sizeof(wal), "torn.wal"); unlink(wal);
-    eg_wal.fp = fopen(wal, "ab"); snprintf(eg_wal.path, sizeof(eg_wal.path), "%s", wal);
-    eg_wal.lsn = 0; eg_wal.bytes = 0;
-    for (int i = 0; i < 12; i++) {
-        char pl[128]; snprintf(pl, sizeof(pl), "{\"id\":\"t-%d\",\"content\":\"payload-%d\"}", i, i);
-        eg_wal_write(EG_OP_NODE_PUT, 0, pl, strlen(pl));
-    }
-    eg_wal_commit(1); wal_close();
-    long sz = file_size(wal);
-    FILE* f = fopen(wal, "rb"); unsigned char* full = malloc(sz); fread(full, 1, sz, f); fclose(f);
-
-    int all_ok = 1, mismatches = 0;
-    char trunc[600]; path_in(trunc, sizeof(trunc), "torn_trunc.wal");
-    for (long L = 0; L <= sz; L++) {
-        write_file(trunc, full, L);
-        reset_store();
-        uint64_t last = 12345;
-        int64_t applied = eg_wal_replay_file(trunc, &last);   /* must not crash */
-        int expect = count_full_records(full, L);
-        if (applied != expect) { all_ok = 0; if (mismatches++ < 3)
-            printf("    L=%ld applied=%lld expect=%d\n", L, (long long)applied, expect); }
-    }
-    ok("no crash across all truncation offsets", 1); /* reached here => survived */
-    ok("recovered record count == #intact records at every offset", all_ok);
-    free(full);
-}
-
-/* ── Compaction crash-window convergence (§7) ───────────────────────────── */
-static void test_compaction_crash(void) {
-    printf("\n== compaction crash-window convergence ==\n");
-    /* Build state: base snapshot has n1; WAL adds n2,n3. */
-    char dir[600]; snprintf(dir, sizeof(dir), "%s/comp", g_tmpdir); mkdir(dir, 0700);
-    char base[700], wal[700], waltmp[700];
-    snprintf(base, sizeof(base), "%s/snapshot.json", dir);
-    snprintf(wal, sizeof(wal), "%s/engram.wal", dir);
-    snprintf(waltmp, sizeof(waltmp), "%s/engram.wal.tmp", dir);
-
-    /* Reference full state = n1,n2,n3. */
-    reset_store();
-    eg_apply_node_put("{\"id\":\"n1\"}");
-    eg_apply_node_put("{\"id\":\"n2\"}");
-    eg_apply_node_put("{\"id\":\"n3\"}");
-    char* full = store_fingerprint();
-
-    /* Prepare OLD base (n1 only) + OLD wal (n2,n3). */
-    reset_store(); eg_apply_node_put("{\"id\":\"n1\"}");
-    engram_save((el_val_t)(uintptr_t)base);
-    wal_close(); unlink(wal);
-    eg_wal.fp = fopen(wal, "ab"); snprintf(eg_wal.path, sizeof(eg_wal.path), "%s", wal); eg_wal.lsn = 0; eg_wal.bytes = 0;
-    reset_store(); eg_apply_node_put("{\"id\":\"n1\"}"); eg_apply_node_put("{\"id\":\"n2\"}"); eg_apply_node_put("{\"id\":\"n3\"}");
-    engram_wal_node_put(EL_STR(dir), EL_STR("n2"));
-    engram_wal_node_put(EL_STR(dir), EL_STR("n3"));
-    eg_wal_commit(1); wal_close();
-
-    /* Boot helper: load base then replay wal (mirrors server boot order). */
-    #define BOOT_FP(fp) do { \
-        engram_load((el_val_t)(uintptr_t)base); \
-        eg_wal_replay_file(wal, NULL); \
-        fp = store_fingerprint(); } while (0)
-
-    /* Crash BEFORE compaction (steady state). */
-    char* c0; BOOT_FP(c0);
-    ok("pre-compaction boot converges to full", strcmp(c0, full) == 0); free(c0);
-
-    /* Crash AFTER step 1 (new base written) but BEFORE wal swap:
-     * base now = full (n1,n2,n3), wal still = old (n2,n3). Idempotent replay. */
-    engram_load((el_val_t)(uintptr_t)base); /* reload old base into store */
-    eg_apply_node_put("{\"id\":\"n2\"}"); eg_apply_node_put("{\"id\":\"n3\"}");
-    engram_save((el_val_t)(uintptr_t)base);  /* == compaction step 1: new base */
-    char* c1; BOOT_FP(c1);
-    ok("crash after new-base, before wal-swap → converges", strcmp(c1, full) == 0); free(c1);
-
-    /* Crash AFTER wal.tmp written but BEFORE rename: stray tmp ignored,
-     * old wal still authoritative over (new) base. */
-    { FILE* tf = fopen(waltmp, "wb"); const char* junk = "PARTIAL"; fwrite(junk,1,7,tf); fclose(tf); }
-    char* c2; BOOT_FP(c2);
-    ok("crash after wal.tmp, before rename → converges", strcmp(c2, full) == 0);
-    unlink(waltmp); free(c2);
-
-    /* Crash AFTER rename (compaction complete): base=full, wal=only COMPACT_MARK. */
-    reset_store();
-    engram_load((el_val_t)(uintptr_t)base);
-    eg_apply_node_put("{\"id\":\"n2\"}"); eg_apply_node_put("{\"id\":\"n3\"}");
-    engram_wal_compact(EL_STR(dir));   /* full compaction */
-    wal_close();
-    char* c3;
-    engram_load((el_val_t)(uintptr_t)base);
-    eg_wal_replay_file(wal, NULL);
-    c3 = store_fingerprint();
-    ok("post-compaction boot converges to full", strcmp(c3, full) == 0);
-    long wsz = file_size(wal);
-    ok("post-compaction WAL truncated (only COMPACT_MARK)",
-       wsz > 0 && wsz < 64);   /* just the marker record */
-    free(c3); free(full);
-}
-
-int main(void) {
-    mk_tmpdir();
-    printf("engram WAL test harness — tmpdir=%s\n", g_tmpdir);
-    test_crc32();
-    test_framing();
-    test_single_ops();
-    test_replay_idempotent();
-    test_hebb_emb_roundtrip();
-    test_data_dir();
-    test_protected();
-    test_replay_parity();
-    test_torn_tail();
-    test_compaction_crash();
-    printf("\n=================  %d passed, %d failed  =================\n", g_pass, g_fail);
-    return g_fail ? 1 : 0;
-}

lang/AGENTS.md

@@ -27,11 +27,11 @@ This is where almost all work belongs. El programs are source files that get com
 
 **Do not add C code when El can express it.** If functionality can be built from existing El primitives (string ops, `exec`, `fs_read/write`, `http_post`, etc.), write it in El.
 
-### Layer 2: The C seed (`runtime/el_seed.c`)
+### Layer 2: The C seed (`el-compiler/runtime/el_seed.c`)
 
 This is the self-contained C OS-boundary layer. It provides the `__`-prefixed primitives that compiled El programs call: libcurl HTTP, pthreads, filesystem I/O, arena allocation, etc. It is **not generated** — it is maintained by hand.
 
-The old `el_runtime.c` has been archived to `runtime/legacy/`. The runtime is now native El (`runtime/*.el`). `el_seed.c` replaces `el_runtime.c` as the sole C compilation dependency.
+The old `el_runtime.c` has been archived to `el-compiler/runtime/legacy/`. The runtime is now native El (`runtime/*.el`). `el_seed.c` replaces `el_runtime.c` as the sole C compilation dependency.
 
 **Only edit `el_seed.c` when you genuinely need OS-level access** (raw sockets, GPU calls, new libcurl features). For everything else, write El.
 
@@ -50,9 +50,9 @@ After changing any `.el` source in `el-compiler/src/`:
 ```bash
 cd /Users/will/Development/neuron-technologies/foundation/el
 ./dist/platform/elc elc-cli.el > elc-new.c
-cc -std=c11 -I runtime -lcurl -lpthread \
+cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
    -o dist/platform/elc-new \
-   elc-new.c runtime/el_seed.c
+   elc-new.c el-compiler/runtime/el_seed.c
 # Verify self-hosting:
 ./dist/platform/elc-new elc-cli.el > elc-verify.c
 diff elc-new.c elc-verify.c   # should be identical
@@ -104,8 +104,8 @@ Use `exec()` (blocking) or `exec_bg()` (fire-and-forget) with shell scripts to r
 | `el-compiler/src/codegen.el` | Code generator — builtin arity table lives here |
 | `el-compiler/src/lexer.el` | Lexer |
 | `el-compiler/src/parser.el` | Parser |
-| `runtime/el_seed.c` | Self-contained C OS-boundary layer (replaces el_runtime.c) |
-| `runtime/el_seed.h` | Seed header (C function declarations) |
+| `el-compiler/runtime/el_seed.c` | Self-contained C OS-boundary layer (replaces el_runtime.c) |
+| `el-compiler/runtime/el_seed.h` | Seed header (C function declarations) |
 | `spec/language.md` | Language specification |
 | `BOOTSTRAP.md` | How to recover the compiler from scratch |
 | `elc-cli.el` | Compiler entry point |

lang/BOOTSTRAP.md

@@ -50,9 +50,9 @@ To rebuild the current binary from source using the current binary:
 ```bash
 cd /path/to/el
 ./dist/platform/elc elc-cli.el elc-new.c
-cc -std=c11 -I runtime -lcurl -lpthread \
+cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
    -o dist/platform/elc-new \
-   elc-new.c runtime/el_runtime.c
+   elc-new.c el-compiler/runtime/el_runtime.c
 ```
 
 Verify self-hosting by using `elc-new` to recompile itself and diffing the outputs.
@@ -288,14 +288,14 @@ The codegen tracks declared names per C scope. When `count` is already in `decla
 
 ## 3. The Runtime API
 
-All runtime functions are declared in `runtime/el_runtime.h`. Every compiled El program links against `runtime/el_runtime.c`.
+All runtime functions are declared in `el-compiler/runtime/el_runtime.h`. Every compiled El program links against `el-compiler/runtime/el_runtime.c`.
 
 All values are `el_val_t` (`int64_t`). Strings are pointers cast through `int64_t` using `EL_STR(s)` / `EL_CSTR(v)` macros.
 
 Canonical compile command:
 ```bash
-cc -std=c11 -I runtime -lcurl -lpthread \
-   -o <out> <prog>.c runtime/el_runtime.c
+cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
+   -o <out> <prog>.c el-compiler/runtime/el_runtime.c
 ```
 
 ### I/O
@@ -794,8 +794,8 @@ Using your minimal implementation, compile `elc-cli.el` (which imports the entir
 python3 minimal_elc.py elc-cli.el > elc-new.c
 
 # Build with the runtime
-cc -std=c11 -I runtime -lcurl -lpthread \
-   -o elc-new elc-new.c runtime/el_runtime.c
+cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
+   -o elc-new elc-new.c el-compiler/runtime/el_runtime.c
 ```
 
 ### Step 5: Verify Self-Hosting
@@ -803,8 +803,8 @@ cc -std=c11 -I runtime -lcurl -lpthread \
 ```bash
 # Compile elc-cli.el with the new compiler
 ./elc-new elc-cli.el elc-v2.c
-cc -std=c11 -I runtime -lcurl -lpthread \
-   -o elc-v2 elc-v2.c runtime/el_runtime.c
+cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
+   -o elc-v2 elc-v2.c el-compiler/runtime/el_runtime.c
 
 # Compile again with the second-generation compiler
 ./elc-v2 elc-cli.el elc-v3.c
@@ -880,9 +880,9 @@ This is the planned path. It does not exist yet.
 | `el-compiler/src/parser.el` | Recursive descent parser. `parse(tokens)` → AST. All statement and expression forms | 1071 |
 | `el-compiler/src/codegen.el` | C code emitter. `codegen(stmts, source)` → (streams to stdout). Expression codegen, statement codegen, function codegen, type tracking, capability enforcement, temporal type dispatch | 2721 |
 | `el-compiler/src/codegen-js.el` | JavaScript backend. `codegen_js(stmts, source)` → JS source | ~500 |
-| `runtime/el_runtime.h` | Full runtime API declaration | 755 |
-| `runtime/el_runtime.c` | Full runtime implementation | large |
-| `runtime/el_runtime.js` | JS runtime | — |
+| `el-compiler/runtime/el_runtime.h` | Full runtime API declaration | 755 |
+| `el-compiler/runtime/el_runtime.c` | Full runtime implementation | large |
+| `el-compiler/runtime/el_runtime.js` | JS runtime | — |
 | `elb.el` | Build coordinator. Reads `manifest.el`, walks import graph, compiles modules, links binary. The `.NET`-style incremental build model | 367 |
 | `elc-combined.el` | Pre-merged single-file bootstrap edition (for early bootstrap iterations) | large |
 | `spec/language.md` | Language specification v1.2.0 | — |

lang/el-compiler/runtime/detect-platforms

@@ -132,7 +132,7 @@ if [[ $LVGL_OK -eq 1 ]]; then
 else
     _miss "LVGL/MCU" "-DEL_TARGET_LVGL  (lvgl.h not found)"
     echo "                             Install: git clone https://github.com/lvgl/lvgl"
-    echo "                                      (place lvgl/ next to runtime/)"
+    echo "                                      (place lvgl/ next to el-compiler/runtime/)"
     MISSING=$((MISSING + 1))
 fi
 

lang/el-compiler/runtime/el_runtime.h

@@ -0,0 +1,897 @@
+/*
+ * el_runtime.h — El language C runtime header
+ *
+ * Declares all built-in functions available to compiled El programs.
+ * Include this in every generated .c file.
+ *
+ * Value model:
+ *   All El values are represented as el_val_t (= int64_t).
+ *   On 64-bit systems a pointer fits in int64_t.
+ *   String values are cast: (el_val_t)(uintptr_t)"hello"
+ *   Integer values are stored directly.
+ *   This lets arithmetic work naturally while still passing strings around.
+ *
+ * Type conventions (El -> C):
+ *   String  -> el_val_t  (holds const char* via uintptr_t cast)
+ *   Int     -> el_val_t
+ *   Bool    -> el_val_t  (0 = false, nonzero = true)
+ *   Any     -> el_val_t
+ *   Void    -> void
+ *
+ * Macros for convenience:
+ *   EL_STR(s)    cast string literal to el_val_t
+ *   EL_CSTR(v)   cast el_val_t back to const char*
+ *   EL_INT(v)    identity — el_val_t is already int64_t
+ *   EL_NULL      null / zero value
+ *   EL_FALSE     boolean false (0)
+ *   EL_TRUE      boolean true (1)
+ *
+ * Link requirements:
+ *   -lcurl     — required for the HTTP client (http_get, http_post, llm_*).
+ *   -lpthread  — required for the HTTP server (one detached thread per
+ *                connection, capped at 64 concurrent).
+ *   -loqs      — optional; required only when liboqs is installed and the
+ *                pq_* / sha3_256_hex entry points are needed. Detected at
+ *                compile time via __has_include(<oqs/oqs.h>).
+ *   -lcrypto   — optional; pulled in alongside -loqs. Used for X25519 in
+ *                pq_hybrid_* and HKDF-SHA256 derivation.
+ *
+ * Canonical compile command:
+ *   cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
+ *      -o <out> <prog>.c el-compiler/runtime/el_runtime.c
+ *
+ * With liboqs (post-quantum stack):
+ *   cc -std=c11 -I el-compiler/runtime -lcurl -lpthread -loqs -lcrypto \
+ *      -o <out> <prog>.c el-compiler/runtime/el_runtime.c
+ */
+
+#pragma once
+
+#include <stdint.h>
+#include <stdlib.h>
+
+typedef int64_t el_val_t;
+
+/* HTTP request-handler function-pointer types. Public because soul modules (routes/chat/etc.)
+ * register handlers across translation units; previously defined only inside el_runtime.c, which
+ * made cross-module references (and the Windows build) fail. Home in the shared header. */
+typedef el_val_t (*http_handler_fn)(el_val_t method, el_val_t path, el_val_t body);
+typedef el_val_t (*http_handler4_fn)(el_val_t method, el_val_t path, el_val_t body, el_val_t headers);
+
+#define EL_STR(s)  ((el_val_t)(uintptr_t)(s))
+#define EL_CSTR(v) ((const char*)(uintptr_t)(v))
+#define EL_INT(v)  (v)
+#define EL_NULL    ((el_val_t)0)
+#define EL_FALSE   ((el_val_t)0)
+#define EL_TRUE    ((el_val_t)1)
+
+/* Float values share the el_val_t (int64) slot via a bit-cast.
+ * The codegen emits Float literals as `el_from_float(<dbl>)` so the
+ * underlying bits represent the IEEE 754 double. Float-aware builtins
+ * (math, format, json) round-trip via these helpers. */
+static inline double el_to_float(el_val_t v) {
+    union { int64_t i; double f; } u;
+    u.i = (int64_t)v;
+    return u.f;
+}
+
+static inline el_val_t el_from_float(double f) {
+    union { double f; int64_t i; } u;
+    u.f = f;
+    return (el_val_t)u.i;
+}
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* ── I/O ──────────────────────────────────────────────────────────────────── */
+
+el_val_t  println(el_val_t s);
+el_val_t  print(el_val_t s);
+el_val_t  readline(void);
+
+/* ── String builtins ─────────────────────────────────────────────────────── */
+
+el_val_t  el_str_concat(el_val_t a, el_val_t b);
+el_val_t  str_eq(el_val_t a, el_val_t b);
+el_val_t  str_starts_with(el_val_t s, el_val_t prefix);
+el_val_t  str_ends_with(el_val_t s, el_val_t suffix);
+el_val_t  str_len(el_val_t s);
+el_val_t  str_concat(el_val_t a, el_val_t b);
+el_val_t  int_to_str(el_val_t n);
+el_val_t  str_to_int(el_val_t s);
+el_val_t  native_str_to_int(el_val_t s);
+el_val_t  str_slice(el_val_t s, el_val_t start, el_val_t end);
+el_val_t  str_contains(el_val_t s, el_val_t sub);
+el_val_t  str_replace(el_val_t s, el_val_t from, el_val_t to);
+el_val_t  str_to_upper(el_val_t s);
+el_val_t  str_to_lower(el_val_t s);
+el_val_t  str_trim(el_val_t s);
+
+/* ── Math ────────────────────────────────────────────────────────────────── */
+
+el_val_t  el_abs(el_val_t n);
+el_val_t  el_max(el_val_t a, el_val_t b);
+el_val_t  el_min(el_val_t a, el_val_t b);
+
+/* ── Refcount (ARC) ──────────────────────────────────────────────────────────
+ * Lists and Maps carry a refcount. Strings and ints do not — el_retain and
+ * el_release are safe no-ops on non-refcounted values (they sniff a magic
+ * header at offset 0 and only act if the magic matches).
+ *
+ * Codegen emits these at let-binding shadowing, function entry (params), and
+ * function exit (locals other than the returned value). The refcount lets
+ * el_list_append and el_map_set mutate in place when uniquely owned (cheap)
+ * and copy-on-write when shared (preserves persistent semantics across
+ * accumulator patterns in the compiler itself).                              */
+
+void      el_retain(el_val_t v);
+void      el_release(el_val_t v);
+
+/* ── Scoped arena (CLI use) ───────────────────────────────────────────────── */
+el_val_t  el_arena_push(void);
+el_val_t  el_arena_pop(el_val_t mark);
+
+/* ── List ────────────────────────────────────────────────────────────────── */
+
+el_val_t  el_list_new(el_val_t count, ...);
+el_val_t  el_list_len(el_val_t list);
+el_val_t  el_list_get(el_val_t list, el_val_t index);
+el_val_t  el_list_append(el_val_t list, el_val_t elem);
+el_val_t  el_list_empty(void);
+el_val_t  el_list_clone(el_val_t list);
+
+/* ── Map ─────────────────────────────────────────────────────────────────── */
+
+el_val_t  el_map_new(el_val_t pair_count, ...);
+el_val_t  el_get_field(el_val_t map, el_val_t key);
+el_val_t  el_map_get(el_val_t map, el_val_t key);
+el_val_t  el_map_set(el_val_t map, el_val_t key, el_val_t value);
+
+/* ── HTTP ─────────────────────────────────────────────────────────────────── */
+
+el_val_t  http_get(el_val_t url);
+el_val_t  http_post(el_val_t url, el_val_t body);
+el_val_t  http_post_json(el_val_t url, el_val_t json_body);
+el_val_t  http_get_with_headers(el_val_t url, el_val_t headers_map);
+el_val_t  http_post_with_headers(el_val_t url, el_val_t body, el_val_t headers_map);
+el_val_t  http_post_json_with_headers(el_val_t url, el_val_t headers_map, el_val_t json_body);
+el_val_t  http_post_form_auth(el_val_t url, el_val_t form_body, el_val_t auth_header);
+el_val_t  http_delete(el_val_t url);
+el_val_t  http_serve(el_val_t port, el_val_t handler);
+el_val_t  http_set_handler(el_val_t name);
+
+/* HTTP server v2 ─────────────────────────────────────────────────────────────
+ * Same dispatch model as http_serve, but the handler signature is widened:
+ *
+ *     el_val_t handler(method, path, headers_map, body)
+ *
+ * `headers_map` is an ElMap from lowercased header name → header value (both
+ * Strings). Repeated headers are joined with ", " per RFC 7230.
+ *
+ * Response value: the handler may return either
+ *   (a) a plain body string — same auto-content-type / 200-OK behaviour as
+ *       http_serve (3-arg) — or
+ *   (b) a response envelope built with `http_response(status, headers_json,
+ *       body)`. The runtime detects the envelope discriminator
+ *       `"el_http_response":1` at the start of the returned string and
+ *       unpacks status / headers / body before sending.
+ *
+ * The 3-arg http_serve(port, handler) remains supported unchanged for
+ * existing handlers (e.g. products/web/server.el): it dispatches with
+ * (method, path, body), hardcodes 200 OK, and auto-detects content type. */
+el_val_t  http_serve_v2(el_val_t port, el_val_t handler);
+void      http_serve_async(el_val_t port, el_val_t handler);
+el_val_t  http_set_handler_v2(el_val_t name);
+
+/* Build an HTTP response envelope. `headers_json` should be a JSON object
+ * literal like `{"WWW-Authenticate":"Basic"}` (or "" / "{}" for none). The
+ * returned string carries the discriminator `{"el_http_response":1,...}`
+ * which the runtime's send-path detects and unpacks. Detection happens
+ * uniformly inside http_send_response, so a 3-arg handler may also return
+ * an envelope. The 3-arg variant remains documented as a fixed 200-OK
+ * auto-content-type contract for legacy handlers that return plain bodies. */
+el_val_t  http_response(el_val_t status, el_val_t headers_json, el_val_t body);
+
+/* SSE connection fd — set by http_worker_v2 before calling the El handler,
+ * cleared afterwards. Defined in el_seed.c; called from el_runtime.c.
+ * The getter is exposed as __http_conn_fd() to El programs. */
+void      el_seed_set_http_conn_fd(int fd);
+
+/* HTTP timeout — every libcurl request honors EL_HTTP_TIMEOUT_MS (default
+ * 60000ms). Read lazily on first use, so setting the env var any time before
+ * the first http_* call is sufficient.                                    */
+
+/* Streaming variants — write the response body straight to a file via
+ * libcurl's CURLOPT_WRITEFUNCTION = fwrite. These bypass the el_val_t string
+ * wrapper entirely, so binary payloads (audio/mpeg, image/png, etc.) survive
+ * embedded NUL bytes that would truncate a strlen()-based code path.
+ *
+ * Both honor EL_HTTP_TIMEOUT_MS, follow redirects, and accept the same
+ * `headers_map` shape as http_post_with_headers (ElMap of String→String).
+ *
+ * Return value: 1 on success (file fully written), 0 on any failure
+ * (network, file open, partial write). On failure the output file is removed
+ * so callers cannot mistake a partially-written file for a valid one. */
+el_val_t  http_post_to_file(el_val_t url, el_val_t body, el_val_t headers_map, el_val_t output_path);
+el_val_t  http_get_to_file(el_val_t url, el_val_t headers_map, el_val_t output_path);
+
+/* ── URL encoding ────────────────────────────────────────────────────────── */
+
+el_val_t  url_encode(el_val_t s);   /* RFC 3986 unreserved set */
+el_val_t  url_decode(el_val_t s);   /* '+' → space, %XX → byte  */
+
+/* ── HTML allowlist sanitizer ────────────────────────────────────────────────
+ * el_html_sanitize(input_html, allowlist_json) — strict allowlist HTML
+ * cleaner. State-machine parser; tag/attribute names compared case-
+ * insensitively against the allowlist; `<a href>` / `<… src>` URL schemes
+ * validated (http, https, mailto, fragment-only, or relative); whole-
+ * subtree drop for script / style / iframe / object / embed / form; HTML-
+ * escapes free text outside dropped subtrees.
+ *
+ * The allowlist is JSON of the form
+ *     {"p":[],"a":["href","title"],"strong":[],...}
+ * where each value is the array of attribute names allowed for that tag. */
+el_val_t  el_html_sanitize(el_val_t input_html, el_val_t allowlist_json);
+el_val_t  html_raw(el_val_t s);
+el_val_t  html_escape(el_val_t s);
+
+/* ── Filesystem ──────────────────────────────────────────────────────────── */
+
+el_val_t  fs_read(el_val_t path);
+el_val_t  fs_write(el_val_t path, el_val_t content);
+el_val_t  fs_list(el_val_t path);
+el_val_t  fs_list_json(el_val_t path);
+el_val_t  fs_exists(el_val_t path);
+el_val_t  fs_mkdir(el_val_t path);   /* mkdir -p, mode 0755                */
+
+/* Length-explicit binary write. `length` is an Int (el_val_t holding the
+ * byte count). The caller knows the length from context — typically because
+ * `bytes` came from base64_decode (which produces a magic-tagged binary
+ * buffer with embedded NULs possible) and the caller already tracks the
+ * decoded length, OR because the bytes came from a fixed-size source
+ * (sha256_bytes = 32, hmac_sha256_bytes = 32). Bypasses strlen entirely.
+ *
+ * Returns 1 on success, 0 on failure (invalid path, can't open, partial
+ * write, negative length). On partial-write failure, the file is removed
+ * so callers cannot read back a truncated artefact. */
+el_val_t  fs_write_bytes(el_val_t path, el_val_t bytes, el_val_t length);
+
+/* ── JSON ────────────────────────────────────────────────────────────────── */
+
+el_val_t  json_get(el_val_t json, el_val_t key);
+el_val_t  json_parse(el_val_t s);
+el_val_t  json_stringify(el_val_t v);
+el_val_t  json_get_string(el_val_t json_str, el_val_t key);
+el_val_t  json_get_int(el_val_t json_str, el_val_t key);
+el_val_t  json_get_float(el_val_t json_str, el_val_t key);
+el_val_t  json_get_bool(el_val_t json_str, el_val_t key);
+el_val_t  json_get_raw(el_val_t json_str, el_val_t key);
+el_val_t  json_set(el_val_t json_str, el_val_t key, el_val_t value);
+el_val_t  json_array_len(el_val_t json_str);
+el_val_t  json_array_get(el_val_t json_str, el_val_t index);
+el_val_t  json_array_get_string(el_val_t json_str, el_val_t index);
+el_val_t  json_escape_string(el_val_t sv);
+el_val_t  json_build_object(el_val_t kvs);
+el_val_t  json_build_array(el_val_t items);
+
+/* ── Time ────────────────────────────────────────────────────────────────── */
+
+el_val_t  time_now(void);
+el_val_t  time_now_utc(void);
+el_val_t  sleep_secs(el_val_t secs);
+el_val_t  sleep_ms(el_val_t ms);
+el_val_t  time_format(el_val_t ts, el_val_t fmt);
+el_val_t  time_to_parts(el_val_t ts);
+el_val_t  time_from_parts(el_val_t secs, el_val_t ns, el_val_t tz);
+el_val_t  time_add(el_val_t ts, el_val_t n, el_val_t unit);
+el_val_t  time_diff(el_val_t ts1, el_val_t ts2, el_val_t unit);
+el_val_t  now_ns(void);
+
+/* ── Instant + Duration: first-class temporal types ──────────────────────────
+ * Both types share the el_val_t (int64) slot. Instants are nanoseconds
+ * since the Unix epoch; Durations are signed nanoseconds. Type discipline
+ * is enforced at codegen-time: BinOps on names registered as Instant or
+ * Duration route through the typed wrappers below; mismatches like
+ * Instant+Instant become #error at the C compiler.
+ *
+ * Postfix literals — `30.seconds`, `1.hour`, `500.millis`, `30.nanos` — are
+ * recognised by the parser as DurationLit AST nodes and lowered to literal
+ * int64 nanoseconds at codegen time. The runtime never sees the units. */
+
+el_val_t  el_now_instant(void);
+el_val_t  now(void);
+el_val_t  unix_seconds(el_val_t n);
+el_val_t  unix_millis(el_val_t n);
+el_val_t  instant_from_iso8601(el_val_t s);
+
+el_val_t  el_duration_from_nanos(el_val_t ns);
+el_val_t  duration_seconds(el_val_t n);
+el_val_t  duration_millis(el_val_t n);
+el_val_t  duration_nanos(el_val_t n);
+
+el_val_t  el_instant_add_dur(el_val_t inst, el_val_t dur);
+el_val_t  el_instant_sub_dur(el_val_t inst, el_val_t dur);
+el_val_t  el_instant_diff(el_val_t a, el_val_t b);
+el_val_t  el_duration_add(el_val_t a, el_val_t b);
+el_val_t  el_duration_sub(el_val_t a, el_val_t b);
+el_val_t  el_duration_scale(el_val_t dur, el_val_t scalar);
+el_val_t  el_duration_div(el_val_t dur, el_val_t scalar);
+
+el_val_t  el_instant_lt(el_val_t a, el_val_t b);
+el_val_t  el_instant_le(el_val_t a, el_val_t b);
+el_val_t  el_instant_gt(el_val_t a, el_val_t b);
+el_val_t  el_instant_ge(el_val_t a, el_val_t b);
+el_val_t  el_instant_eq(el_val_t a, el_val_t b);
+el_val_t  el_instant_ne(el_val_t a, el_val_t b);
+el_val_t  el_duration_lt(el_val_t a, el_val_t b);
+el_val_t  el_duration_le(el_val_t a, el_val_t b);
+el_val_t  el_duration_gt(el_val_t a, el_val_t b);
+el_val_t  el_duration_ge(el_val_t a, el_val_t b);
+el_val_t  el_duration_eq(el_val_t a, el_val_t b);
+el_val_t  el_duration_ne(el_val_t a, el_val_t b);
+
+el_val_t  instant_to_unix_seconds(el_val_t i);
+el_val_t  instant_to_unix_millis(el_val_t i);
+el_val_t  instant_to_iso8601(el_val_t i);
+el_val_t  duration_to_seconds(el_val_t d);
+el_val_t  duration_to_millis(el_val_t d);
+el_val_t  duration_to_nanos(el_val_t d);
+
+el_val_t  el_sleep_duration(el_val_t dur);
+el_val_t  unix_timestamp(void);
+
+el_val_t  ttl_cache_set(el_val_t key, el_val_t value);
+el_val_t  ttl_cache_get(el_val_t key, el_val_t max_age);
+el_val_t  ttl_cache_age(el_val_t key);
+
+/* ── Calendar + CalendarTime + Rhythm + LocalDate/Time/DateTime ─────────────
+ * Phase 1.5 of the time system. Calendar is pluggable: EarthCalendar (IANA
+ * zones, Gregorian, DST) is the user-facing default; MarsCalendar,
+ * CycleCalendar(period), NoCycleCalendar, RelativeCalendar handle non-Earth
+ * domains.
+ *
+ * A Calendar interprets an Instant under a particular cycle convention and
+ * produces a CalendarTime. CalendarTime carries the underlying Instant and
+ * a back-pointer to its Calendar; arithmetic and formatting consult the
+ * Calendar to convert ns since epoch into year/month/day/hour/minute/second
+ * (or sol/phase, or cycle/phase, depending on kind).
+ *
+ * Storage convention: Calendar / CalendarTime / Rhythm / LocalDate /
+ * LocalDateTime are heap-allocated structs whose pointers are cast into
+ * el_val_t. A 24-bit magic header at offset 0 lets the runtime identify
+ * the kind safely. LocalTime is small enough to live in the int64 slot
+ * directly (nanos since midnight, signed).                                  */
+
+/* Zone — opaque IANA zone or fixed offset, used by EarthCalendar.
+ * `zone_id` is either an IANA name ("America/New_York", "UTC") or a fixed
+ * offset string ("+05:30", "-08:00"). The runtime resolves it via tzset()
+ * on first use of the owning EarthCalendar.                                  */
+el_val_t  zone(el_val_t id);
+el_val_t  zone_utc(void);
+el_val_t  zone_local(void);
+el_val_t  zone_offset(el_val_t hours, el_val_t minutes);
+
+/* Calendar constructors. Each returns an el_val_t pointer to a heap-
+ * allocated, magic-tagged Calendar struct. Calendars are interned by
+ * (kind, zone_id, period_ns, epoch_ns) so identical constructors return
+ * the same pointer — equality is reference equality.                        */
+el_val_t  earth_calendar(el_val_t z);
+el_val_t  earth_calendar_default(void);
+el_val_t  mars_calendar(void);
+el_val_t  cycle_calendar(el_val_t period_dur);
+el_val_t  no_cycle_calendar(void);
+el_val_t  relative_calendar(el_val_t epoch_inst);
+
+/* CalendarTime constructors and methods. Returns a heap-allocated struct
+ * whose pointer fits in el_val_t. */
+el_val_t  now_in(el_val_t cal);
+el_val_t  in_calendar(el_val_t inst, el_val_t cal);
+el_val_t  cal_format(el_val_t ct, el_val_t pattern);
+el_val_t  cal_to_instant(el_val_t ct);
+el_val_t  cal_cycle_phase(el_val_t ct);
+el_val_t  cal_in(el_val_t ct, el_val_t cal);
+
+/* LocalDate / LocalTime / LocalDateTime — calendar-agnostic value types.
+ * LocalTime carries nanoseconds since midnight as a signed int64 directly
+ * in the el_val_t slot (no allocation). LocalDate / LocalDateTime are
+ * heap-allocated structs with magic headers. */
+el_val_t  local_date(el_val_t y, el_val_t m, el_val_t d);
+el_val_t  local_time(el_val_t h, el_val_t m, el_val_t s, el_val_t ns);
+el_val_t  local_datetime(el_val_t date, el_val_t time);
+el_val_t  zoned(el_val_t date, el_val_t time, el_val_t cal);
+
+el_val_t  local_date_year(el_val_t ld);
+el_val_t  local_date_month(el_val_t ld);
+el_val_t  local_date_day(el_val_t ld);
+el_val_t  local_time_hour(el_val_t lt);
+el_val_t  local_time_minute(el_val_t lt);
+el_val_t  local_time_second(el_val_t lt);
+el_val_t  local_time_nanos(el_val_t lt);
+
+el_val_t  el_local_date_add_dur(el_val_t ld, el_val_t dur);
+el_val_t  el_local_time_add_dur(el_val_t lt, el_val_t dur);
+el_val_t  el_local_date_lt(el_val_t a, el_val_t b);
+el_val_t  el_local_date_eq(el_val_t a, el_val_t b);
+
+/* Rhythm — pluggable recurrence AST. Returns a heap-allocated struct
+ * pointer in el_val_t; rhythms are immutable so callers may share them. */
+el_val_t  rhythm_cycle_start(void);
+el_val_t  rhythm_cycle_phase(el_val_t phase);
+el_val_t  rhythm_duration(el_val_t d);
+el_val_t  rhythm_session_start(void);
+el_val_t  rhythm_event(el_val_t name);
+el_val_t  rhythm_and(el_val_t a, el_val_t b);
+el_val_t  rhythm_or(el_val_t a, el_val_t b);
+el_val_t  rhythm_weekday(el_val_t day);
+el_val_t  rhythm_weekly_at(el_val_t day, el_val_t hour, el_val_t minute);
+el_val_t  rhythm_next_after(el_val_t r, el_val_t after, el_val_t cal);
+el_val_t  rhythm_matches(el_val_t r, el_val_t ct);
+
+/* ── UUID ────────────────────────────────────────────────────────────────── */
+
+el_val_t  uuid_new(void);
+el_val_t  uuid_v4(void);
+
+/* ── Environment ─────────────────────────────────────────────────────────── */
+
+el_val_t  env(el_val_t key);
+
+/* ── In-process state K/V ────────────────────────────────────────────────── */
+
+el_val_t  state_set(el_val_t key, el_val_t value);
+el_val_t  state_get(el_val_t key);
+el_val_t  state_del(el_val_t key);
+el_val_t  state_keys(void);
+el_val_t  state_has(el_val_t key);
+el_val_t  state_get_or(el_val_t key, el_val_t default_val);
+
+/* ── Float formatting ────────────────────────────────────────────────────── */
+
+el_val_t  float_to_str(el_val_t f);
+el_val_t  int_to_float(el_val_t n);
+el_val_t  float_to_int(el_val_t f);
+el_val_t  format_float(el_val_t f, el_val_t decimals);
+el_val_t  decimal_round(el_val_t f, el_val_t decimals);
+el_val_t  str_to_float(el_val_t s);
+
+/* ── Math (Float-aware) ──────────────────────────────────────────────────── */
+
+el_val_t  math_sqrt(el_val_t f);
+el_val_t  math_log(el_val_t f);
+el_val_t  math_ln(el_val_t f);
+el_val_t  math_sin(el_val_t f);
+el_val_t  math_cos(el_val_t f);
+el_val_t  math_pi(void);
+
+/* ── String additions ────────────────────────────────────────────────────── */
+
+el_val_t  str_index_of(el_val_t s, el_val_t sub);
+el_val_t  str_split(el_val_t s, el_val_t sep);
+el_val_t  str_char_at(el_val_t s, el_val_t i);
+el_val_t  str_char_code(el_val_t s, el_val_t i);
+el_val_t  str_pad_left(el_val_t s, el_val_t width, el_val_t pad);
+el_val_t  str_pad_right(el_val_t s, el_val_t width, el_val_t pad);
+el_val_t  str_format(el_val_t fmt, el_val_t data);
+el_val_t  str_lower(el_val_t s);
+el_val_t  str_upper(el_val_t s);
+
+/* ── Text-processing primitives (Phase 1: byte/codepoint, ASCII char classes)
+ * Phase 2 (filed): Unicode-grapheme awareness, NFC/NFD normalization, regex.
+ * is_* predicates: empty input returns false; multi-char requires ALL bytes
+ * to match. ASCII ranges only in Phase 1. */
+
+/* Counting */
+el_val_t  str_count(el_val_t s, el_val_t sub);              /* non-overlapping */
+el_val_t  str_count_chars(el_val_t s);                      /* codepoint count */
+el_val_t  str_count_bytes(el_val_t s);                      /* alias of str_len */
+el_val_t  str_count_lines(el_val_t s);
+el_val_t  str_count_words(el_val_t s);
+el_val_t  str_count_letters(el_val_t s);                    /* ASCII [A-Za-z] */
+el_val_t  str_count_digits(el_val_t s);                     /* ASCII [0-9] */
+
+/* Find / position */
+el_val_t  str_index_of_all(el_val_t s, el_val_t sub);       /* [Int] of byte offsets */
+el_val_t  str_last_index_of(el_val_t s, el_val_t sub);
+el_val_t  str_find_chars(el_val_t s, el_val_t any_of);      /* first idx of any ch */
+
+/* Transform */
+el_val_t  str_repeat(el_val_t s, el_val_t n);
+el_val_t  str_reverse(el_val_t s);                          /* by codepoint */
+el_val_t  str_strip_prefix(el_val_t s, el_val_t prefix);
+el_val_t  str_strip_suffix(el_val_t s, el_val_t suffix);
+el_val_t  str_strip_chars(el_val_t s, el_val_t chars);
+el_val_t  str_lstrip(el_val_t s);
+el_val_t  str_rstrip(el_val_t s);
+
+/* Char classification (Bool) */
+el_val_t  is_letter(el_val_t s);
+el_val_t  is_digit(el_val_t s);
+el_val_t  is_alphanumeric(el_val_t s);
+el_val_t  is_whitespace(el_val_t s);
+el_val_t  is_punctuation(el_val_t s);
+el_val_t  is_uppercase(el_val_t s);
+el_val_t  is_lowercase(el_val_t s);
+
+/* Split / join */
+el_val_t  str_split_lines(el_val_t s);
+el_val_t  str_split_chars(el_val_t s);                      /* alias of native_string_chars */
+el_val_t  str_split_n(el_val_t s, el_val_t sep, el_val_t n);
+el_val_t  str_join(el_val_t list, el_val_t sep);            /* alias of list_join */
+
+/* ── List additions ──────────────────────────────────────────────────────── */
+
+el_val_t  list_push(el_val_t list, el_val_t elem);
+el_val_t  list_push_front(el_val_t list, el_val_t elem);
+el_val_t  list_join(el_val_t list, el_val_t sep);
+el_val_t  list_range(el_val_t start, el_val_t end);
+
+/* ── Bool helpers ────────────────────────────────────────────────────────── */
+
+el_val_t  bool_to_str(el_val_t b);
+
+/* ── Numeric parsing ─────────────────────────────────────────────────────── */
+
+el_val_t  parse_int(el_val_t s, el_val_t default_val);
+
+/* ── Process ─────────────────────────────────────────────────────────────── */
+
+el_val_t  exit_program(el_val_t code);
+el_val_t  getpid_now(void);
+
+/* Self-terminating memory guard. Reads ELC_MAX_MEM_MB (default 512) and
+ * exits with code 1 if resident memory exceeds the limit. Call periodically
+ * during long compilation loops (e.g. after each function is compiled).
+ * Returns 0 when memory is within bounds.                                   */
+el_val_t  el_mem_check(void);
+
+/* ── CGI identity ─────────────────────────────────────────────────────────────
+ * Called at the start of main() in CGI programs (those with a `cgi {}` block).
+ * Records the program's DHARMA identity before any other code executes.      */
+
+void      el_cgi_init(el_val_t name, el_val_t dharma_id, el_val_t principal,
+                      el_val_t network, el_val_t engram);
+
+/* ── DHARMA network builtins ─────────────────────────────────────────────────
+ * Available to CGI programs (declared with a `cgi {}` block).
+ *
+ * Peers are addressed by `dharma_id` of the form
+ *     "<registry-id>@<transport-url>"   e.g. "ntn-genesis@http://localhost:7770"
+ * If the @<url> portion is omitted, transport defaults to
+ * "http://localhost:7770" (the local CGI daemon assumption).
+ *
+ * Wire protocol (all peers expose):
+ *   POST <url>/dharma/recv      { channel, from, content } → response body
+ *   POST <url>/dharma/event     { type, payload, source, timestamp }
+ *   POST <url>/api/activate     { query }                 → list of nodes
+ *
+ * Hosting application's responsibility: an El program with a `cgi {}` block
+ * runs http_serve() with its own request handler; that handler should route
+ * "/dharma/event" requests by calling el_runtime_dharma_event_arrive() so
+ * incoming events feed dharma_field() queues. The runtime itself does not
+ * intercept any /dharma path.                                                */
+
+el_val_t  dharma_connect(el_val_t cgi_id);
+el_val_t  dharma_send(el_val_t channel, el_val_t content);
+el_val_t  dharma_activate(el_val_t query);
+void      dharma_emit(el_val_t event_type, el_val_t payload);
+el_val_t  dharma_field(el_val_t event_type);
+void      dharma_strengthen(el_val_t cgi_id, el_val_t weight);
+el_val_t  dharma_relationship(el_val_t cgi_id);
+el_val_t  dharma_peers(void);
+
+/* Public C API: called by an El program's HTTP handler when a /dharma/event
+ * request arrives. Pushes onto the per-event-type queue and signals any
+ * pending dharma_field() blockers. All three arguments must be NUL-terminated
+ * C strings (or NULL — then treated as empty).                               */
+void      el_runtime_dharma_event_arrive(const char* event_type,
+                                         const char* payload,
+                                         const char* source);
+
+/* ── Engram local graph primitives ───────────────────────────────────────────
+ * Operate on the CGI's local Engram knowledge graph.
+ * `engram_activate` queries the local graph only; `dharma_activate` is
+ * network-wide across all connected CGI graphs.                              */
+
+el_val_t  engram_node(el_val_t content, el_val_t node_type, el_val_t salience);
+el_val_t  engram_node_full(el_val_t content, el_val_t node_type, el_val_t label,
+                           el_val_t salience, el_val_t importance, el_val_t confidence,
+                           el_val_t tier, el_val_t tags);
+/* Layered consciousness — see el_runtime.c for the layered architecture
+ * design notes (search "Layered consciousness architecture"). The five
+ * canonical layers (safety / core-identity / domain-knowledge / imprint /
+ * suit) are seeded automatically; engram_add_layer extends the registry
+ * with imprint or suit overlays at runtime. Nodes default to layer 1
+ * (core-identity) when created via engram_node / engram_node_full. */
+el_val_t  engram_node_layered(el_val_t content, el_val_t node_type, el_val_t label,
+                              el_val_t salience, el_val_t certainty, el_val_t confidence,
+                              el_val_t status, el_val_t tags, el_val_t layer_id);
+el_val_t  engram_add_layer(el_val_t name, el_val_t priority, el_val_t suppressible,
+                           el_val_t transparent, el_val_t injectable);
+el_val_t  engram_remove_layer(el_val_t layer_id);
+el_val_t  engram_list_layers(void);
+el_val_t  engram_get_node(el_val_t id);
+void      engram_strengthen(el_val_t node_id);
+void      engram_forget(el_val_t node_id);
+el_val_t  engram_node_count(void);
+el_val_t  engram_search(el_val_t query, el_val_t limit);
+el_val_t  engram_scan_nodes(el_val_t limit, el_val_t offset);
+void      engram_connect(el_val_t from_id, el_val_t to_id, el_val_t weight, el_val_t relation);
+el_val_t  engram_edge_between(el_val_t from_id, el_val_t to_id);
+el_val_t  engram_neighbors(el_val_t node_id);
+el_val_t  engram_neighbors_filtered(el_val_t node_id, el_val_t max_depth, el_val_t direction);
+el_val_t  engram_edge_count(void);
+/* Three-pass activation: background fan-out → working-memory promotion →
+ * Layer 0 override. See "Three-pass activation" in el_runtime.c. */
+el_val_t  engram_activate(el_val_t query, el_val_t depth);
+el_val_t  engram_save(el_val_t path);
+el_val_t  engram_load(el_val_t path);
+
+/* JSON-string accessors — return pre-serialized JSON so HTTP handlers
+ * can pass results straight through without round-tripping ElList/ElMap
+ * through json_stringify. */
+el_val_t  engram_get_node_json(el_val_t id);
+el_val_t  engram_get_node_by_label(el_val_t label);
+el_val_t  engram_search_json(el_val_t query, el_val_t limit);
+el_val_t  engram_scan_nodes_json(el_val_t limit, el_val_t offset);
+el_val_t  engram_scan_nodes_by_type_json(el_val_t node_type, el_val_t limit, el_val_t offset);
+el_val_t  engram_neighbors_json(el_val_t node_id, el_val_t max_depth, el_val_t direction);
+el_val_t  engram_activate_json(el_val_t query, el_val_t depth);
+el_val_t  engram_stats_json(void);
+el_val_t  engram_list_layers_json(void);
+/* engram_compile_layered_json — produce a prompt-ready text block split
+ * into "[LAYER 0 — STRUCTURAL]" (non-suppressible layers, sacred fire)
+ * and "[ENGRAM CONTEXT]" (standard suppressible layers). Returns "" if
+ * no nodes promoted to working memory. */
+el_val_t  engram_compile_layered_json(el_val_t intent, el_val_t depth);
+
+/* ── Working memory ──────────────────────────────────────────────────────────*/
+el_val_t  engram_wm_count(void);
+el_val_t  engram_wm_avg_weight(void);
+el_val_t  engram_wm_top_json(el_val_t n);
+el_val_t  engram_load_merge(el_val_t path);
+
+/* ── LLM (Anthropic API client) ─────────────────────────────────────────────
+ * All functions call https://api.anthropic.com/v1/messages with the API key
+ * from env ANTHROPIC_API_KEY. Default model when empty: claude-sonnet-4-5. */
+
+el_val_t  llm_call(el_val_t model, el_val_t prompt);
+el_val_t  llm_call_system(el_val_t model, el_val_t system_prompt, el_val_t user_prompt);
+el_val_t  llm_call_agentic(el_val_t model, el_val_t system, el_val_t user, el_val_t tools);
+el_val_t  llm_vision(el_val_t model, el_val_t system, el_val_t prompt, el_val_t image_url_or_b64);
+el_val_t  llm_models(void);
+
+/* Register a tool handler by name. The handler is looked up via dlsym
+ * (mirroring http_set_handler), so any El `fn <name>(input)` compiles to
+ * a global C symbol that this function can locate at runtime.
+ * Handler signature: `el_val_t handler(el_val_t input_json)` — receives
+ * the tool input as a JSON-string el_val_t and returns a JSON-string
+ * el_val_t result. Used by llm_call_agentic.                                 */
+void      llm_register_tool(el_val_t name, el_val_t handler_fn_name);
+
+/* ── args() ─────────────────────────────────────────────────────────────────
+ * Provides access to command-line arguments passed to the program.
+ * Populated by el_runtime_init_args() before main() runs.           */
+
+el_val_t  args(void);
+void      el_runtime_init_args(int argc, char** argv);
+
+/* ── Crypto primitives ─────────────────────────────────────────────────────
+ * SHA-256, HMAC-SHA-256, and base64 (standard + URL-safe).
+ * Self-contained — no OpenSSL/libcrypto dependency. The implementations are
+ * adapted from public-domain reference code (Brad Conte / RFC 4648).
+ *
+ * Bytes-returning variants (sha256_bytes, hmac_sha256_bytes) return a string
+ * value whose contents are raw binary; callers usually feed these into
+ * base64_encode. Note that el_val_t strings are NUL-terminated by convention,
+ * so the binary payload may contain embedded NULs — pass it directly into
+ * base64_encode (which uses an explicit length) rather than treating it as
+ * a printable C string.
+ *
+ * The "base64" variants emit/accept RFC 4648 standard alphabet with padding.
+ * The "base64url" variants use URL-safe alphabet (`-`/`_`) with no padding,
+ * as used in JWTs.                                                           */
+
+el_val_t  sha256_hex(el_val_t input);
+el_val_t  sha256_bytes(el_val_t input);
+el_val_t  hmac_sha256_hex(el_val_t key, el_val_t message);
+el_val_t  hmac_sha256_bytes(el_val_t key, el_val_t message);
+el_val_t  base64_encode(el_val_t input);
+el_val_t  base64_decode(el_val_t input);
+el_val_t  base64url_encode(el_val_t input);
+el_val_t  base64url_decode(el_val_t input);
+
+/* Length-aware variants (internal — exposed for the rare caller that already
+ * has a known-length binary buffer and doesn't want to round-trip through
+ * a NUL-terminated el_val_t string). Sha256_bytes and hmac_sha256_bytes feed
+ * these implicitly. */
+el_val_t  el_sha256_bytes_n(const unsigned char* data, size_t len);
+el_val_t  el_base64_encode_n(const unsigned char* data, size_t len, int url_safe);
+
+/* ── Post-quantum primitives (liboqs-backed) ────────────────────────────────
+ * All inputs/outputs hex-encoded. Algorithm choices:
+ *   Signature: CRYSTALS-Dilithium-3   (NIST level 3, balanced)
+ *   KEM:       CRYSTALS-Kyber-768     (NIST level 3)
+ *   Hash:      SHA3-256 (Keccak)      (PQ-aware protocols favour SHA3 over SHA2)
+ *
+ * If liboqs is not linked (detected via __has_include(<oqs/oqs.h>) at compile
+ * time), the pq_* entry points return a JSON-shaped error string so callers
+ * fail loudly rather than silently fall back to classical schemes:
+ *   {"error":"liboqs not linked, post-quantum primitives unavailable"}
+ *
+ * The hybrid handshake pairs X25519 with Kyber-768 per NIST PQ guidance and
+ * CNSA 2.0. Combined shared secret is HKDF-SHA256(x25519_ss || kyber_ss).
+ * Even if Kyber falls, X25519 holds; if X25519 falls under quantum attack,
+ * Kyber holds. SHA3-256 also remains usable independent of liboqs (the
+ * Keccak permutation is PQ-OK as a primitive). */
+
+el_val_t  pq_keygen_signature(void);
+el_val_t  pq_sign(el_val_t secret_key_hex, el_val_t message);
+el_val_t  pq_verify(el_val_t public_key_hex, el_val_t message, el_val_t signature_hex);
+
+el_val_t  pq_kem_keygen(void);
+el_val_t  pq_kem_encaps(el_val_t public_key_hex);
+el_val_t  pq_kem_decaps(el_val_t secret_key_hex, el_val_t ciphertext_hex);
+
+el_val_t  pq_hybrid_keygen(void);
+el_val_t  pq_hybrid_handshake(el_val_t remote_pub_combined);
+
+el_val_t  sha3_256_hex(el_val_t input);
+
+/* ── AEAD: AES-256-GCM (libcrypto-backed) ───────────────────────────────────
+ * Symmetric authenticated encryption used to wrap envelopes after a KEM
+ * handshake. Caller MUST supply a 32-byte key (64 hex chars) — typically the
+ * Kyber-768 / hybrid shared_secret, optionally normalized via SHA3-256.
+ *
+ * aead_encrypt returns a JSON map {"nonce":"...","ciphertext":"..."} where
+ * ciphertext is the AES-256-GCM output with the 16-byte auth tag appended.
+ * Nonce is a fresh 12-byte CSPRNG draw — callers never pick the nonce, which
+ * structurally rules out the GCM nonce-reuse footgun.
+ *
+ * aead_decrypt returns the plaintext String, or "" on any failure (including
+ * auth-tag mismatch). Callers MUST check for "" before trusting the result. */
+el_val_t  aead_encrypt(el_val_t key_hex, el_val_t plaintext);
+el_val_t  aead_decrypt(el_val_t key_hex, el_val_t nonce_hex, el_val_t ciphertext_hex);
+
+/* ── Native VM builtin aliases (for compiled El source) ─────────────────────
+ * These match the El VM's native_* builtins so that El source compiled
+ * to C can call the same names without modification.                */
+
+el_val_t  native_list_get(el_val_t list, el_val_t index);
+el_val_t  native_list_len(el_val_t list);
+el_val_t  native_list_append(el_val_t list, el_val_t elem);
+el_val_t  native_list_empty(void);
+el_val_t  native_list_clone(el_val_t list);
+el_val_t  native_string_chars(el_val_t s);
+el_val_t  native_int_to_str(el_val_t n);
+
+/* ── Method-call shorthand aliases ──────────────────────────────────────────
+ * The El method-call convention `obj.method(args)` compiles to
+ * `method(obj, args)`.  These aliases expose the runtime functions under
+ * the short names that result from method calls in El source.
+ *
+ * Example: `myList.append(x)` → `append(myList, x)` (calls this alias)
+ *          `myList.len()`     → `len(myList)`         (calls this alias)  */
+
+el_val_t  append(el_val_t list, el_val_t elem);   /* el_list_append */
+el_val_t  len(el_val_t list);                      /* el_list_len    */
+el_val_t  get(el_val_t list, el_val_t index);      /* el_list_get    */
+el_val_t  map_get(el_val_t map, el_val_t key);     /* el_map_get     */
+el_val_t  map_set(el_val_t map, el_val_t key, el_val_t value); /* el_map_set */
+
+/* ── OTLP/HTTP Observability ─────────────────────────────────────────────── */
+/* See bottom of el_runtime.c for the implementation.
+ * Configured by env vars OTLP_ENDPOINT, OTEL_SERVICE_NAME, OTEL_SERVICE_VERSION.
+ * No-op when OTLP_ENDPOINT is unset. Drop-on-failure semantics. */
+/* ── Subprocess execution ────────────────────────────────────────────────── */
+el_val_t exec_command(el_val_t cmd);   /* run shell command, return exit code */
+el_val_t exec_capture(el_val_t cmd);   /* run shell command, capture stdout   */
+el_val_t exec(el_val_t cmd);           /* exec(cmd) → stdout String (30s timeout) */
+el_val_t exec_bg(el_val_t cmd);        /* exec_bg(cmd) → PID String (non-blocking) */
+
+/* ── Stdout redirection (used by compiler JS pipeline) ───────────────────── */
+el_val_t stdout_to_file(el_val_t path); /* redirect process stdout to a file  */
+el_val_t stdout_restore(void);          /* restore process stdout to terminal  */
+
+el_val_t emit_log(el_val_t level, el_val_t msg, el_val_t fields_json);
+el_val_t emit_metric(el_val_t name, el_val_t value, el_val_t tags_json);
+el_val_t trace_span_start(el_val_t name);
+el_val_t trace_span_end(el_val_t span_handle);
+el_val_t emit_event(el_val_t name, el_val_t duration_ms);
+
+el_val_t __thread_create(el_val_t fn_name_v, el_val_t arg_v);
+el_val_t __thread_join(el_val_t tid_v);
+
+/* ── __ prefixed aliases (self-hosting compiler ABI) ─────────────────────────
+ * The El self-hosting compiler emits calls to __-prefixed names. These are
+ * forwarding wrappers around the existing el_runtime functions above.        */
+
+/* I/O */
+el_val_t  __println(el_val_t s);
+el_val_t  __print(el_val_t s);
+el_val_t  __readline(void);
+
+/* String */
+el_val_t  __int_to_str(el_val_t n);
+el_val_t  __str_to_int(el_val_t s);
+el_val_t  __float_to_str(el_val_t f);
+el_val_t  __str_to_float(el_val_t s);
+el_val_t  __str_len(el_val_t s);
+el_val_t  __str_char_at(el_val_t s, el_val_t i);
+el_val_t  __str_cmp(el_val_t a, el_val_t b);
+el_val_t  __str_ncmp(el_val_t a, el_val_t b, el_val_t n);
+el_val_t  __str_concat_raw(el_val_t a, el_val_t b);
+el_val_t  __str_slice_raw(el_val_t s, el_val_t start, el_val_t end);
+el_val_t  __str_alloc(el_val_t n);
+el_val_t  __str_set_char(el_val_t s, el_val_t i, el_val_t c);
+
+/* URL encoding */
+el_val_t  __url_encode(el_val_t s);
+el_val_t  __url_decode(el_val_t s);
+
+/* Environment */
+el_val_t  __env_get(el_val_t key);
+
+/* Subprocess */
+el_val_t  __exec(el_val_t cmd);
+el_val_t  __exec_bg(el_val_t cmd);
+
+/* Process */
+el_val_t  __exit_program(el_val_t code);
+
+/* Filesystem */
+el_val_t  __fs_exists(el_val_t path);
+el_val_t  __fs_mkdir(el_val_t path);
+el_val_t  __fs_read(el_val_t path);
+el_val_t  __fs_write(el_val_t path, el_val_t content);
+el_val_t  __fs_write_bytes(el_val_t path, el_val_t bytes, el_val_t n);
+el_val_t  __fs_list_raw(el_val_t path);
+
+/* HTTP server */
+el_val_t  __http_response(el_val_t status, el_val_t headers_json, el_val_t body);
+el_val_t  __http_serve(el_val_t port, el_val_t handler);
+el_val_t  __http_serve_v2(el_val_t port, el_val_t handler);
+
+/* HTTP conn fd / SSE (weak; overridden by el_seed.c when linked together) */
+el_val_t  __http_conn_fd(void);
+el_val_t  __http_sse_open(el_val_t conn_id);
+el_val_t  __http_sse_send(el_val_t conn_id, el_val_t data);
+el_val_t  __http_sse_close(el_val_t conn_id);
+
+/* HTTP client (requires HAVE_CURL; stubs provided for no-curl builds) */
+el_val_t  __http_do(el_val_t method, el_val_t url, el_val_t body,
+                    el_val_t headers_map, el_val_t timeout_ms);
+el_val_t  __http_do_map(el_val_t method, el_val_t url, el_val_t body,
+                        el_val_t headers_json, el_val_t timeout_ms);
+el_val_t  __http_do_map_to_file(el_val_t method, el_val_t url, el_val_t body,
+                                el_val_t headers_json, el_val_t output_path);
+
+/* JSON */
+el_val_t  __json_array_get(el_val_t json, el_val_t index);
+el_val_t  __json_array_get_string(el_val_t json, el_val_t index);
+el_val_t  __json_array_len(el_val_t json);
+el_val_t  __json_get(el_val_t json, el_val_t key);
+el_val_t  __json_get_raw(el_val_t json, el_val_t key);
+el_val_t  __json_set(el_val_t json, el_val_t key, el_val_t value);
+el_val_t  __json_parse_map(el_val_t json_str);
+el_val_t  __json_stringify_val(el_val_t val);
+
+/* Hashing */
+el_val_t  __sha256_hex(el_val_t s);
+
+/* State K/V */
+el_val_t  __state_del(el_val_t key);
+el_val_t  __state_get(el_val_t key);
+el_val_t  __state_keys(void);
+el_val_t  __state_set(el_val_t key, el_val_t val);
+
+/* UUID */
+el_val_t  __uuid_v4(void);
+
+/* Args */
+el_val_t  __args_json(void);
+
+#ifdef __cplusplus
+}
+#endif

lang/el-compiler/runtime/el_seed.c

@@ -8,7 +8,7 @@
  * Threading: __thread_create / __thread_join use dlsym(RTLD_DEFAULT) to look
  * up El function symbols at runtime. This is the foundation of El's parallelism.
  *
- * Link: cc -std=c11 -I runtime -lcurl -lpthread \
+ * Link: cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
  *           -o <out> <prog>.c el_seed.c
  */
 

lang/el-compiler/runtime/legacy/el_runtime.h

@@ -0,0 +1,761 @@
+/*
+ * el_runtime.h — El language C runtime header
+ *
+ * Declares all built-in functions available to compiled El programs.
+ * Include this in every generated .c file.
+ *
+ * Value model:
+ *   All El values are represented as el_val_t (= int64_t).
+ *   On 64-bit systems a pointer fits in int64_t.
+ *   String values are cast: (el_val_t)(uintptr_t)"hello"
+ *   Integer values are stored directly.
+ *   This lets arithmetic work naturally while still passing strings around.
+ *
+ * Type conventions (El -> C):
+ *   String  -> el_val_t  (holds const char* via uintptr_t cast)
+ *   Int     -> el_val_t
+ *   Bool    -> el_val_t  (0 = false, nonzero = true)
+ *   Any     -> el_val_t
+ *   Void    -> void
+ *
+ * Macros for convenience:
+ *   EL_STR(s)    cast string literal to el_val_t
+ *   EL_CSTR(v)   cast el_val_t back to const char*
+ *   EL_INT(v)    identity — el_val_t is already int64_t
+ *
+ * Link requirements:
+ *   -lcurl     — required for the HTTP client (http_get, http_post, llm_*).
+ *   -lpthread  — required for the HTTP server (one detached thread per
+ *                connection, capped at 64 concurrent).
+ *   -loqs      — optional; required only when liboqs is installed and the
+ *                pq_* / sha3_256_hex entry points are needed. Detected at
+ *                compile time via __has_include(<oqs/oqs.h>).
+ *   -lcrypto   — optional; pulled in alongside -loqs. Used for X25519 in
+ *                pq_hybrid_* and HKDF-SHA256 derivation.
+ *
+ * Canonical compile command:
+ *   cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
+ *      -o <out> <prog>.c el-compiler/runtime/el_runtime.c
+ *
+ * With liboqs (post-quantum stack):
+ *   cc -std=c11 -I el-compiler/runtime -lcurl -lpthread -loqs -lcrypto \
+ *      -o <out> <prog>.c el-compiler/runtime/el_runtime.c
+ */
+
+#pragma once
+
+#include <stdint.h>
+#include <stdlib.h>
+
+typedef int64_t el_val_t;
+
+#define EL_STR(s)  ((el_val_t)(uintptr_t)(s))
+#define EL_CSTR(v) ((const char*)(uintptr_t)(v))
+#define EL_INT(v)  (v)
+#define EL_NULL    ((el_val_t)0)
+
+/* Float values share the el_val_t (int64) slot via a bit-cast.
+ * The codegen emits Float literals as `el_from_float(<dbl>)` so the
+ * underlying bits represent the IEEE 754 double. Float-aware builtins
+ * (math, format, json) round-trip via these helpers. */
+static inline double el_to_float(el_val_t v) {
+    union { int64_t i; double f; } u;
+    u.i = (int64_t)v;
+    return u.f;
+}
+
+static inline el_val_t el_from_float(double f) {
+    union { double f; int64_t i; } u;
+    u.f = f;
+    return (el_val_t)u.i;
+}
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* ── I/O ──────────────────────────────────────────────────────────────────── */
+
+void      println(el_val_t s);
+void      print(el_val_t s);
+el_val_t  readline(void);
+
+/* ── String builtins ─────────────────────────────────────────────────────── */
+
+el_val_t  el_str_concat(el_val_t a, el_val_t b);
+el_val_t  str_eq(el_val_t a, el_val_t b);
+el_val_t  str_starts_with(el_val_t s, el_val_t prefix);
+el_val_t  str_ends_with(el_val_t s, el_val_t suffix);
+el_val_t  str_len(el_val_t s);
+el_val_t  str_concat(el_val_t a, el_val_t b);
+el_val_t  int_to_str(el_val_t n);
+el_val_t  str_to_int(el_val_t s);
+el_val_t  str_slice(el_val_t s, el_val_t start, el_val_t end);
+el_val_t  str_contains(el_val_t s, el_val_t sub);
+el_val_t  str_replace(el_val_t s, el_val_t from, el_val_t to);
+el_val_t  str_to_upper(el_val_t s);
+el_val_t  str_to_lower(el_val_t s);
+el_val_t  str_trim(el_val_t s);
+
+/* ── Math ────────────────────────────────────────────────────────────────── */
+
+el_val_t  el_abs(el_val_t n);
+el_val_t  el_max(el_val_t a, el_val_t b);
+el_val_t  el_min(el_val_t a, el_val_t b);
+
+/* ── Refcount (ARC) ──────────────────────────────────────────────────────────
+ * Lists and Maps carry a refcount. Strings and ints do not — el_retain and
+ * el_release are safe no-ops on non-refcounted values (they sniff a magic
+ * header at offset 0 and only act if the magic matches).
+ *
+ * Codegen emits these at let-binding shadowing, function entry (params), and
+ * function exit (locals other than the returned value). The refcount lets
+ * el_list_append and el_map_set mutate in place when uniquely owned (cheap)
+ * and copy-on-write when shared (preserves persistent semantics across
+ * accumulator patterns in the compiler itself).                              */
+
+void      el_retain(el_val_t v);
+void      el_release(el_val_t v);
+
+/* ── List ────────────────────────────────────────────────────────────────── */
+
+el_val_t  el_list_new(el_val_t count, ...);
+el_val_t  el_list_len(el_val_t list);
+el_val_t  el_list_get(el_val_t list, el_val_t index);
+el_val_t  el_list_append(el_val_t list, el_val_t elem);
+el_val_t  el_list_empty(void);
+el_val_t  el_list_clone(el_val_t list);
+
+/* ── Map ─────────────────────────────────────────────────────────────────── */
+
+el_val_t  el_map_new(el_val_t pair_count, ...);
+el_val_t  el_get_field(el_val_t map, el_val_t key);
+el_val_t  el_map_get(el_val_t map, el_val_t key);
+el_val_t  el_map_set(el_val_t map, el_val_t key, el_val_t value);
+
+/* ── HTTP ─────────────────────────────────────────────────────────────────── */
+
+el_val_t  http_get(el_val_t url);
+el_val_t  http_post(el_val_t url, el_val_t body);
+el_val_t  http_post_json(el_val_t url, el_val_t json_body);
+el_val_t  http_get_with_headers(el_val_t url, el_val_t headers_map);
+el_val_t  http_post_with_headers(el_val_t url, el_val_t body, el_val_t headers_map);
+el_val_t  http_post_form_auth(el_val_t url, el_val_t form_body, el_val_t auth_header);
+el_val_t  http_delete(el_val_t url);
+void      http_serve(el_val_t port, el_val_t handler);
+void      http_set_handler(el_val_t name);
+
+/* HTTP server v2 ─────────────────────────────────────────────────────────────
+ * Same dispatch model as http_serve, but the handler signature is widened:
+ *
+ *     el_val_t handler(method, path, headers_map, body)
+ *
+ * `headers_map` is an ElMap from lowercased header name → header value (both
+ * Strings). Repeated headers are joined with ", " per RFC 7230.
+ *
+ * Response value: the handler may return either
+ *   (a) a plain body string — same auto-content-type / 200-OK behaviour as
+ *       http_serve (3-arg) — or
+ *   (b) a response envelope built with `http_response(status, headers_json,
+ *       body)`. The runtime detects the envelope discriminator
+ *       `"el_http_response":1` at the start of the returned string and
+ *       unpacks status / headers / body before sending.
+ *
+ * The 3-arg http_serve(port, handler) remains supported unchanged for
+ * existing handlers (e.g. products/web/server.el): it dispatches with
+ * (method, path, body), hardcodes 200 OK, and auto-detects content type. */
+void      http_serve_v2(el_val_t port, el_val_t handler);
+void      http_set_handler_v2(el_val_t name);
+
+/* Build an HTTP response envelope. `headers_json` should be a JSON object
+ * literal like `{"WWW-Authenticate":"Basic"}` (or "" / "{}" for none). The
+ * returned string carries the discriminator `{"el_http_response":1,...}`
+ * which the runtime's send-path detects and unpacks. Detection happens
+ * uniformly inside http_send_response, so a 3-arg handler may also return
+ * an envelope. The 3-arg variant remains documented as a fixed 200-OK
+ * auto-content-type contract for legacy handlers that return plain bodies. */
+el_val_t  http_response(el_val_t status, el_val_t headers_json, el_val_t body);
+
+/* SSE connection fd — set by http_worker_v2 before calling the El handler,
+ * cleared afterwards. Defined in el_seed.c; called from el_runtime.c.
+ * The getter is exposed as __http_conn_fd() to El programs. */
+void      el_seed_set_http_conn_fd(int fd);
+
+/* HTTP timeout — every libcurl request honors EL_HTTP_TIMEOUT_MS (default
+ * 60000ms). Read lazily on first use, so setting the env var any time before
+ * the first http_* call is sufficient.                                    */
+
+/* Streaming variants — write the response body straight to a file via
+ * libcurl's CURLOPT_WRITEFUNCTION = fwrite. These bypass the el_val_t string
+ * wrapper entirely, so binary payloads (audio/mpeg, image/png, etc.) survive
+ * embedded NUL bytes that would truncate a strlen()-based code path.
+ *
+ * Both honor EL_HTTP_TIMEOUT_MS, follow redirects, and accept the same
+ * `headers_map` shape as http_post_with_headers (ElMap of String→String).
+ *
+ * Return value: 1 on success (file fully written), 0 on any failure
+ * (network, file open, partial write). On failure the output file is removed
+ * so callers cannot mistake a partially-written file for a valid one. */
+el_val_t  http_post_to_file(el_val_t url, el_val_t body, el_val_t headers_map, el_val_t output_path);
+el_val_t  http_get_to_file(el_val_t url, el_val_t headers_map, el_val_t output_path);
+
+/* ── URL encoding ────────────────────────────────────────────────────────── */
+
+el_val_t  url_encode(el_val_t s);   /* RFC 3986 unreserved set */
+el_val_t  url_decode(el_val_t s);   /* '+' → space, %XX → byte  */
+
+/* ── HTML allowlist sanitizer ────────────────────────────────────────────────
+ * el_html_sanitize(input_html, allowlist_json) — strict allowlist HTML
+ * cleaner. State-machine parser; tag/attribute names compared case-
+ * insensitively against the allowlist; `<a href>` / `<… src>` URL schemes
+ * validated (http, https, mailto, fragment-only, or relative); whole-
+ * subtree drop for script / style / iframe / object / embed / form; HTML-
+ * escapes free text outside dropped subtrees.
+ *
+ * The allowlist is JSON of the form
+ *     {"p":[],"a":["href","title"],"strong":[],...}
+ * where each value is the array of attribute names allowed for that tag. */
+el_val_t  el_html_sanitize(el_val_t input_html, el_val_t allowlist_json);
+
+/* ── Filesystem ──────────────────────────────────────────────────────────── */
+
+el_val_t  fs_read(el_val_t path);
+el_val_t  fs_write(el_val_t path, el_val_t content);
+el_val_t  fs_list(el_val_t path);
+el_val_t  fs_exists(el_val_t path);
+el_val_t  fs_mkdir(el_val_t path);   /* mkdir -p, mode 0755                */
+
+/* Length-explicit binary write. `length` is an Int (el_val_t holding the
+ * byte count). The caller knows the length from context — typically because
+ * `bytes` came from base64_decode (which produces a magic-tagged binary
+ * buffer with embedded NULs possible) and the caller already tracks the
+ * decoded length, OR because the bytes came from a fixed-size source
+ * (sha256_bytes = 32, hmac_sha256_bytes = 32). Bypasses strlen entirely.
+ *
+ * Returns 1 on success, 0 on failure (invalid path, can't open, partial
+ * write, negative length). On partial-write failure, the file is removed
+ * so callers cannot read back a truncated artefact. */
+el_val_t  fs_write_bytes(el_val_t path, el_val_t bytes, el_val_t length);
+
+/* ── JSON ────────────────────────────────────────────────────────────────── */
+
+el_val_t  json_get(el_val_t json, el_val_t key);
+el_val_t  json_parse(el_val_t s);
+el_val_t  json_stringify(el_val_t v);
+el_val_t  json_get_string(el_val_t json_str, el_val_t key);
+el_val_t  json_get_int(el_val_t json_str, el_val_t key);
+el_val_t  json_get_float(el_val_t json_str, el_val_t key);
+el_val_t  json_get_bool(el_val_t json_str, el_val_t key);
+el_val_t  json_get_raw(el_val_t json_str, el_val_t key);
+el_val_t  json_set(el_val_t json_str, el_val_t key, el_val_t value);
+el_val_t  json_array_len(el_val_t json_str);
+el_val_t  json_array_get(el_val_t json_str, el_val_t index);
+el_val_t  json_array_get_string(el_val_t json_str, el_val_t index);
+
+/* ── Time ────────────────────────────────────────────────────────────────── */
+
+el_val_t  time_now(void);
+el_val_t  time_now_utc(void);
+el_val_t  sleep_secs(el_val_t secs);
+el_val_t  sleep_ms(el_val_t ms);
+el_val_t  time_format(el_val_t ts, el_val_t fmt);
+el_val_t  time_to_parts(el_val_t ts);
+el_val_t  time_from_parts(el_val_t secs, el_val_t ns, el_val_t tz);
+el_val_t  time_add(el_val_t ts, el_val_t n, el_val_t unit);
+el_val_t  time_diff(el_val_t ts1, el_val_t ts2, el_val_t unit);
+
+/* ── Instant + Duration: first-class temporal types ──────────────────────────
+ * Both types share the el_val_t (int64) slot. Instants are nanoseconds
+ * since the Unix epoch; Durations are signed nanoseconds. Type discipline
+ * is enforced at codegen-time: BinOps on names registered as Instant or
+ * Duration route through the typed wrappers below; mismatches like
+ * Instant+Instant become #error at the C compiler.
+ *
+ * Postfix literals — `30.seconds`, `1.hour`, `500.millis`, `30.nanos` — are
+ * recognised by the parser as DurationLit AST nodes and lowered to literal
+ * int64 nanoseconds at codegen time. The runtime never sees the units. */
+
+el_val_t  el_now_instant(void);
+el_val_t  now(void);
+el_val_t  unix_seconds(el_val_t n);
+el_val_t  unix_millis(el_val_t n);
+el_val_t  instant_from_iso8601(el_val_t s);
+
+el_val_t  el_duration_from_nanos(el_val_t ns);
+el_val_t  duration_seconds(el_val_t n);
+el_val_t  duration_millis(el_val_t n);
+el_val_t  duration_nanos(el_val_t n);
+
+el_val_t  el_instant_add_dur(el_val_t inst, el_val_t dur);
+el_val_t  el_instant_sub_dur(el_val_t inst, el_val_t dur);
+el_val_t  el_instant_diff(el_val_t a, el_val_t b);
+el_val_t  el_duration_add(el_val_t a, el_val_t b);
+el_val_t  el_duration_sub(el_val_t a, el_val_t b);
+el_val_t  el_duration_scale(el_val_t dur, el_val_t scalar);
+el_val_t  el_duration_div(el_val_t dur, el_val_t scalar);
+
+el_val_t  el_instant_lt(el_val_t a, el_val_t b);
+el_val_t  el_instant_le(el_val_t a, el_val_t b);
+el_val_t  el_instant_gt(el_val_t a, el_val_t b);
+el_val_t  el_instant_ge(el_val_t a, el_val_t b);
+el_val_t  el_instant_eq(el_val_t a, el_val_t b);
+el_val_t  el_instant_ne(el_val_t a, el_val_t b);
+el_val_t  el_duration_lt(el_val_t a, el_val_t b);
+el_val_t  el_duration_le(el_val_t a, el_val_t b);
+el_val_t  el_duration_gt(el_val_t a, el_val_t b);
+el_val_t  el_duration_ge(el_val_t a, el_val_t b);
+el_val_t  el_duration_eq(el_val_t a, el_val_t b);
+el_val_t  el_duration_ne(el_val_t a, el_val_t b);
+
+el_val_t  instant_to_unix_seconds(el_val_t i);
+el_val_t  instant_to_unix_millis(el_val_t i);
+el_val_t  instant_to_iso8601(el_val_t i);
+el_val_t  duration_to_seconds(el_val_t d);
+el_val_t  duration_to_millis(el_val_t d);
+el_val_t  duration_to_nanos(el_val_t d);
+
+el_val_t  el_sleep_duration(el_val_t dur);
+el_val_t  unix_timestamp(void);
+
+el_val_t  ttl_cache_set(el_val_t key, el_val_t value);
+el_val_t  ttl_cache_get(el_val_t key, el_val_t max_age);
+el_val_t  ttl_cache_age(el_val_t key);
+
+/* ── Calendar + CalendarTime + Rhythm + LocalDate/Time/DateTime ─────────────
+ * Phase 1.5 of the time system. Calendar is pluggable: EarthCalendar (IANA
+ * zones, Gregorian, DST) is the user-facing default; MarsCalendar,
+ * CycleCalendar(period), NoCycleCalendar, RelativeCalendar handle non-Earth
+ * domains.
+ *
+ * A Calendar interprets an Instant under a particular cycle convention and
+ * produces a CalendarTime. CalendarTime carries the underlying Instant and
+ * a back-pointer to its Calendar; arithmetic and formatting consult the
+ * Calendar to convert ns since epoch into year/month/day/hour/minute/second
+ * (or sol/phase, or cycle/phase, depending on kind).
+ *
+ * Storage convention: Calendar / CalendarTime / Rhythm / LocalDate /
+ * LocalDateTime are heap-allocated structs whose pointers are cast into
+ * el_val_t. A 24-bit magic header at offset 0 lets the runtime identify
+ * the kind safely. LocalTime is small enough to live in the int64 slot
+ * directly (nanos since midnight, signed).                                  */
+
+/* Zone — opaque IANA zone or fixed offset, used by EarthCalendar.
+ * `zone_id` is either an IANA name ("America/New_York", "UTC") or a fixed
+ * offset string ("+05:30", "-08:00"). The runtime resolves it via tzset()
+ * on first use of the owning EarthCalendar.                                  */
+el_val_t  zone(el_val_t id);
+el_val_t  zone_utc(void);
+el_val_t  zone_local(void);
+el_val_t  zone_offset(el_val_t hours, el_val_t minutes);
+
+/* Calendar constructors. Each returns an el_val_t pointer to a heap-
+ * allocated, magic-tagged Calendar struct. Calendars are interned by
+ * (kind, zone_id, period_ns, epoch_ns) so identical constructors return
+ * the same pointer — equality is reference equality.                        */
+el_val_t  earth_calendar(el_val_t z);
+el_val_t  earth_calendar_default(void);
+el_val_t  mars_calendar(void);
+el_val_t  cycle_calendar(el_val_t period_dur);
+el_val_t  no_cycle_calendar(void);
+el_val_t  relative_calendar(el_val_t epoch_inst);
+
+/* CalendarTime constructors and methods. Returns a heap-allocated struct
+ * whose pointer fits in el_val_t. */
+el_val_t  now_in(el_val_t cal);
+el_val_t  in_calendar(el_val_t inst, el_val_t cal);
+el_val_t  cal_format(el_val_t ct, el_val_t pattern);
+el_val_t  cal_to_instant(el_val_t ct);
+el_val_t  cal_cycle_phase(el_val_t ct);
+el_val_t  cal_in(el_val_t ct, el_val_t cal);
+
+/* LocalDate / LocalTime / LocalDateTime — calendar-agnostic value types.
+ * LocalTime carries nanoseconds since midnight as a signed int64 directly
+ * in the el_val_t slot (no allocation). LocalDate / LocalDateTime are
+ * heap-allocated structs with magic headers. */
+el_val_t  local_date(el_val_t y, el_val_t m, el_val_t d);
+el_val_t  local_time(el_val_t h, el_val_t m, el_val_t s, el_val_t ns);
+el_val_t  local_datetime(el_val_t date, el_val_t time);
+el_val_t  zoned(el_val_t date, el_val_t time, el_val_t cal);
+
+el_val_t  local_date_year(el_val_t ld);
+el_val_t  local_date_month(el_val_t ld);
+el_val_t  local_date_day(el_val_t ld);
+el_val_t  local_time_hour(el_val_t lt);
+el_val_t  local_time_minute(el_val_t lt);
+el_val_t  local_time_second(el_val_t lt);
+el_val_t  local_time_nanos(el_val_t lt);
+
+el_val_t  el_local_date_add_dur(el_val_t ld, el_val_t dur);
+el_val_t  el_local_time_add_dur(el_val_t lt, el_val_t dur);
+el_val_t  el_local_date_lt(el_val_t a, el_val_t b);
+el_val_t  el_local_date_eq(el_val_t a, el_val_t b);
+
+/* Rhythm — pluggable recurrence AST. Returns a heap-allocated struct
+ * pointer in el_val_t; rhythms are immutable so callers may share them. */
+el_val_t  rhythm_cycle_start(void);
+el_val_t  rhythm_cycle_phase(el_val_t phase);
+el_val_t  rhythm_duration(el_val_t d);
+el_val_t  rhythm_session_start(void);
+el_val_t  rhythm_event(el_val_t name);
+el_val_t  rhythm_and(el_val_t a, el_val_t b);
+el_val_t  rhythm_or(el_val_t a, el_val_t b);
+el_val_t  rhythm_weekday(el_val_t day);
+el_val_t  rhythm_weekly_at(el_val_t day, el_val_t hour, el_val_t minute);
+el_val_t  rhythm_next_after(el_val_t r, el_val_t after, el_val_t cal);
+el_val_t  rhythm_matches(el_val_t r, el_val_t ct);
+
+/* ── UUID ────────────────────────────────────────────────────────────────── */
+
+el_val_t  uuid_new(void);
+el_val_t  uuid_v4(void);
+
+/* ── Environment ─────────────────────────────────────────────────────────── */
+
+el_val_t  env(el_val_t key);
+
+/* ── In-process state K/V ────────────────────────────────────────────────── */
+
+el_val_t  state_set(el_val_t key, el_val_t value);
+el_val_t  state_get(el_val_t key);
+el_val_t  state_del(el_val_t key);
+el_val_t  state_keys(void);
+
+/* ── Float formatting ────────────────────────────────────────────────────── */
+
+el_val_t  float_to_str(el_val_t f);
+el_val_t  int_to_float(el_val_t n);
+el_val_t  float_to_int(el_val_t f);
+el_val_t  format_float(el_val_t f, el_val_t decimals);
+el_val_t  decimal_round(el_val_t f, el_val_t decimals);
+el_val_t  str_to_float(el_val_t s);
+
+/* ── Math (Float-aware) ──────────────────────────────────────────────────── */
+
+el_val_t  math_sqrt(el_val_t f);
+el_val_t  math_log(el_val_t f);
+el_val_t  math_ln(el_val_t f);
+el_val_t  math_sin(el_val_t f);
+el_val_t  math_cos(el_val_t f);
+el_val_t  math_pi(void);
+
+/* ── String additions ────────────────────────────────────────────────────── */
+
+el_val_t  str_index_of(el_val_t s, el_val_t sub);
+el_val_t  str_split(el_val_t s, el_val_t sep);
+el_val_t  str_char_at(el_val_t s, el_val_t i);
+el_val_t  str_char_code(el_val_t s, el_val_t i);
+el_val_t  str_pad_left(el_val_t s, el_val_t width, el_val_t pad);
+el_val_t  str_pad_right(el_val_t s, el_val_t width, el_val_t pad);
+el_val_t  str_format(el_val_t fmt, el_val_t data);
+el_val_t  str_lower(el_val_t s);
+el_val_t  str_upper(el_val_t s);
+
+/* ── Text-processing primitives (Phase 1: byte/codepoint, ASCII char classes)
+ * Phase 2 (filed): Unicode-grapheme awareness, NFC/NFD normalization, regex.
+ * is_* predicates: empty input returns false; multi-char requires ALL bytes
+ * to match. ASCII ranges only in Phase 1. */
+
+/* Counting */
+el_val_t  str_count(el_val_t s, el_val_t sub);              /* non-overlapping */
+el_val_t  str_count_chars(el_val_t s);                      /* codepoint count */
+el_val_t  str_count_bytes(el_val_t s);                      /* alias of str_len */
+el_val_t  str_count_lines(el_val_t s);
+el_val_t  str_count_words(el_val_t s);
+el_val_t  str_count_letters(el_val_t s);                    /* ASCII [A-Za-z] */
+el_val_t  str_count_digits(el_val_t s);                     /* ASCII [0-9] */
+
+/* Find / position */
+el_val_t  str_index_of_all(el_val_t s, el_val_t sub);       /* [Int] of byte offsets */
+el_val_t  str_last_index_of(el_val_t s, el_val_t sub);
+el_val_t  str_find_chars(el_val_t s, el_val_t any_of);      /* first idx of any ch */
+
+/* Transform */
+el_val_t  str_repeat(el_val_t s, el_val_t n);
+el_val_t  str_reverse(el_val_t s);                          /* by codepoint */
+el_val_t  str_strip_prefix(el_val_t s, el_val_t prefix);
+el_val_t  str_strip_suffix(el_val_t s, el_val_t suffix);
+el_val_t  str_strip_chars(el_val_t s, el_val_t chars);
+el_val_t  str_lstrip(el_val_t s);
+el_val_t  str_rstrip(el_val_t s);
+
+/* Char classification (Bool) */
+el_val_t  is_letter(el_val_t s);
+el_val_t  is_digit(el_val_t s);
+el_val_t  is_alphanumeric(el_val_t s);
+el_val_t  is_whitespace(el_val_t s);
+el_val_t  is_punctuation(el_val_t s);
+el_val_t  is_uppercase(el_val_t s);
+el_val_t  is_lowercase(el_val_t s);
+
+/* Split / join */
+el_val_t  str_split_lines(el_val_t s);
+el_val_t  str_split_chars(el_val_t s);                      /* alias of native_string_chars */
+el_val_t  str_split_n(el_val_t s, el_val_t sep, el_val_t n);
+el_val_t  str_join(el_val_t list, el_val_t sep);            /* alias of list_join */
+
+/* ── List additions ──────────────────────────────────────────────────────── */
+
+el_val_t  list_push(el_val_t list, el_val_t elem);
+el_val_t  list_push_front(el_val_t list, el_val_t elem);
+el_val_t  list_join(el_val_t list, el_val_t sep);
+el_val_t  list_range(el_val_t start, el_val_t end);
+
+/* ── Bool helpers ────────────────────────────────────────────────────────── */
+
+el_val_t  bool_to_str(el_val_t b);
+
+/* ── Numeric parsing ─────────────────────────────────────────────────────── */
+
+el_val_t  parse_int(el_val_t s, el_val_t default_val);
+
+/* ── Process ─────────────────────────────────────────────────────────────── */
+
+void      exit_program(el_val_t code);
+el_val_t  getpid_now(void);
+
+/* ── CGI identity ─────────────────────────────────────────────────────────────
+ * Called at the start of main() in CGI programs (those with a `cgi {}` block).
+ * Records the program's DHARMA identity before any other code executes.      */
+
+void      el_cgi_init(el_val_t name, el_val_t dharma_id, el_val_t principal,
+                      el_val_t network, el_val_t engram);
+
+/* ── DHARMA network builtins ─────────────────────────────────────────────────
+ * Available to CGI programs (declared with a `cgi {}` block).
+ *
+ * Peers are addressed by `dharma_id` of the form
+ *     "<registry-id>@<transport-url>"   e.g. "ntn-genesis@http://localhost:7770"
+ * If the @<url> portion is omitted, transport defaults to
+ * "http://localhost:7770" (the local CGI daemon assumption).
+ *
+ * Wire protocol (all peers expose):
+ *   POST <url>/dharma/recv      { channel, from, content } → response body
+ *   POST <url>/dharma/event     { type, payload, source, timestamp }
+ *   POST <url>/api/activate     { query }                 → list of nodes
+ *
+ * Hosting application's responsibility: an El program with a `cgi {}` block
+ * runs http_serve() with its own request handler; that handler should route
+ * "/dharma/event" requests by calling el_runtime_dharma_event_arrive() so
+ * incoming events feed dharma_field() queues. The runtime itself does not
+ * intercept any /dharma path.                                                */
+
+el_val_t  dharma_connect(el_val_t cgi_id);
+el_val_t  dharma_send(el_val_t channel, el_val_t content);
+el_val_t  dharma_activate(el_val_t query);
+void      dharma_emit(el_val_t event_type, el_val_t payload);
+el_val_t  dharma_field(el_val_t event_type);
+void      dharma_strengthen(el_val_t cgi_id, el_val_t weight);
+el_val_t  dharma_relationship(el_val_t cgi_id);
+el_val_t  dharma_peers(void);
+
+/* Public C API: called by an El program's HTTP handler when a /dharma/event
+ * request arrives. Pushes onto the per-event-type queue and signals any
+ * pending dharma_field() blockers. All three arguments must be NUL-terminated
+ * C strings (or NULL — then treated as empty).                               */
+void      el_runtime_dharma_event_arrive(const char* event_type,
+                                         const char* payload,
+                                         const char* source);
+
+/* ── Engram local graph primitives ───────────────────────────────────────────
+ * Operate on the CGI's local Engram knowledge graph.
+ * `engram_activate` queries the local graph only; `dharma_activate` is
+ * network-wide across all connected CGI graphs.                              */
+
+el_val_t  engram_node(el_val_t content, el_val_t node_type, el_val_t salience);
+el_val_t  engram_node_full(el_val_t content, el_val_t node_type, el_val_t label,
+                           el_val_t salience, el_val_t importance, el_val_t confidence,
+                           el_val_t tier, el_val_t tags);
+/* Layered consciousness — see el_runtime.c for the layered architecture
+ * design notes (search "Layered consciousness architecture"). The five
+ * canonical layers (safety / core-identity / domain-knowledge / imprint /
+ * suit) are seeded automatically; engram_add_layer extends the registry
+ * with imprint or suit overlays at runtime. Nodes default to layer 1
+ * (core-identity) when created via engram_node / engram_node_full. */
+el_val_t  engram_node_layered(el_val_t content, el_val_t node_type, el_val_t label,
+                              el_val_t salience, el_val_t certainty, el_val_t confidence,
+                              el_val_t status, el_val_t tags, el_val_t layer_id);
+el_val_t  engram_add_layer(el_val_t name, el_val_t priority, el_val_t suppressible,
+                           el_val_t transparent, el_val_t injectable);
+el_val_t  engram_remove_layer(el_val_t layer_id);
+el_val_t  engram_list_layers(void);
+el_val_t  engram_get_node(el_val_t id);
+void      engram_strengthen(el_val_t node_id);
+void      engram_forget(el_val_t node_id);
+el_val_t  engram_node_count(void);
+el_val_t  engram_search(el_val_t query, el_val_t limit);
+el_val_t  engram_scan_nodes(el_val_t limit, el_val_t offset);
+void      engram_connect(el_val_t from_id, el_val_t to_id, el_val_t weight, el_val_t relation);
+el_val_t  engram_edge_between(el_val_t from_id, el_val_t to_id);
+el_val_t  engram_neighbors(el_val_t node_id);
+el_val_t  engram_neighbors_filtered(el_val_t node_id, el_val_t max_depth, el_val_t direction);
+el_val_t  engram_edge_count(void);
+/* Three-pass activation: background fan-out → working-memory promotion →
+ * Layer 0 override. See "Three-pass activation" in el_runtime.c. */
+el_val_t  engram_activate(el_val_t query, el_val_t depth);
+el_val_t  engram_save(el_val_t path);
+el_val_t  engram_load(el_val_t path);
+
+/* JSON-string accessors — return pre-serialized JSON so HTTP handlers
+ * can pass results straight through without round-tripping ElList/ElMap
+ * through json_stringify. */
+el_val_t  engram_get_node_json(el_val_t id);
+el_val_t  engram_search_json(el_val_t query, el_val_t limit);
+el_val_t  engram_scan_nodes_json(el_val_t limit, el_val_t offset);
+el_val_t  engram_scan_nodes_by_type_json(el_val_t node_type, el_val_t limit, el_val_t offset);
+el_val_t  engram_neighbors_json(el_val_t node_id, el_val_t max_depth, el_val_t direction);
+el_val_t  engram_activate_json(el_val_t query, el_val_t depth);
+el_val_t  engram_stats_json(void);
+el_val_t  engram_list_layers_json(void);
+/* engram_compile_layered_json — produce a prompt-ready text block split
+ * into "[LAYER 0 — STRUCTURAL]" (non-suppressible layers, sacred fire)
+ * and "[ENGRAM CONTEXT]" (standard suppressible layers). Returns "" if
+ * no nodes promoted to working memory. */
+el_val_t  engram_compile_layered_json(el_val_t intent, el_val_t depth);
+
+/* ── LLM (Anthropic API client) ─────────────────────────────────────────────
+ * All functions call https://api.anthropic.com/v1/messages with the API key
+ * from env ANTHROPIC_API_KEY. Default model when empty: claude-sonnet-4-5. */
+
+el_val_t  llm_call(el_val_t model, el_val_t prompt);
+el_val_t  llm_call_system(el_val_t model, el_val_t system_prompt, el_val_t user_prompt);
+el_val_t  llm_call_agentic(el_val_t model, el_val_t system, el_val_t user, el_val_t tools);
+el_val_t  llm_vision(el_val_t model, el_val_t system, el_val_t prompt, el_val_t image_url_or_b64);
+el_val_t  llm_models(void);
+
+/* Register a tool handler by name. The handler is looked up via dlsym
+ * (mirroring http_set_handler), so any El `fn <name>(input)` compiles to
+ * a global C symbol that this function can locate at runtime.
+ * Handler signature: `el_val_t handler(el_val_t input_json)` — receives
+ * the tool input as a JSON-string el_val_t and returns a JSON-string
+ * el_val_t result. Used by llm_call_agentic.                                 */
+void      llm_register_tool(el_val_t name, el_val_t handler_fn_name);
+
+/* ── args() ─────────────────────────────────────────────────────────────────
+ * Provides access to command-line arguments passed to the program.
+ * Populated by el_runtime_init_args() before main() runs.           */
+
+el_val_t  args(void);
+void      el_runtime_init_args(int argc, char** argv);
+
+/* ── Crypto primitives ─────────────────────────────────────────────────────
+ * SHA-256, HMAC-SHA-256, and base64 (standard + URL-safe).
+ * Self-contained — no OpenSSL/libcrypto dependency. The implementations are
+ * adapted from public-domain reference code (Brad Conte / RFC 4648).
+ *
+ * Bytes-returning variants (sha256_bytes, hmac_sha256_bytes) return a string
+ * value whose contents are raw binary; callers usually feed these into
+ * base64_encode. Note that el_val_t strings are NUL-terminated by convention,
+ * so the binary payload may contain embedded NULs — pass it directly into
+ * base64_encode (which uses an explicit length) rather than treating it as
+ * a printable C string.
+ *
+ * The "base64" variants emit/accept RFC 4648 standard alphabet with padding.
+ * The "base64url" variants use URL-safe alphabet (`-`/`_`) with no padding,
+ * as used in JWTs.                                                           */
+
+el_val_t  sha256_hex(el_val_t input);
+el_val_t  sha256_bytes(el_val_t input);
+el_val_t  hmac_sha256_hex(el_val_t key, el_val_t message);
+el_val_t  hmac_sha256_bytes(el_val_t key, el_val_t message);
+el_val_t  base64_encode(el_val_t input);
+el_val_t  base64_decode(el_val_t input);
+el_val_t  base64url_encode(el_val_t input);
+el_val_t  base64url_decode(el_val_t input);
+
+/* Length-aware variants (internal — exposed for the rare caller that already
+ * has a known-length binary buffer and doesn't want to round-trip through
+ * a NUL-terminated el_val_t string). Sha256_bytes and hmac_sha256_bytes feed
+ * these implicitly. */
+el_val_t  el_sha256_bytes_n(const unsigned char* data, size_t len);
+el_val_t  el_base64_encode_n(const unsigned char* data, size_t len, int url_safe);
+
+/* ── Post-quantum primitives (liboqs-backed) ────────────────────────────────
+ * All inputs/outputs hex-encoded. Algorithm choices:
+ *   Signature: CRYSTALS-Dilithium-3   (NIST level 3, balanced)
+ *   KEM:       CRYSTALS-Kyber-768     (NIST level 3)
+ *   Hash:      SHA3-256 (Keccak)      (PQ-aware protocols favour SHA3 over SHA2)
+ *
+ * If liboqs is not linked (detected via __has_include(<oqs/oqs.h>) at compile
+ * time), the pq_* entry points return a JSON-shaped error string so callers
+ * fail loudly rather than silently fall back to classical schemes:
+ *   {"error":"liboqs not linked, post-quantum primitives unavailable"}
+ *
+ * The hybrid handshake pairs X25519 with Kyber-768 per NIST PQ guidance and
+ * CNSA 2.0. Combined shared secret is HKDF-SHA256(x25519_ss || kyber_ss).
+ * Even if Kyber falls, X25519 holds; if X25519 falls under quantum attack,
+ * Kyber holds. SHA3-256 also remains usable independent of liboqs (the
+ * Keccak permutation is PQ-OK as a primitive). */
+
+el_val_t  pq_keygen_signature(void);
+el_val_t  pq_sign(el_val_t secret_key_hex, el_val_t message);
+el_val_t  pq_verify(el_val_t public_key_hex, el_val_t message, el_val_t signature_hex);
+
+el_val_t  pq_kem_keygen(void);
+el_val_t  pq_kem_encaps(el_val_t public_key_hex);
+el_val_t  pq_kem_decaps(el_val_t secret_key_hex, el_val_t ciphertext_hex);
+
+el_val_t  pq_hybrid_keygen(void);
+el_val_t  pq_hybrid_handshake(el_val_t remote_pub_combined);
+
+el_val_t  sha3_256_hex(el_val_t input);
+
+/* ── AEAD: AES-256-GCM (libcrypto-backed) ───────────────────────────────────
+ * Symmetric authenticated encryption used to wrap envelopes after a KEM
+ * handshake. Caller MUST supply a 32-byte key (64 hex chars) — typically the
+ * Kyber-768 / hybrid shared_secret, optionally normalized via SHA3-256.
+ *
+ * aead_encrypt returns a JSON map {"nonce":"...","ciphertext":"..."} where
+ * ciphertext is the AES-256-GCM output with the 16-byte auth tag appended.
+ * Nonce is a fresh 12-byte CSPRNG draw — callers never pick the nonce, which
+ * structurally rules out the GCM nonce-reuse footgun.
+ *
+ * aead_decrypt returns the plaintext String, or "" on any failure (including
+ * auth-tag mismatch). Callers MUST check for "" before trusting the result. */
+el_val_t  aead_encrypt(el_val_t key_hex, el_val_t plaintext);
+el_val_t  aead_decrypt(el_val_t key_hex, el_val_t nonce_hex, el_val_t ciphertext_hex);
+
+/* ── Native VM builtin aliases (for compiled El source) ─────────────────────
+ * These match the El VM's native_* builtins so that El source compiled
+ * to C can call the same names without modification.                */
+
+el_val_t  native_list_get(el_val_t list, el_val_t index);
+el_val_t  native_list_len(el_val_t list);
+el_val_t  native_list_append(el_val_t list, el_val_t elem);
+el_val_t  native_list_empty(void);
+el_val_t  native_list_clone(el_val_t list);
+el_val_t  native_string_chars(el_val_t s);
+el_val_t  native_int_to_str(el_val_t n);
+
+/* ── Method-call shorthand aliases ──────────────────────────────────────────
+ * The El method-call convention `obj.method(args)` compiles to
+ * `method(obj, args)`.  These aliases expose the runtime functions under
+ * the short names that result from method calls in El source.
+ *
+ * Example: `myList.append(x)` → `append(myList, x)` (calls this alias)
+ *          `myList.len()`     → `len(myList)`         (calls this alias)  */
+
+el_val_t  append(el_val_t list, el_val_t elem);   /* el_list_append */
+el_val_t  len(el_val_t list);                      /* el_list_len    */
+el_val_t  get(el_val_t list, el_val_t index);      /* el_list_get    */
+el_val_t  map_get(el_val_t map, el_val_t key);     /* el_map_get     */
+el_val_t  map_set(el_val_t map, el_val_t key, el_val_t value); /* el_map_set */
+
+/* ── OTLP/HTTP Observability ─────────────────────────────────────────────── */
+/* See bottom of el_runtime.c for the implementation.
+ * Configured by env vars OTLP_ENDPOINT, OTEL_SERVICE_NAME, OTEL_SERVICE_VERSION.
+ * No-op when OTLP_ENDPOINT is unset. Drop-on-failure semantics. */
+/* ── Subprocess execution ────────────────────────────────────────────────── */
+el_val_t exec_command(el_val_t cmd);   /* run shell command, return exit code */
+el_val_t exec_capture(el_val_t cmd);   /* run shell command, capture stdout   */
+el_val_t exec(el_val_t cmd);           /* exec(cmd) → stdout String (30s timeout) */
+el_val_t exec_bg(el_val_t cmd);        /* exec_bg(cmd) → PID String (non-blocking) */
+
+el_val_t emit_log(el_val_t level, el_val_t msg, el_val_t fields_json);
+el_val_t emit_metric(el_val_t name, el_val_t value, el_val_t tags_json);
+el_val_t trace_span_start(el_val_t name);
+el_val_t trace_span_end(el_val_t span_handle);
+el_val_t emit_event(el_val_t name, el_val_t duration_ms);
+
+#ifdef __cplusplus
+}
+#endif

lang/el-compiler/src/codegen-js.el

@@ -1202,7 +1202,7 @@ fn codegen_js_inner(stmts: [Map<String, Any>], source: String, bundle_mode: Bool
         js_emit_line(js_strip_es_exports(runtime_content))
         js_emit_line("")
     } else {
-        js_emit_line("// Runtime: foundation/el/runtime/el_runtime.js")
+        js_emit_line("// Runtime: foundation/el/el-compiler/runtime/el_runtime.js")
         js_emit_line("import \"./el_runtime.js\";")
     }
     // In module mode: destructure all builtins off globalThis.__el so call

lang/elb.el

@@ -368,13 +368,13 @@ fn main() -> Void {
         let which_out: String = str_trim(exec_capture("which " + elc_bin + " 2>/dev/null"))
         if !str_eq(which_out, "") {
             let elc_dir: String = dirname_of(which_out)
-            runtime_path = elc_dir + "/../runtime/el_runtime.c"
+            runtime_path = elc_dir + "/../el-compiler/runtime/el_runtime.c"
         }
     }
     // If --runtime points to a directory, auto-locate el_runtime.c inside it.
     // This lets both forms work:
-    //   --runtime=/opt/el/runtime          (directory form)
-    //   --runtime=/opt/el/runtime/el_runtime.c  (file form)
+    //   --runtime=/opt/el/el-compiler/runtime          (directory form)
+    //   --runtime=/opt/el/el-compiler/runtime/el_runtime.c  (file form)
     if !str_eq(runtime_path, "") {
         let is_dir: String = str_trim(exec_capture("test -d " + runtime_path + " && echo dir || echo file"))
         if str_eq(is_dir, "dir") {

lang/examples/html-page.el

@@ -6,8 +6,8 @@
 //
 // Compile and run:
 //   ./dist/platform/elc examples/html-page.el > /tmp/html-page.c
-//   cc -std=c11 -I runtime -lcurl -lpthread \
-//      -o /tmp/html-page /tmp/html-page.c runtime/el_runtime.c
+//   cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
+//      -o /tmp/html-page /tmp/html-page.c el-compiler/runtime/el_runtime.c
 //   /tmp/html-page
 
 fn render_item(item: String) -> String {

lang/releases/v1.0.0-20260501/RELEASE.md

@@ -0,0 +1,28 @@
+# El Compiler Release v1.0.0 — 2026-05-02
+
+## Components
+- `bootstrap.py` — El language compiler (Python, recursive descent parser, emits C)
+- `el_runtime.c` — El runtime (C, HTTP server, engram, DHARMA, LLM chain)
+- `el_runtime.h` — Runtime public API header
+
+## Changes in this release
+
+### Critical bug fixes
+- `state_set`/`state_get` are now thread-safe (pthread_mutex). Was racing across 64 worker threads.
+- `looks_like_string` threshold raised from 1,000,000 to 4GB. Unix timestamps were being dereferenced as heap pointers.
+- `fs_read` guards against negative `ftell` result (pipe/special file overflow).
+
+### Engram architecture (major)
+- Two-layer activation: `background_activation` (Layer 1, broad fan-out) + `working_memory_weight` (Layer 2, executive filter)
+- Inhibitory edges: `EngramEdge.inhibitory` flag suppresses working memory promotion without affecting background activation
+- Suppression memory: `suppression_count` — nodes activated-but-suppressed accumulate pressure toward breakthrough
+- Temporal decay: `temporal_decay_rate`, `created_at`, `last_activated_at`, `activation_count` on EngramNode
+- Per-type activation thresholds (Safety: 0.05, Canonical: 0.15, Lesson: 0.25, Note: 0.40)
+- Temporal range query: `engram_query_range(start_ms, end_ms)`
+- Layered consciousness: `EngramLayer` struct, `layer_id` on nodes and edges, `EngramStore.layers[]`
+- Layer 0 override pass: safety layer fires last and cannot be suppressed
+
+## SHA256
+bootstrap.py
+el_runtime.c
+el_runtime.h

lang/releases/v1.0.0-20260501/el_runtime.h

@@ -34,12 +34,12 @@
  *                pq_hybrid_* and HKDF-SHA256 derivation.
  *
  * Canonical compile command:
- *   cc -std=c11 -I runtime -lcurl -lpthread \
- *      -o <out> <prog>.c runtime/el_runtime.c
+ *   cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
+ *      -o <out> <prog>.c el-compiler/runtime/el_runtime.c
  *
  * With liboqs (post-quantum stack):
- *   cc -std=c11 -I runtime -lcurl -lpthread -loqs -lcrypto \
- *      -o <out> <prog>.c runtime/el_runtime.c
+ *   cc -std=c11 -I el-compiler/runtime -lcurl -lpthread -loqs -lcrypto \
+ *      -o <out> <prog>.c el-compiler/runtime/el_runtime.c
  */
 
 #pragma once
@@ -628,30 +628,22 @@ el_val_t  engram_hebb_drain_json(el_val_t max);
 /* Document frequency of a term across node labels — term-specificity signal
  * for curiosity seed selection. (2026-08-03 self-review.) */
 el_val_t  engram_label_df(el_val_t term);
+/* Best curiosity seed from one node: argmax over idf·position·casing across
+ * the candidate tokens of its label, falling back to its content when the
+ * label is a sentinel. Excludes pipe-delimited tabu terms during selection
+ * and gates candidates to the df band [min_df, max_df]. Returns "" when
+ * nothing qualifies. (2026-08-13 self-review.) */
+el_val_t  engram_salient_term(el_val_t node_id, el_val_t max_df,
+                              el_val_t min_df, el_val_t tabu);
 el_val_t  engram_embed_backfill(el_val_t count);
 el_val_t  engram_list_layers_json(void);
 /* Working memory introspection — count, mean weight, and top-N snapshot.
- * Ported from runtime on 2026-06-30 self-review. */
+ * Ported from el-compiler/runtime on 2026-06-30 self-review. */
 el_val_t  engram_wm_count(void);
 el_val_t  engram_wm_avg_weight(void);
 el_val_t  engram_wm_top_json(el_val_t n);
 /* Merge-load: add nodes/edges from a snapshot without resetting the store. */
 el_val_t  engram_load_merge(el_val_t path);
-
-/* ── WAL + compaction + integrity (ENGRAM_WAL=on; design doc §§3-14,§18) ──── */
-int       engram_wal_enabled(void);
-el_val_t  engram_crc32(el_val_t s);
-el_val_t  engram_wal_boot(el_val_t dir);          /* replay + open; returns records */
-el_val_t  engram_wal_open_dir(el_val_t dir);
-el_val_t  engram_wal_node_put(el_val_t dir, el_val_t id);
-el_val_t  engram_wal_edges_since(el_val_t dir, el_val_t start_count);
-el_val_t  engram_wal_hebb_batch(el_val_t dir, el_val_t start_count);
-el_val_t  engram_wal_forget(el_val_t dir, el_val_t id);
-el_val_t  engram_wal_compact(el_val_t dir);
-el_val_t  engram_wal_maybe_compact(el_val_t dir);
-el_val_t  engram_resolve_data_dir(void);          /* §18.2 fail-loud default */
-el_val_t  engram_is_protected(el_val_t id);       /* §18.1/18.3 derived set */
-el_val_t  engram_protected_json(void);
 /* engram_compile_layered_json — produce a prompt-ready text block split
  * into "[LAYER 0 — STRUCTURAL]" (non-suppressible layers, sacred fire)
  * and "[ENGRAM CONTEXT]" (standard suppressible layers). Returns "" if

lang/runtime/json.el

@@ -2,7 +2,7 @@
 //
 // Thin El wrappers over seed JSON primitives, plus pure-El builders and
 // helpers.  Each function here corresponds to (and replaces) a C function
-// from runtime/el_runtime.c (lines 2692–3333).
+// from el-compiler/runtime/legacy/el_runtime.c (lines 2692–3333).
 //
 // Seed primitives consumed by this module:
 //   __json_get(json, key)              -> String   (value as string)

lang/runtime/manifest.el

@@ -25,8 +25,8 @@
 //       runtime/collections.el \
 //       <user-program.el> > combined.el
 //   ./dist/platform/elc combined.el > output.c
-//   cc -std=c11 -I runtime -lcurl -lpthread \
-//      -o output output.c runtime/el_seed.c
+//   cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
+//      -o output output.c el-compiler/runtime/el_seed.c
 
 // This file itself is not compiled — it is documentation only.
 fn runtime_version() -> String {

lang/runtime/math.el

@@ -1,6 +1,6 @@
 // runtime/math.el — Float math, integer utilities, and numeric conversions.
 //
-// Implements the math/float surface from runtime/el_runtime.c
+// Implements the math/float surface from el-compiler/runtime/legacy/el_runtime.c
 // (lines 303–305 for el_abs/max/min, lines 4725–4771 for float/format ops)
 // in pure El, using seed primitives.
 //

lang/runtime/time.el

@@ -1,6 +1,6 @@
 // runtime/time.el — Time operations, sleep, and formatting.
 //
-// Implements the time surface from runtime/el_runtime.c
+// Implements the time surface from el-compiler/runtime/legacy/el_runtime.c
 // (lines 3334–3440, 3471–3656) in pure El, using seed primitives.
 //
 // Seed primitives consumed:

lang/tests/calendar/run.sh

@@ -11,7 +11,7 @@ cd "$(dirname "$0")"
 
 EL_HOME="${EL_HOME:-$(cd ../.. && pwd)}"
 ELC="${EL_HOME}/dist/platform/elc"
-RUNTIME_DIR="${EL_HOME}/runtime"
+RUNTIME_DIR="${EL_HOME}/el-compiler/runtime"
 
 if [ ! -x "${ELC}" ]; then
     echo "elc not found at ${ELC}" >&2

lang/tests/html_sanitizer/run.sh

@@ -10,7 +10,7 @@ cd "$(dirname "$0")"
 
 EL_HOME="${EL_HOME:-$(cd ../.. && pwd)}"
 ELC="${EL_HOME}/dist/platform/elc"
-RUNTIME_DIR="${EL_HOME}/runtime"
+RUNTIME_DIR="${EL_HOME}/el-compiler/runtime"
 
 if [ ! -x "${ELC}" ]; then
     echo "elc not found at ${ELC}" >&2

lang/tests/runtime/string_test.el

@@ -14,8 +14,8 @@
 //       tests/runtime/string_test.el > /tmp/string_test_combined.el
 //
 //   ./dist/platform/elc /tmp/string_test_combined.el > /tmp/string_test.c
-//   cc -std=c11 -I runtime -lcurl -lpthread \
-//      -o /tmp/string_test /tmp/string_test.c runtime/el_seed.c
+//   cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
+//      -o /tmp/string_test /tmp/string_test.c el-compiler/runtime/el_seed.c
 //   /tmp/string_test; echo "exit: $?"
 //
 // Exit code equals the number of failing assertions (0 = all pass).

lang/tests/text/run.sh

@@ -11,7 +11,7 @@ cd "$(dirname "$0")"
 
 EL_HOME="${EL_HOME:-$(cd ../.. && pwd)}"
 ELC="${ELC:-${EL_HOME}/dist/platform/elc}"
-RUNTIME_DIR="${EL_HOME}/runtime"
+RUNTIME_DIR="${EL_HOME}/el-compiler/runtime"
 
 if [ ! -x "${ELC}" ]; then
     echo "elc not found at ${ELC}" >&2

lang/tests/time/run.sh

@@ -16,7 +16,7 @@ cd "$(dirname "$0")"
 
 EL_HOME="${EL_HOME:-$(cd ../.. && pwd)}"
 ELC="${EL_HOME}/dist/platform/elc"
-RUNTIME_DIR="${EL_HOME}/runtime"
+RUNTIME_DIR="${EL_HOME}/el-compiler/runtime"
 
 if [ ! -x "${ELC}" ]; then
     echo "elc not found at ${ELC}" >&2

lang/tools/install.sh

@@ -44,7 +44,7 @@ INCLUDE_DIR="${PREFIX}/include"
 LIB_DIR="${PREFIX}/lib"
 
 ELC_SRC="${EL_ROOT}/dist/platform/elc"
-RUNTIME_SRC="${EL_ROOT}/runtime"
+RUNTIME_SRC="${EL_ROOT}/el-compiler/runtime"
 STDLIB_SRC="${EL_ROOT}/runtime"
 
 echo "==> Installing El framework to ${PREFIX}"

lang/tools/new-project.sh

@@ -42,7 +42,7 @@ fi
 # Discover el_runtime.c
 EL_RUNTIME=""
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-LOCAL_RUNTIME="${SCRIPT_DIR}/../runtime/el_runtime.c"
+LOCAL_RUNTIME="${SCRIPT_DIR}/../el-compiler/runtime/el_runtime.c"
 if [[ -f "${LOCAL_RUNTIME}" ]]; then
     EL_RUNTIME="$(cd "$(dirname "${LOCAL_RUNTIME}")" && pwd)/$(basename "${LOCAL_RUNTIME}")"
     EL_INCLUDE="$(dirname "${EL_RUNTIME}")"

scripts/check-single-runtime.sh

@@ -1,94 +0,0 @@
-#!/usr/bin/env bash
-# check-single-runtime.sh — CODE-VS-ARTIFACT drift guard for the el runtime.
-#
-# Enforces org policy docs/CODE-VS-ARTIFACT.md rule #1 (single source of truth):
-# there is exactly ONE authored el_runtime.c, and it lives at lang/runtime/.
-# Any other el_runtime.c in the tree is a fork (a hand-synced copy). A lagging
-# fork is exactly what shipped to prod and dropped learned `hebb` edges on
-# restart — this guard exists to make that class of bug impossible to reintroduce.
-#
-# Exemptions:
-#   * Build output — generated amalgamations under any dist/ or build/ dir are
-#     artifacts, not sources.
-#   * A small, explicit ALLOWLIST of pre-existing example-app vendored/staging
-#     copies (see below). These are KNOWN DEFERRED DEBT, tracked separately from
-#     the SDK/CI-published runtime. They do NOT ship to prod. The guard warns on
-#     them (visible, greppable) but does not fail — while HARD-FAILING on any new
-#     or non-allowlisted fork, including any return of lang/el-compiler/runtime/
-#     or a lang/releases/ vendored copy.
-#
-# Wire-in: run from the repo root in CI (see note at bottom). Exits non-zero on drift.
-set -euo pipefail
-
-ROOT="$(cd "$(dirname "$0")/.." && pwd)"
-cd "$ROOT"
-
-CANONICAL="lang/runtime/el_runtime.c"
-
-# KNOWN DEFERRED example-app forks — remove these as a follow-up, then delete
-# this allowlist. iOS + Docker copies are regenerated by their build scripts
-# (cp from lang/runtime) and can be git-rm'd now; the Android jni/ copy is a
-# committed source its CMake build depends on and needs a build-script change
-# (cp from lang/runtime) before removal. Tracked in docs/CODE-VS-ARTIFACT.md.
-ALLOWLIST=(
-  "ui/examples/native-hello-android/app/src/main/jni/el_runtime.c"
-  "ui/examples/native-hello-ios/NativeHello/el_runtime.c"
-  "ui/examples/native-hello/build-docker/runtime/el_runtime.c"
-)
-
-is_allowlisted() {
-  local p="$1"
-  for a in "${ALLOWLIST[@]}"; do [ "$p" = "$a" ] && return 0; done
-  return 1
-}
-
-if [ ! -f "$CANONICAL" ]; then
-  echo "FATAL: canonical runtime source missing: $CANONICAL" >&2
-  exit 1
-fi
-
-# All el_runtime.c files tracked by git, excluding build output (dist/ , build/)
-# and the canonical source itself.
-mapfile -t CANDIDATES < <(
-  git ls-files '*el_runtime.c' \
-    | grep -Ev '(^|/)(dist|build)/' \
-    | grep -vx "$CANONICAL" || true
-)
-
-FORKS=()
-DEFERRED=()
-for f in "${CANDIDATES[@]}"; do
-  if is_allowlisted "$f"; then DEFERRED+=("$f"); else FORKS+=("$f"); fi
-done
-
-if [ "${#DEFERRED[@]}" -gt 0 ]; then
-  echo "WARN: allowlisted (deferred) el_runtime.c forks still present — clean these up:" >&2
-  for f in "${DEFERRED[@]}"; do echo "        - $f" >&2; done
-fi
-
-if [ "${#FORKS[@]}" -gt 0 ]; then
-  echo "FATAL: el_runtime.c fork(s) detected outside the canonical location." >&2
-  echo "       Canonical (the ONLY allowed source): $CANONICAL" >&2
-  echo "       Offending copies:" >&2
-  for f in "${FORKS[@]}"; do echo "         - $f" >&2; done
-  echo "" >&2
-  echo "Consumers must build against $CANONICAL (pin by git ref where" >&2
-  echo "reproducibility matters) — never a hand-maintained copy." >&2
-  echo "See docs/CODE-VS-ARTIFACT.md." >&2
-  exit 1
-fi
-
-echo "OK: single canonical runtime source — $CANONICAL (no un-allowlisted forks)."
-
-# ---------------------------------------------------------------------------
-# CI wire-in:
-#   foundation/el .gitea/workflows/ci-dev.yaml, ci-stage.yaml, sdk-release.yaml
-#   Add an early step (before the build/publish steps). It must run from the
-#   REPO ROOT, so override the job's `defaults.run.working-directory: lang`:
-#
-#     - name: Guard - single canonical runtime source
-#       working-directory: ${{ github.workspace }}
-#       run: bash scripts/check-single-runtime.sh
-#
-#   Also add to .githooks/pre-commit so drift is caught before it is committed.
-# ---------------------------------------------------------------------------

ui/examples/native-hello-android/build.sh

@@ -18,7 +18,7 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
 EL_UI_ROOT="${SCRIPT_DIR}/../.."
-EL_RUNTIME="${EL_LANG_ROOT}/runtime"
+EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
 EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
 EL_APP_ENTRY="${EL_UI_ROOT}/examples/native-hello/src/main.el"
 EL_MANIFEST="${EL_UI_ROOT}/examples/native-hello/manifest.el"

ui/examples/native-hello-ios/build.sh

@@ -17,7 +17,7 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
 EL_UI_ROOT="${SCRIPT_DIR}/../.."
-EL_RUNTIME="${EL_LANG_ROOT}/runtime"
+EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
 EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
 EL_APP_ENTRY="${EL_UI_ROOT}/examples/native-hello/src/main.el"
 EL_MANIFEST="${EL_UI_ROOT}/examples/native-hello/manifest.el"

ui/examples/native-hello/build-gtk4.sh

@@ -24,7 +24,7 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
 EL_UI_ROOT="${SCRIPT_DIR}/../.."
-EL_RUNTIME="${EL_LANG_ROOT}/runtime"
+EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
 EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
 BUILD_DIR="${SCRIPT_DIR}/build-gtk4"
 

ui/examples/native-hello/build-sdl2.sh

@@ -23,7 +23,7 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
 EL_UI_ROOT="${SCRIPT_DIR}/../.."
-EL_RUNTIME="${EL_LANG_ROOT}/runtime"
+EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
 EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
 BUILD_DIR="${SCRIPT_DIR}/build"
 

ui/examples/native-hello/build-win32.sh

@@ -18,7 +18,7 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
 EL_UI_ROOT="${SCRIPT_DIR}/../.."
-EL_RUNTIME="${EL_LANG_ROOT}/runtime"
+EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
 EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
 BUILD_DIR="${SCRIPT_DIR}/build-win32"
 

ui/examples/native-hello/build.sh

@@ -40,7 +40,7 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
 EL_UI_ROOT="${SCRIPT_DIR}/../.."
-EL_RUNTIME="${EL_LANG_ROOT}/runtime"
+EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
 EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
 BUILD_DIR="${SCRIPT_DIR}/build"
 
@@ -193,6 +193,6 @@ run() {
 case "${1:-run}" in
     clean)     clean   ;;
     compile)   compile ;;
-    platforms) "${EL_LANG_ROOT}/runtime/detect-platforms" ;;
+    platforms) "${EL_LANG_ROOT}/el-compiler/runtime/detect-platforms" ;;
     run|*)     run     ;;
 esac

ui/examples/native-hello/docker-build-linux.sh

@@ -32,7 +32,7 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
 EL_UI_ROOT="${SCRIPT_DIR}/../.."
-EL_RUNTIME="${EL_LANG_ROOT}/runtime"
+EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
 EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
 BUILD_DIR="${SCRIPT_DIR}/build"
 DOCKER_CTX="${SCRIPT_DIR}/build-docker"