The UI needs full memory CRUD; the soul had create (handle_api_remember)
and the older /memory/forget + /memory/evolve, but no endpoints matching
the UI's delete/update contract.
POST /api/neuron/memory/delete {"id"}
Hard delete. engram_forget is a true delete primitive (removes the node
and all incident edges from the engram store), so no soft-delete
fallback is needed. Unlike /memory/forget, this checks the node exists
first - engram_forget silently no-ops on unknown ids, and a bad id must
return an error, not fake success. Protected identity/values nodes are
blocked, same as the other accumulation-path handlers.
POST /api/neuron/memory/update {"id","content"}
Evolve-style update. The engram runtime has no in-place node mutation
primitive (only node-create, strengthen, forget, connect), so update
creates a new Memory node and wires a supersedes edge to the prior one,
same pattern as handle_api_evolve_knowledge. Unlike /memory/evolve, id
is required and must reference an existing node; create+link delegates
to handle_api_evolve_memory. Returns {id, supersedes, ok}.
Both files syntax-checked with elc --target=c (exit 0, no stderr).
Compile-verified only - local builds cannot run the soul; needs Will's
build for runtime verification.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
handle_chat_agentic now always attaches Anthropic's native web_search_20250305
tool instead of gating it behind a per-request web_search flag. Web search is a
built-in capability: the model invokes it only when a query needs fresh info
(max_uses:5 caps it), so there is no user-facing toggle. The body's web_search
field is now ignored (back-compat — old UI clients sending it cause no harm).
Pairs with neuron-ui removing the chat-input web search toggle.
Note: .el change only — no elc on the authoring machine; reviewer builds/verifies.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
When a chat request carries web_search=true, handle_chat_agentic now attaches Anthropic's
NATIVE server-side web_search tool (web_search_20250305) to the request. The native tool is
executed by Anthropic (not by the soul), so it returns real results with citations and needs
no local runtime — it sidesteps the soul's lack of executable tools entirely.
- new agentic_tools_with_web(web_search) helper (appends the native tool to the standard set)
- handle_chat_agentic reads json_get_bool(body,"web_search") and uses it
Pairs with neuron-ui: ChatRequest.web_search + the chat-input Web search toggle.
Note: built/verified by reviewer — no elc on the authoring machine.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
On startup, prefer the local engram snapshot if it has >50 nodes.
HTTP Engram is only used on first boot (no snapshot yet). This means
sessions, conversation history, and in-process state survive daemon
restarts.
awareness.el: sync source with compiled binary (periodic mem_save
on heartbeat was already in the binary but not in source).
Rebuilds soul.c with the new startup logic and ships updated binary.
Call engram_wm_top_json(5) in emit_heartbeat() and embed the result as
wm_top field in the heartbeat JSON payload. Each entry carries label,
node_type, tier, and wm_weight. This closes the WM composition blindspot:
previously the heartbeat showed wm_active=670 with no breakdown of what
was in working memory. With wm_top visible, ISE-dominated WM is immediately
detectable (all entries show node_type=InternalStateEvent), as was the case
on this session's first post-restart heartbeat before the runtime fix.
Calls engram_wm_avg_weight() (new builtin) in emit_heartbeat() and appends
wm_avg_weight field to the heartbeat JSON payload. This makes activation
quality visible in the ISE stream — a heartbeat showing wm_active=2000 and
wm_avg_weight=0.075 reveals the sparse-graph problem directly (many nodes
barely clearing the threshold), vs wm_avg_weight=0.4+ which would indicate
dense, high-confidence activations.
Rebuilt dist/neuron from soul.el (which imports awareness.el). Build uses
single self-contained dist/neuron.c to avoid duplicate-symbol linker errors
from the dist/ directory containing stale soul_new.c / soul-rebuilt.c files.
Two awareness loop bugs fixed:
1. Seed rotation never worked: dist/awareness.c was compiled from stale
source (pre-fix awareness.el still had broken ts_minutes % 4). Compiled
C showed `minute_block = (ts / 60000); EL_NULL; 4;` — minute_block was
always ts_minutes (millions), never 0-3. if(minute_block==1/2/3) never
matched. Fix: recompile from current awareness.el which has the correct
modulo workaround: ts_minutes - minute_q4 (via + - / only).
2. Heartbeat/curiosity silent for 24h at 99% CPU: old design used idle-tick
counting (idle_n >= beat_interval). Failed when perceive() inbox guard
false-positives on "soul-inbox" substring matches in knowledge nodes —
did_work=true every tick, idle_n never accumulated, neither signal fired.
Fix: wall-clock elapsed time (time_now() - last_ts >= interval_ms).
Heartbeat fires regardless of load. New SOUL_HEARTBEAT_MS env var (default
60000ms) avoids the broken EL * operator. Verified: heartbeat ISEs flowing
at pulse 3 within 2 minutes of restart.
dist/awareness.c was stale — still had the broken EL % operator codegen
(minute_block = ts/60000 raw, EL_NULL; 4; as dead statements) and the
broken should_scan/should_beat logic (idle_n truthy check instead of >=).
Recompiled awareness.el to bring dist/awareness.c in sync with the source
fix committed 2026-05-25 (fb69044). The monolithic dist/neuron.c (compiled
from soul.el which imports awareness.el) was already correct from fb69044 —
only the standalone dist/awareness.c was behind.
Bug #2 (99% CPU) root cause identified: perceive() inbox guard
(engram_search_json) has false positives — knowledge nodes containing
"soul-inbox" as a substring match, causing engram_activate_json(..., hops=2)
to run on every tick on a 162K-node graph. This blocks sleep_ms and prevents
idle_n accumulation → no heartbeats. Separate fix needed.
Three bugs fixed in awareness.el:
1. EL let-rebinding inside if-blocks creates inner scope only — outer
variable unchanged after block exits. Curiosity seed terms were always
"memory/knowledge/context" regardless of minute_block. Fix: state_set
inside if-blocks, state_get after to retrieve selected values.
2. EL % operator completely broken in v1.0.0-20260501 — compiles as dead
code (left operand assigned, modulo dropped). minute_block was always
ts/60000 (a large int, never 0-3). Fix: arithmetic workaround:
x%4 = x - (q+q+q+q) where q = x/4.
3. awareness_run idle_n % beat_interval == 0 also broken by same % bug —
should_scan and should_beat fired every idle tick instead of every N
ticks. Fix: idle_n >= interval comparisons with idle_reset() after
firing, so the counter restarts cleanly after each event.
EL % and * operators filed as P1 backlog item for elc compiler fix.
Also adds minute_block field to curiosity_scan ISE for observability.
Rebuilt awareness.c and neuron.c from source using the updated elc (which now
correctly recognizes http_serve_async as a 2-arg builtin). Rebuilt the neuron
binary against the updated el_runtime.c which now sorts InternalStateEvent scans
by created_at DESC. The soul daemon now posts heartbeats that surface immediately
at offset 0 of the ISE scan, rather than being buried behind 20K older entries.
Two fixes:
1. proactive_curiosity() was calling engram_activate_json with multi-word phrases
("memory knowledge context"). engram_activate finds seeds via istr_contains
(substring match), so the phrase had to appear verbatim in a node's content.
Almost no node contains the exact string "memory knowledge context", so only
0-2 nodes activated per curiosity scan. Fixed by activating each word separately:
"memory", "knowledge", "context" → 3 independent activate calls → hundreds of
nodes promoted to WM per cycle.
2. dist/neuron.c called http_serve() (blocking accept loop) which made awareness_run()
unreachable. soul.el correctly specifies http_serve_async but elc silently drops
unknown builtins, leaving blocking http_serve in the compiled C. Patched neuron.c
to call http_serve_async directly — HTTP server runs in a background pthread,
awareness_run() runs on the main thread as intended.
engram_wm_count() exists and counts nodes with working_memory_weight > 0.
emit_heartbeat() and proactive_curiosity() were both calling
engram_node_count() (total graph size: ~17K) instead — every heartbeat
and curiosity_scan ISE had been reporting wm_active=17769 since the graph
grew past ~3K nodes, making the metric meaningless for observability.
Fix: use engram_wm_count() for the wm_active field in both ISE payloads.
EL compiles any variable named 'seed' to EL_NULL at call sites (likely
conflicts with BFS seed node terminology in the runtime builtins). Rename to
'curiosity_seed' throughout proactive_curiosity(). Also note this as a known
EL reserved-name hazard alongside the inline if-else string expression bug.
1. perceive() guard — gate on engram_search_json before running activation.
engram_activate_json with no matching seeds cleared all WM weights every
second during idle operation, destroying context built by MCP-layer calls.
The search-based guard is a no-WM-side-effect pre-check.
2. emit_heartbeat() pulse field — replace broken if-else string default with
int_to_str(pulse_count()). EL codegen initialises inline if-else result
slots to 0, producing "pulse":, (invalid JSON) when the true branch fires.
3. proactive_curiosity() — new function that activates a rotating 4-domain seed
every beat_interval/2 idle ticks to build working memory between heartbeats.
Seeds rotate on wall-clock minute cycle to avoid single-topic WM dominance.
Seed selection uses imperative let-rebinding (not inline if-else) to avoid
the same EL codegen empty-string bug.
Ollama availability is a silent failure mode: when the embedding service
is down, semantic seed injection falls back to lexical-only activation with
no signal in the ISE stream. Add embed_ok field (0/1) to every heartbeat
by probing http://localhost:11434 — makes Ollama health visible without
a separate monitoring path.
state_get() returns "" for unset keys. Both soul.pulse and soul_boot_count
could be empty on first heartbeat cycle, producing invalid JSON like
{"event":"heartbeat","pulse":,"boot":,...}. Add defensive guards:
if str_eq(raw, "") { "0" } else { raw } for both fields.
Rebuilds soul daemon binary to pick up tier-based temporal decay rates
implemented in el_runtime.c. No source changes to awareness.el or soul.el —
pure rebuild to stay in sync with Engram runtime.
Heartbeat ISEs now include wm_active: number of nodes currently in
working memory. Makes ISEs observable enough to diagnose activation
health without a separate query.
Heartbeat ISEs previously emitted only {event, pulse, boot, ts} —
sparse enough to be nearly useless for observability. Now they include
node_count, edge_count (from engram_node_count/edge_count builtins),
and the current idle cycle count. This gives each heartbeat a snapshot
of graph growth over time and rhythm health without adding any overhead.
Block evolve_knowledge, evolve_memory, forget, and link_entities (to_id
direction) from modifying the 15 hardcoded identity and values node IDs.
Returns HTTP 403 with a hint to use the cultivation path instead.
Add POST /api/neuron/cultivate — the bypass endpoint for intentional
cultivation sessions. Accepts { "operation": "...", ...args } and performs
the same operations without the protection check.
Add handle_api_forget and handle_api_evolve_memory as new protected-by-
default handlers, routed at /api/neuron/memory/forget and
/api/neuron/memory/evolve respectively.
Tested: 10 verification cases — 403 on all blocked targets, 200 on
non-protected nodes and FROM-direction links, cultivate bypass confirmed.
The engram binary was never published to Artifact Registry (foundation-dev/engram
package does not exist). Updated Dockerfile to build engram from source using the
El SDK packages (el-elc, el-runtime-c, el-runtime-h) from foundation-dev.
Also:
- Switch runtime base to Ubuntu 24.04 (GLIBC 2.39 required by elc-compiled binaries)
- Add -lm to engram link flags (el_runtime.c uses pow/sqrt/log/sin/cos/exp)
- Update deploy-gke.yaml to clone neuron-technologies/engram into build context
Download both neuron-soul and engram binaries from Artifact Registry.
entrypoint.sh starts engram on :8742, waits for /health, then launches
the soul with ENGRAM_URL set. Removes SOUL_ENGRAM_PATH / file mode.
Dockerfile: downloads linux/amd64 soul binary from Artifact Registry
(foundation-dev/neuron-soul) into ubuntu:22.04 runtime image.
Pushes to neuron-api Docker repo as neuron-soul:<sha>.
scripts/blue-green-deploy.sh: swaps active slot on GKE — sets image,
scales new slot to 1, flips service selector, scales old slot to 0.
scripts/seed-engram-gke.sh: downloads latest GCS backup, extracts
snapshot.json, copies into neuron-engram-data PVC via a seed Job.
.gitea/workflows/deploy-gke.yaml: triggers on push to main, auto-detects
idle slot, builds Docker image from Artifact Registry binary, blue-green
deploys to neuron-prod on GKE neuron-platform cluster.
Downloads El SDK from Artifact Registry, generates ELP declarations header,
builds the neuron soul binary with elb, smoke-tests it, and publishes to
foundation-dev on push to main.
neuron-api.el is a new first-class El module that implements all Neuron
cognitive API handlers natively — no HTTP round-trips, no MCP wrapper,
direct engram builtin calls. All capabilities that previously lived in
the MCP wrapper adapter now live here in the soul.
Handlers: begin_session, compile_ctx, remember, recall, search_knowledge,
browse_knowledge, capture_knowledge, evolve_knowledge, promote_knowledge,
browse_processes, define_process, log_state_event, list_state_events,
inspect_config, tune_config, inspect_graph, link_entities, list_typed,
consolidate.
Routes wired in routes.el under /api/neuron/* (GET + POST).
Also compiles all loop-1/loop-2 .el source changes into dist/*.c and
rebuilds the binary. memory.elh and neuron-api.elh updated with new exports.
Adds handle_dharma_room_turn_agentic to chat.el — same full tool loop
as handle_chat_agentic but reads transcript directly (not message), and
returns {response, cgi_id, tools_used} to match the dharma room shape.
Registers dharma_room_turn_agentic as a new event type in routes.el so
the studio can dispatch @neuron turns through this dedicated path.
- soul.el: SOUL_CGI_ID, SOUL_ENGRAM_PATH, SOUL_IDENTITY env vars;
state_set("soul_snapshot_path") so callers can find it; only call
init_soul_edges() when cgi_id == "ntn-genesis"
- chat.el: handle_dharma_room_turn — soul builds its own context from its
own engram, assembles system prompt, calls LLM, persists episodic memory;
also fix is_new_tool scoping bug in handle_chat_agentic (use has_tool)
- routes.el: wire dharma_room_turn event type before chat_as_soul branch
- rebuild dist/neuron: handle_dharma_room_turn now compiled in
elp-input.el: walk frame_nodes to pick the first node whose content
contains the query topic (case-insensitive) rather than always taking
index 0 — prevents the always-high-salience CGI architecture memory
from hijacking every ELP response.
chat.el: rewrite handle_chat_agentic to run the tool loop natively in
El using http_post_with_headers + Map headers, bypassing the broken
llm_call_agentic(model, system, message, tools) C binding that cast a
JSON String as an ElList and never serialized tools. New impl supports
up to 8 tool-use iterations with read_file, write_file, web_get,
search_memory, and run_command dispatch.
elp-input.el: replace broken engram_search_json with engram_activate_json
as Layer 1. Layer 2 suppress/filter keeps nodes with non-zero salience/
importance. Reason step extracts patient from top activated node content.
ELP grammar realizes the response via generate().
routes.el: add 'elp' event_type to handle_dharma_recv so the studio can
route ELP requests through dharma.
Replace scan-by-offset fallback with engram_get_node_json calls for the
known high-salience identity nodes (family, origin). Offset-based scanning
is order-dependent and unreliable; direct ID fetch is stable regardless of
snapshot position. Ensures biographical context (Fox, Bobby, etc.) is
always in the system prompt when vector search returns nothing.