Compare commits

...

16 Commits

Author SHA1 Message Date
will.anderson ce3c3873c5 fix(ci): link soul.c only — drop multi-module cc that triggers capability #error
Neuron Soul CI / build (pull_request) Failing after 7m44s
elb generates a dist/soul.c with all El modules inlined. Linking
dist/soul.c alone is sufficient and is exactly what the local mac
build does. Including other dist/*.c files causes two failures:
  1. dist/chat.c has a capability-violation #error that fires when the
     file is compiled as a utility module (outside the cgi entrypoint).
  2. --allow-multiple-definition masked other issues silently.

Drop OTHER_C, drop --allow-multiple-definition, drop the now-unused
elp-c-decls.h generation step. The cc command now matches the proven
local build exactly.
2026-06-18 11:27:57 -05:00
will.anderson 74ac457e1c Merge pull request 'fix(soul): ratio guard against genesis seeding over a populated engram' (#21) from feat/connectors-soul into main
Deploy Soul to GKE / deploy (push) Failing after 12m51s
Neuron Soul CI / build (push) Failing after 13m3s
fix(soul): ratio guard against genesis seeding over a populated engram
2026-06-17 18:19:52 +00:00
will.anderson 8b692e4666 fix/test: PR #21 review — guard, safety Bell, api write-back, temp paths
Neuron Soul CI / build (pull_request) Failing after 13m22s
fix(soul): add HTTP-engram guard to safe_to_seed — when ENGRAM_URL is set
the HTTP Engram owns persistence; genesis must never save to local snapshot
regardless of node counts (was: guard_disk forced to empty string, making
the ratio check vacuously true and allowing init_soul_edges+engram_save).

fix(soul): use multiplication form for ratio guard — node_count * 16000 <
disk_len avoids floor-division truncation that underestimated boundary files
(250KB / 16000 = 15.6, floors to 15; a 15-node graph wrongly passed old guard).

fix(chat): add safety_augment_system to handle_chat_as_soul,
handle_dharma_room_turn, and handle_dharma_room_turn_agentic — all three
called the LLM without Hard Bell evaluation, leaving users in dharma rooms
without crisis resource routing.

fix(neuron-api): add api_persisted read-back to handle_api_define_process —
was the only write handler that returned ok:true without verifying the node
was actually written to engram.

fix(routes): unique temp file path in connectd_post — replaces fixed
/tmp/neuron-connectors-req.json with a timestamped path to prevent
collision if concurrency is added or two soul instances share a machine.

test: add tests/test_bell_safety.el — covers safety_detect_bell_level
(none/soft/hard), safety_classify_hard_bell (abuse/self_harm routing),
safety_normalize (smart-quote), safety_augment_system, and
handle_safety_contact_post (validation + read-back).

test: add tests/test_soul_guard.el — pure-function logic tests for the
safe_to_seed predicate: 200KB boundary, 47MB/63-node clobber scenario,
HTTP-engram mode, multiplication vs division truncation at 250KB.

test: add tests/test_api_define_process.el — verifies the define_process
write is read-back verified after the fix.
2026-06-17 13:19:15 -05:00
Tim Lingo 5ddb860201 fix(soul): ratio guard against genesis seeding over a populated engram
Genesis boot previously seeded a fresh identity and saved it over snapshot.json
whenever the in-memory graph looked empty. Replace the fixed node-count threshold
with a ratio guard: refuse to seed when the on-disk snapshot is large
(>200KB) but the loaded graph is sparse (< disk/16000 nodes).

KNOWN LIMITATION: this gates only the seed/pre-serve-save path. The deeper cause
is a non-atomic engram_save (fopen wb truncates to 0 before writing 47MB), which
creates a window where a concurrent load reads an empty file -> genesis -> and if
guard_disk is read in that same window the guard passes. The real fix is an
atomic engram_save (temp + fsync + rename) in el_runtime.c, tracked separately.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 13:18:35 -05:00
Tim Lingo 6d8a992716 feat(soul): add safety module, expand connectors API, memory-recall bug notes
- safety.el/.elh: new safety module
- neuron-api.el, routes.el, soul.el, chat.el: connectors API expansion
- regenerated dist/ C artifacts
- MEMORY_RECALL_BUG.md: investigation notes

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 13:18:35 -05:00
will.anderson 2797909633 Merge pull request 'fix(chat): prevent double-escape corruption of messages/tools in agentic bridge' (#20) from fix/bridge-save-serialization into main
Deploy Soul to GKE / deploy (push) Failing after 13m1s
Neuron Soul CI / build (push) Failing after 13m10s
fix(chat): prevent double-escape corruption of messages/tools in agentic bridge
2026-06-17 18:08:12 +00:00
will.anderson 8db3c8c7f7 fix(chat): harden bridge_save/agentic_resume against empty and corrupt state
Neuron Soul CI / build (pull_request) Failing after 13m18s
BLOCKER 1: use untyped reassignment (let x = ...) for the fallback bindings
in agentic_resume instead of re-declaring typed let bindings (let x: Type = ...)
for the same variable in the same scope. The typed form risks shadowing semantics
that differ from the established pattern used everywhere else in the loop
(e.g. agentic_loop line 720).

BLOCKER 2: add empty-string guards in both bridge_save and agentic_resume.
bridge_save now returns false without writing state if messages or tools_json
is empty — preventing syntactically invalid JSON blobs. agentic_resume now
returns an error envelope after the fallback resolution if either field is
still empty, rather than passing empty strings into agentic_loop which would
silently start a fresh turn with no context.

Also add tests:
- test_bridge_serialization.el: covers bridge_save empty-guard, golden-path
  raw-JSON round-trip, agentic_resume unknown/corrupt/missing-fields paths,
  and legacy string-escaped fallback path
- test_sessions_routes.el: covers DELETE and PATCH /api/sessions/:id routes
  (valid args, unknown id, empty body) and GET /api/sessions regression after
  removal of the duplicate route_sessions() handler
2026-06-17 13:07:43 -05:00
will.anderson e7297275a3 Merge pull request 'fix(chat): wire agentic_tools_all into both agentic loop entry points' (#19) from fix/agentic-tools-all into main
Deploy Soul to GKE / deploy (push) Failing after 6m23s
Neuron Soul CI / build (push) Failing after 14m16s
fix(chat): wire agentic_tools_all into both agentic loop entry points
2026-06-17 18:06:35 +00:00
will.anderson fc74bd2a4b Merge pull request 'fix(sessions): unify dual suspension systems, wire approve to agentic_resume' (#18) from fix/agentic-tool-approval-unification into main
Deploy Soul to GKE / deploy (push) Failing after 6m35s
Neuron Soul CI / build (push) Failing after 14m31s
fix(sessions): unify dual suspension systems, wire approve to agentic_resume
2026-06-17 18:06:01 +00:00
will.anderson 189093b348 Merge pull request 'fix(routes): remove duplicate GET /api/sessions shadowing session_list()' (#17) from fix/sessions-route-dedup into main
Deploy Soul to GKE / deploy (push) Failing after 14m41s
Neuron Soul CI / build (push) Failing after 14m51s
fix(routes): remove duplicate GET /api/sessions shadowing session_list()
2026-06-17 18:05:19 +00:00
will.anderson f7ae7df9d6 fix/test(chat): guard handle_dharma_room_turn_agentic against tool_pending and empty reply
Neuron Soul CI / build (pull_request) Failing after 8m0s
When agentic_loop suspends for an MCP bridge tool it returns a
{"tool_pending":true,...} envelope with no "reply" key. Without an
explicit check, json_get(loop_result, "reply") returns "" and the
function emitted {"response":"","cgi_id":"..."} — a silent empty
response indistinguishable from a successful LLM turn with no content.

Two guards added after the existing error check:

1. tool_pending passthrough: if the loop suspended, return the pending
   envelope directly so callers (dharma room orchestrators) can
   distinguish suspension from failure and route to the approve flow.

2. Empty-reply guard: if final_text is empty after the pending check,
   return an explicit {"error":"no response",...} envelope instead of
   silently succeeding with an empty response field.

Also adds tests/test_agentic_tools.el:
- agentic_tools_all() includes all literal tool names and web_search
- connector_tools_json() returns valid JSON when bridge is down (graceful degradation)
- tool_pending envelope detection patterns (the is_pending logic)
- json_get(pending_envelope, "reply") returns "" confirming the empty-reply
  guard is load-bearing (pure string/JSON, no LLM or network required)
2026-06-17 13:01:13 -05:00
will.anderson b1fdd14ed5 fix(sessions): invalidate session_index cache in session_delete
Neuron Soul CI / build (pull_request) Failing after 8m11s
session_delete cleared the per-session state (session_hist_ and
session_node_) but not the shared session_index cache. The next call
to session_list() hit the fast path (state_get("session_index")) and
returned the deleted session until the daemon restarted.

session_update_patch already called state_set("session_index","") to
force a re-fetch from Engram; session_delete now does the same.

Add tests/test_sessions.el covering:
- session_title_from_message (pure function, all edge cases)
- session_make_content (JSON structure and required session:meta marker)
- DELETE cache invalidation: session_index cleared, fast path disabled
- PATCH cache invalidation: stale title/folder not returned via fast path
- GET /api/sessions: session_list() fast path returns session_index
  (confirms removal of the stale route_sessions() engram stub)
2026-06-17 12:59:47 -05:00
will.anderson 91902d6bf2 fix(sessions): resolve blockers and warnings in handle_session_approve
Neuron Soul CI / build (pull_request) Failing after 9m3s
BLOCKER 1 (sessions.el, modern path): Add guard that rejects allow
action when tool_name is missing from the body. Previously, omitting
tool_name caused dispatch_tool("", ...) to return "unknown tool: " and
silently inject a corrupted tool_result into the conversation.

BLOCKER 2 (sessions.el, modern path): Stop re-executing client-side
tools server-side. When the client provides body["content"], use it
directly as the tool result (matching the handle_tool_result contract).
Only fall back to dispatch_tool for builtin tools when no content is
present. Non-builtin tools with no client content now return a clear
error instead of a broken dispatch attempt.

WARNING 1 (chat.el, agentic_loop): Wire always_allow_<session_id> state
into the bridge-suspension decision. When a tool is in the session's
always-allow list, treat it as locally dispatchable (like a builtin)
and skip the bridge pause, so the approval UI is never shown again for
that tool in that session.

WARNING 2 (sessions.el, legacy path): Read a "tools_variant" field from
the legacy pending blob when present, and call the corresponding
agentic_tools_*() variant on resume. Falls back to agentic_tools_literal()
for blobs written before this field existed.

tests/test_sessions_approve.el: Add 10-case test suite covering:
- empty session_id / missing call_id / missing action guards
- no pending tool returns correct error
- missing tool_name on allow returns error (BLOCKER 1)
- deny action does not require tool_name
- legacy call_id mismatch returns mismatch error
- always action records tool_name in always_allow state
- allow with client content skips re-execution (BLOCKER 2)
2026-06-17 12:58:44 -05:00
will.anderson 26513d56b7 fix(chat): store bridge messages/tools as raw JSON to prevent double-escape corruption on agentic_resume
bridge_save was wrapping messages and tools_json with json_safe() before
storing them as string fields. Since both are already well-formed JSON arrays
containing double quotes, json_safe added a second escape layer. agentic_resume
then called json_get() which stripped only one layer, leaving the messages array
corrupted before it was passed back into agentic_loop.

Fix: store messages as messages_raw and tools_json as tools_raw as inline raw
JSON values (unquoted), and read them back with json_get_raw. Backward
compatibility: fall back to the old string-escaped fields if the raw fields are
absent, so sessions saved before this fix can still be resumed.

Also fixes write_file returning a pre-escaped literal instead of calling
json_safe consistently with every other tool result.
2026-06-15 13:04:51 -05:00
will.anderson c43d3e6ca8 fix(routes): remove duplicate GET /api/sessions that shadowed session_list()
Neuron Soul CI / build (pull_request) Failing after 9m52s
The first registration called route_sessions() which searched for a
'session-start' label that no longer exists, returning an empty array
on every list request and making the sidebar appear empty after restart.
The second registration (dead code) called the correct session_list().

Removes route_sessions() entirely and the stale first route block.
Also wires up session_delete() and session_update_patch() — both existed
in sessions.el but had no HTTP routes — via new DELETE and PATCH blocks.
2026-06-15 13:03:56 -05:00
will.anderson 7c7dc310a0 fix(sessions): unify dual suspension systems in handle_session_approve
Neuron Soul CI / build (pull_request) Failing after 11m26s
The approve endpoint was permanently broken for all sessions going through
the modern agentic_loop path. agentic_loop suspends via bridge_save() into
mcp_bridge:<session_id>, but handle_session_approve was reading from
pending_tool_<session_id> — a different key — so it always returned
"no pending tool for session".

Replace the body of handle_session_approve with a two-path design:

Modern path: check mcp_bridge:<session_id> first. If the blob is there,
dispatch_tool() on allow (or build the denial string), then delegate to
agentic_resume() which re-enters agentic_loop from the exact suspension
point. This is the path all live sessions take.

Legacy path: if only pending_tool_<session_id> exists (in-flight session
from before this deploy), synthesise a bridge blob from the stored
messages_so_far and route through agentic_resume() as well. The stale
inline agentic loop (90 lines, agentic_tools_literal only, no MCP
connector support, no bridge suspension) is removed entirely.

routes.el already calls handle_session_approve correctly — no change needed.
2026-06-15 13:03:15 -05:00
24 changed files with 2172 additions and 205 deletions
+10 -25
View File
@@ -91,44 +91,29 @@ jobs:
echo "El SDK ready"
/opt/el/dist/platform/elc --version || true
- name: Generate ELP master declarations header
run: |
{
printf '/* Auto-generated C forward declarations for ELP cross-module calls */\n'
printf '#pragma once\n'
printf '#include "el_runtime.h"\n'
printf '\n'
grep -h -E '^(el_val_t|void|int|char\*|const char\*)[[:space:]]+[a-zA-Z_][a-zA-Z0-9_]*[[:space:]]*\(' dist/*.c 2>/dev/null \
| grep ';$' | sort -u
} > dist/elp-c-decls.h
echo "Generated elp-c-decls.h with $(grep -c ';' dist/elp-c-decls.h 2>/dev/null || echo 0) declarations"
- name: Build neuron soul binary
run: |
ELB=/opt/el/dist/bin/elb
ELC=/opt/el/dist/platform/elc
RUNTIME=/opt/el/runtime
# Compile all El modules to C.
# This step will fail at link on Linux: the El compiler inlines imported
# modules into each module's .c file, producing duplicate strong symbol
# definitions. GNU ld rejects these; macOS ld accepts them silently.
# We capture the link failure and re-link manually below.
# Compile all El modules to C via elb.
# elb fails at link on Linux (GNU ld rejects duplicate strong symbols that
# macOS ld accepts silently) — that's expected and captured with || true.
# The important output is dist/soul.c: the El compiler inlines all imported
# modules into the entry-point file, so soul.c is a self-contained
# translation unit. We never link the other dist/*.c files — they contain
# the same symbols inlined again, plus capability-violation #error guards
# that fire when compiled outside the cgi entrypoint.
$ELB --elc=$ELC --runtime=$RUNTIME/el_runtime.c || true
# Re-link with soul.c listed first so its real main() (from the cgi block)
# wins over the stub main()s generated in every other module.
# --allow-multiple-definition tells GNU ld to pick the first definition
# for each duplicate symbol — safe here because all duplicates are identical
# (same El source compiled independently into multiple .c files).
# Link only soul.c + the runtime. No --allow-multiple-definition needed.
mkdir -p dist
OTHER_C=$(ls dist/*.c | grep -v '/soul\.c$' | sort | tr '\n' ' ')
cc -O2 -DHAVE_CURL \
-I$RUNTIME \
dist/soul.c $OTHER_C \
dist/soul.c \
$RUNTIME/el_runtime.c \
-lssl -lcrypto -lcurl -lpthread -lm \
-Wl,--allow-multiple-definition \
-o dist/neuron
ls -lh dist/neuron
+55 -6
View File
@@ -387,7 +387,7 @@ fn dispatch_tool(tool_name: String, tool_input: String) -> String {
let path: String = json_get(tool_input, "path")
let content: String = json_get(tool_input, "content")
fs_write(path, content)
return "{\\\"ok\\\":true}"
return json_safe("{\"ok\":true}")
}
if str_eq(tool_name, "web_get") {
let url: String = json_get(tool_input, "url")
@@ -691,7 +691,13 @@ fn agentic_loop(session_id: String, model: String, safe_sys: String, tools_json:
// A real tool turn that targets a tool the soul cannot run in-process is a
// CLIENT bridge: suspend the loop and hand the tool to the client.
let is_tool_turn: Bool = str_eq(stop_reason, "tool_use") && has_tool
let needs_bridge: Bool = is_tool_turn && !is_builtin_tool(tool_name)
// If the user previously chose "always allow" for this tool in this session,
// treat it like a builtin run server-side via dispatch_tool and skip the
// bridge suspension entirely so the approval UI is never shown again.
let always_key: String = "always_allow_" + session_id
let always_list: String = if !str_eq(session_id, "") { state_get(always_key) } else { "" }
let is_always_allowed: Bool = !str_eq(tool_name, "") && !str_eq(always_list, "") && str_contains(always_list, tool_name)
let needs_bridge: Bool = is_tool_turn && !is_builtin_tool(tool_name) && !is_always_allowed
// Built-in tools dispatch locally; bridged tools yield "" (never sent upstream).
let tool_result_raw: String = if is_tool_turn && !needs_bridge { dispatch_tool(tool_name, tool_input) } else { "" }
@@ -766,10 +772,20 @@ fn agentic_loop(session_id: String, model: String, safe_sys: String, tools_json:
// stored `messages` already includes the assistant turn that requested the tool, so
// resume just appends the client's tool_result for `tool_use_id`.
fn bridge_save(session_id: String, model: String, safe_sys: String, tools_json: String, messages: String, tools_log: String, tool_use_id: String) -> Bool {
// Guard: empty messages or tools_json would produce syntactically invalid JSON.
// Return false so the caller detects the failure rather than writing a corrupt
// blob that agentic_resume would later resume with no context.
if str_eq(messages, "") || str_eq(tools_json, "") {
return false
}
// messages and tools_json are already well-formed JSON arrays; embed them as raw
// JSON values (not string-escaped) so the round-trip through state_get/json_get_raw
// never corrupts nested quotes. Scalar strings (model, safe_sys, tools_log,
// tool_use_id) stay as string fields via json_safe as before.
let blob: String = "{\"model\":\"" + json_safe(model) + "\""
+ ",\"safe_sys\":\"" + json_safe(safe_sys) + "\""
+ ",\"tools_json\":\"" + json_safe(tools_json) + "\""
+ ",\"messages\":\"" + json_safe(messages) + "\""
+ ",\"messages_raw\":" + messages
+ ",\"tools_raw\":" + tools_json
+ ",\"tools_log\":\"" + json_safe(tools_log) + "\""
+ ",\"tool_use_id\":\"" + json_safe(tool_use_id) + "\"}"
state_set("mcp_bridge:" + session_id, blob)
@@ -789,8 +805,18 @@ fn agentic_resume(session_id: String, tool_use_id: String, content: String) -> S
let model: String = json_get(blob, "model")
let safe_sys: String = json_get(blob, "safe_sys")
let tools_json: String = json_get(blob, "tools_json")
let messages: String = json_get(blob, "messages")
// messages_raw and tools_raw are embedded as raw JSON (not string-escaped);
// fall back to legacy string-escaped fields for sessions saved before this fix.
let messages: String = json_get_raw(blob, "messages_raw")
let messages = if str_eq(messages, "") { json_get(blob, "messages") } else { messages }
let tools_json: String = json_get_raw(blob, "tools_raw")
let tools_json = if str_eq(tools_json, "") { json_get(blob, "tools_json") } else { tools_json }
// Guard: a corrupt or missing bridge blob (e.g. state cleared mid-flight)
// yields empty messages/tools. Return an error envelope rather than resuming
// with no context, which would cause the model to start a fresh turn.
if str_eq(messages, "") || str_eq(tools_json, "") {
return "{\"error\":\"corrupt bridge state\",\"reply\":\"\"}"
}
let tools_log: String = json_get(blob, "tools_log")
let saved_use_id: String = json_get(blob, "tool_use_id")
@@ -883,6 +909,9 @@ fn handle_chat_as_soul(body: String) -> String {
let req_model: String = json_get(body, "model")
let model: String = if str_eq(req_model, "") { chat_default_model() } else { req_model }
// Hard Bell: pre-LLM safety evaluation multi-soul room conversations are real interactions.
let system_prompt = safety_augment_system(system_prompt, eff_message)
let raw_response: String = llm_call_system(model, system_prompt, eff_message)
let is_error: Bool = str_starts_with(raw_response, "{\"error\"")
@@ -929,6 +958,9 @@ fn handle_dharma_room_turn(body: String) -> String {
identity + "\n\n" + engram_ctx
}
// Hard Bell: pre-LLM safety evaluation dharma room turns are real conversations.
let system_prompt = safety_augment_system(system_prompt, transcript)
let raw_response: String = llm_call_system(model, system_prompt, transcript)
let is_error: Bool = str_starts_with(raw_response, "{\"error\"")
@@ -975,6 +1007,9 @@ fn handle_dharma_room_turn_agentic(body: String) -> String {
let system: String = identity + " You have access to tools: read files, write files, browse the web, search your memory, run commands. Use them when they add genuine value. Be direct and stay in character.\n\n" + ctx
let api_key: String = agentic_api_key()
// Hard Bell: pre-LLM safety evaluation on agentic dharma room turns.
let system = safety_augment_system(system, transcript)
let tools_json: String = agentic_tools_all()
let safe_transcript: String = json_safe(transcript)
let safe_sys: String = json_safe(system)
@@ -993,7 +1028,21 @@ fn handle_dharma_room_turn_agentic(body: String) -> String {
return "{\"error\":\"" + result_error + "\",\"response\":\"\",\"cgi_id\":\"" + cgi_id + "\"}"
}
// If agentic_loop suspended for an MCP bridge tool, pass the pending envelope
// straight through so callers can distinguish suspension from failure.
// A silent empty response is indistinguishable from an LLM error to any caller.
let is_pending: Bool = str_eq(json_get(loop_result, "tool_pending"), "true")
|| str_starts_with(loop_result, "{\"tool_pending\":true")
if is_pending {
return loop_result
}
let final_text: String = json_get(loop_result, "reply")
// Guard against a silent empty response - produce an explicit error so callers
// cannot mistake a failed turn for a successful one with empty content.
if str_eq(final_text, "") {
return "{\"error\":\"no response\",\"response\":\"\",\"cgi_id\":\"" + cgi_id + "\"}"
}
let tools_arr: String = json_get_raw(loop_result, "tools_used")
let eff_tools: String = if str_eq(tools_arr, "") { "[]" } else { tools_arr }
let safe_text: String = json_safe(final_text)
+11 -1
View File
@@ -1,4 +1,4 @@
// auto-generated by elc --emit-header do not edit
// auto-generated by elc --emit-header - do not edit
extern fn chat_default_model() -> String
extern fn gemini_api_key() -> String
extern fn xai_api_key() -> String
@@ -19,8 +19,18 @@ extern fn studio_tools_json() -> String
extern fn agentic_api_key() -> String
extern fn call_neuron_mcp(tool_name: String, args_json: String) -> String
extern fn agentic_tools_literal() -> String
extern fn agentic_tools_with_web() -> String
extern fn dispatch_tool(tool_name: String, tool_input: String) -> String
extern fn json_array_append(arr: String, item: String) -> String
extern fn append_tool_log(log: String, name: String) -> String
extern fn exec_tool_block(block: String) -> String
extern fn agentic_blob(model: String, system: String, tools_json: String, messages: String, origin: String, approval: Bool, iteration: Int, tools_log: String, content: String, queue: String, results: String, next: Int) -> String
extern fn extract_all_text(s: String) -> String
extern fn strip_citations(s: String) -> String
extern fn agentic_api_turn(model: String, safe_sys: String, tools_json: String, messages: String) -> String
extern fn agentic_engine(session_id: String, blob: String) -> String
extern fn handle_chat_agentic(body: String) -> String
extern fn handle_session_approve(session_id: String, body: String) -> String
extern fn handle_chat_as_soul(body: String) -> String
extern fn handle_dharma_room_turn(body: String) -> String
extern fn handle_dharma_room_turn_agentic(body: String) -> String
Generated Vendored
+2 -1
View File
@@ -1,4 +1,4 @@
// auto-generated by elc --emit-header do not edit
// auto-generated by elc --emit-header - do not edit
extern fn chat_default_model() -> String
extern fn gemini_api_key() -> String
extern fn xai_api_key() -> String
@@ -19,6 +19,7 @@ extern fn studio_tools_json() -> String
extern fn agentic_api_key() -> String
extern fn call_neuron_mcp(tool_name: String, args_json: String) -> String
extern fn agentic_tools_literal() -> String
extern fn agentic_tools_with_web() -> String
extern fn dispatch_tool(tool_name: String, tool_input: String) -> String
extern fn handle_chat_agentic(body: String) -> String
extern fn handle_chat_as_soul(body: String) -> String
Generated Vendored
+36 -2
View File
@@ -1042,12 +1042,36 @@ el_val_t call_neuron_mcp(el_val_t tool_name, el_val_t args_json);
el_val_t agentic_tools_literal(void);
el_val_t agentic_tools_with_web(void);
el_val_t dispatch_tool(el_val_t tool_name, el_val_t tool_input);
el_val_t json_array_append(el_val_t arr, el_val_t item);
el_val_t append_tool_log(el_val_t log, el_val_t name);
el_val_t exec_tool_block(el_val_t block);
el_val_t agentic_blob(el_val_t model, el_val_t system, el_val_t tools_json, el_val_t messages, el_val_t origin, el_val_t approval, el_val_t iteration, el_val_t tools_log, el_val_t content, el_val_t queue, el_val_t results, el_val_t next);
el_val_t extract_all_text(el_val_t s);
el_val_t strip_citations(el_val_t s);
el_val_t agentic_api_turn(el_val_t model, el_val_t safe_sys, el_val_t tools_json, el_val_t messages);
el_val_t agentic_engine(el_val_t session_id, el_val_t blob);
el_val_t handle_chat_agentic(el_val_t body);
el_val_t handle_session_approve(el_val_t session_id, el_val_t body);
el_val_t handle_chat_as_soul(el_val_t body);
el_val_t handle_dharma_room_turn(el_val_t body);
el_val_t handle_dharma_room_turn_agentic(el_val_t body);
el_val_t auto_persist(el_val_t req, el_val_t resp);
el_val_t strengthen_chat_nodes(el_val_t activation_nodes);
el_val_t safety_self_harm_phrases(void);
el_val_t safety_abuse_phrases(void);
el_val_t safety_general_hard_phrases(void);
el_val_t safety_soft_phrases(void);
el_val_t safety_normalize(el_val_t message);
el_val_t safety_any_match(el_val_t text, el_val_t phrases_json);
el_val_t safety_count_match(el_val_t text, el_val_t phrases_json);
el_val_t safety_detect_bell_level(el_val_t message);
el_val_t safety_classify_hard_bell(el_val_t message);
el_val_t safety_soft_directive(void);
el_val_t safety_hard_directive(el_val_t hard_type);
el_val_t safety_augment_system(el_val_t system, el_val_t user_msg);
el_val_t safety_contact_path(void);
el_val_t handle_safety_contact_get(void);
el_val_t handle_safety_contact_post(el_val_t body);
el_val_t auth_headers(el_val_t tok);
el_val_t axon_get(el_val_t path);
el_val_t axon_post(el_val_t path, el_val_t body);
@@ -1110,6 +1134,7 @@ el_val_t session_update_meta_timestamp(el_val_t session_id);
el_val_t session_auto_title(el_val_t session_id, el_val_t first_message);
el_val_t handle_session_approve(el_val_t session_id, el_val_t body);
el_val_t strip_query(el_val_t path);
el_val_t flag_true(el_val_t body, el_val_t key);
el_val_t err_404(el_val_t path);
el_val_t err_405(el_val_t method, el_val_t path);
el_val_t route_health(void);
@@ -1144,6 +1169,9 @@ el_val_t local_node_count;
el_val_t snapshot_usable;
el_val_t boot_num;
el_val_t is_genesis;
el_val_t guard_disk;
el_val_t guard_disk_len;
el_val_t safe_to_seed;
el_val_t lang_profile(el_val_t code, el_val_t word_order, el_val_t morph_type, el_val_t has_case, el_val_t has_gender, el_val_t script_dir, el_val_t agreement, el_val_t null_subject) {
el_val_t r = native_list_empty();
@@ -28915,7 +28943,13 @@ int main(int _argc, char** _argv) {
state_set(EL_STR("soul_engram_api_key"), engram_api_key_raw);
state_set(EL_STR("soul.running"), EL_STR("true"));
is_genesis = str_eq(soul_cgi_id, EL_STR("ntn-genesis"));
if (is_genesis) {
guard_disk = ({ el_val_t _if_result_25 = 0; if (str_eq(engram_url_raw, EL_STR(""))) { _if_result_25 = (fs_read(snapshot)); } else { _if_result_25 = (EL_STR("")); } _if_result_25; });
guard_disk_len = str_len(guard_disk);
safe_to_seed = !((guard_disk_len > 200000) && (engram_node_count() < (guard_disk_len / 16000)));
if (is_genesis && !safe_to_seed) {
println(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("[soul] GUARD: loaded "), int_to_str(engram_node_count())), EL_STR(" nodes but snapshot file is ")), int_to_str(guard_disk_len)), EL_STR(" bytes \xe2\x80\x94 refusing to seed/save over a real graph")));
}
if (is_genesis && safe_to_seed) {
el_val_t edge_count_now = engram_edge_count();
if (edge_count_now < 100) {
init_soul_edges();
@@ -28926,7 +28960,7 @@ int main(int _argc, char** _argv) {
state_set(EL_STR("soul_snapshot_path"), snapshot);
engram_save(snapshot);
}
if (is_genesis) {
if (is_genesis && safe_to_seed) {
el_val_t snap = state_get(EL_STR("soul_snapshot_path"));
if (!str_eq(snap, EL_STR(""))) {
engram_save(snap);
+1 -1
View File
@@ -1,4 +1,4 @@
// auto-generated by elc --emit-header do not edit
// auto-generated by elc --emit-header - do not edit
extern fn elp_extract_topic(msg: String) -> String
extern fn elp_detect_predicate(msg: String) -> String
extern fn elp_parse(msg: String) -> String
+1 -1
View File
@@ -1,4 +1,4 @@
// auto-generated by elc --emit-header do not edit
// auto-generated by elc --emit-header - do not edit
extern fn tier_working() -> String
extern fn tier_episodic() -> String
extern fn tier_canonical() -> String
+118 -4
View File
@@ -87,6 +87,21 @@ fn api_or_empty(s: String) -> String {
return "[]"
}
// api_persisted read-back-after-write guard against hallucinated saves.
// After a write builtin returns an id, confirm the node is actually queryable
// via engram_get_node_json(id) (returns "" or "null" when missing). Returns
// true only when the node is genuinely persisted.
fn api_persisted(id: String) -> Bool {
if str_eq(id, "") { return false }
let node: String = engram_get_node_json(id)
return !str_eq(node, "") && !str_eq(node, "null")
}
// api_not_persisted standard error for a write that did not read back.
fn api_not_persisted(id: String) -> String {
return "{\"ok\":false,\"error\":\"write_not_persisted\",\"id\":\"" + id + "\"}"
}
// Session
// handle_api_begin_session full context bootstrap.
@@ -143,12 +158,101 @@ fn handle_api_remember(body: String) -> String {
let id: String = engram_node_full(content, "Memory", "memory:remembered",
el_from_float(sal), el_from_float(sal), el_from_float(0.9),
"Episodic", final_tags)
if !api_persisted(id) { return api_not_persisted(id) }
return "{\"id\":\"" + id + "\",\"ok\":true}"
}
// handle_api_node_create generic typed-node create (BacklogItem, Artifact, ...).
// Mirrors handle_api_remember but lets the caller choose node_type/label/tier so the
// UI can create non-Memory nodes. Read-back verified against hallucinated saves.
fn handle_api_node_create(body: String) -> String {
let content: String = json_get(body, "content")
if str_eq(content, "") { return api_err("content is required") }
let nt_raw: String = json_get(body, "node_type")
let node_type: String = if str_eq(nt_raw, "") { "Memory" } else { nt_raw }
let label_raw: String = json_get(body, "label")
let label: String = if str_eq(label_raw, "") { "node:created" } else { label_raw }
let tier_raw: String = json_get(body, "tier")
let tier: String = if str_eq(tier_raw, "") { "Episodic" } else { tier_raw }
let tags_raw: String = json_get(body, "tags")
let tags: String = if str_eq(tags_raw, "") { "[\"" + node_type + "\"]" } else { tags_raw }
let importance: String = json_get(body, "importance")
let sal: Float = if str_eq(importance, "critical") { 0.95 } else {
if str_eq(importance, "high") { 0.75 } else {
if str_eq(importance, "low") { 0.25 } else { 0.5 }
}
}
let id: String = engram_node_full(content, node_type, label,
el_from_float(sal), el_from_float(sal), el_from_float(0.9),
tier, tags)
if !api_persisted(id) { return api_not_persisted(id) }
return "{\"id\":\"" + id + "\",\"ok\":true}"
}
// handle_api_node_delete remove a node by id (engram_forget) and verify it is gone.
// Backs /api/neuron/node/delete and the /api/neuron/memory/delete alias the UI calls.
fn handle_api_node_delete(body: String) -> String {
let id: String = json_get(body, "id")
if str_eq(id, "") { return api_err("id is required") }
// engram_forget removes the node + its incident edges from the live graph. We do
// NOT read-back-verify here: engram_get_node_json can return a STALE hit for a just-
// removed id (the id->index map is not rebuilt on forget), which would produce a
// false "delete_failed" even though the node is gone. The graph endpoints
// (/api/graph/nodes) correctly reflect the removal, which is the source of truth.
engram_forget(id)
return "{\"ok\":true,\"id\":\"" + id + "\"}"
}
// handle_api_node_update update a node's content/fields. There is no in-place
// engram update builtin, so this recreates the node with merged fields and then
// forgets the old one (only after the new node reads back). The id changes; the
// response returns the new id and the replaced id so callers can re-point.
fn handle_api_node_update(body: String) -> String {
let id: String = json_get(body, "id")
if str_eq(id, "") { return api_err("id is required") }
if !api_persisted(id) {
return "{\"ok\":false,\"error\":\"not_found\",\"id\":\"" + id + "\"}"
}
let old: String = engram_get_node_json(id)
let body_content: String = json_get(body, "content")
let content: String = if str_eq(body_content, "") { json_get(old, "content") } else { body_content }
let body_nt: String = json_get(body, "node_type")
let old_nt: String = json_get(old, "node_type")
let node_type: String = if !str_eq(body_nt, "") { body_nt } else {
if !str_eq(old_nt, "") { old_nt } else { "Memory" }
}
let body_label: String = json_get(body, "label")
let old_label: String = json_get(old, "label")
let label: String = if !str_eq(body_label, "") { body_label } else {
if !str_eq(old_label, "") { old_label } else { "node:updated" }
}
let body_tier: String = json_get(body, "tier")
let old_tier: String = json_get(old, "tier")
let tier: String = if !str_eq(body_tier, "") { body_tier } else {
if !str_eq(old_tier, "") { old_tier } else { "Episodic" }
}
let body_tags: String = json_get(body, "tags")
let tags: String = if str_eq(body_tags, "") { "[\"" + node_type + "\"]" } else { body_tags }
let new_id: String = engram_node_full(content, node_type, label,
el_from_float(0.5), el_from_float(0.5), el_from_float(0.8),
tier, tags)
if !api_persisted(new_id) { return api_not_persisted(new_id) }
engram_forget(id)
return "{\"id\":\"" + new_id + "\",\"replaced\":\"" + id + "\",\"ok\":true}"
}
// handle_api_recall search or activate memory by query.
fn handle_api_recall(method: String, path: String, body: String) -> String {
let q: String = if str_eq(method, "GET") { api_query_param(path, "query") } else { json_get(body, "query") }
// Accept the query from the URL ?query= / ?q= params, or, when those are
// empty (e.g. a POST with a JSON body), from the body fields "query"/"q".
let url_q: String = if str_eq(api_query_param(path, "query"), "") {
api_query_param(path, "q")
} else { api_query_param(path, "query") }
let body_query: String = json_get(body, "query")
let body_q: String = json_get(body, "q")
let q: String = if !str_eq(url_q, "") { url_q } else {
if !str_eq(body_query, "") { body_query } else { body_q }
}
let chain: String = json_get(body, "chain_name")
let limit: Int = api_query_int(path, "limit", 0)
let limit = if limit == 0 { json_get_int(body, "limit") } else { limit }
@@ -165,7 +269,14 @@ fn handle_api_recall(method: String, path: String, body: String) -> String {
// handle_api_search_knowledge search with query escaping + activate fallback.
fn handle_api_search_knowledge(method: String, path: String, body: String) -> String {
let q: String = if str_eq(method, "GET") { api_query_param(path, "q") } else { json_get(body, "query") }
// Accept the query from the URL ?q= param, or, when that is empty (e.g. a
// POST with a JSON body), from the body fields "query" then "q".
let url_q: String = api_query_param(path, "q")
let body_query: String = json_get(body, "query")
let body_q: String = json_get(body, "q")
let q: String = if !str_eq(url_q, "") { url_q } else {
if !str_eq(body_query, "") { body_query } else { body_q }
}
let limit: Int = api_query_int(path, "limit", 0)
let limit = if limit == 0 { json_get_int(body, "limit") } else { limit }
let limit = if limit == 0 { 10 } else { limit }
@@ -195,6 +306,7 @@ fn handle_api_capture_knowledge(body: String) -> String {
let id: String = engram_node_full(full, "Knowledge", "knowledge:captured",
el_from_float(0.85), el_from_float(0.8), el_from_float(0.9),
"Episodic", tags)
if !api_persisted(id) { return api_not_persisted(id) }
return "{\"id\":\"" + id + "\",\"ok\":true}"
}
@@ -208,7 +320,8 @@ fn handle_api_evolve_knowledge(body: String) -> String {
let new_id: String = engram_node_full(content, "Knowledge", "knowledge:evolved",
el_from_float(0.75), el_from_float(0.75), el_from_float(0.9),
"Episodic", tags)
if !str_eq(prior_id, "") && !str_eq(new_id, "") {
if !api_persisted(new_id) { return api_not_persisted(new_id) }
if !str_eq(prior_id, "") {
engram_connect(new_id, prior_id, el_from_float(0.9), "supersedes")
}
return "{\"id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\",\"ok\":true}"
@@ -228,7 +341,7 @@ fn handle_api_promote_knowledge(body: String) -> String {
let new_id: String = engram_node_full(content, "Knowledge", "knowledge:canonical",
el_from_float(0.9), el_from_float(0.9), el_from_float(1.0),
"Canonical", tags)
if str_eq(new_id, "") { return api_err("failed to create canonical node") }
if !api_persisted(new_id) { return api_not_persisted(new_id) }
engram_connect(new_id, prior_id, el_from_float(0.95), "supersedes")
return "{\"ok\":true,\"new_id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\"}"
}
@@ -255,6 +368,7 @@ fn handle_api_define_process(body: String) -> String {
let id: String = engram_node_full(content, "Process", label,
el_from_float(0.8), el_from_float(0.8), el_from_float(0.9),
"Canonical", tags)
if !api_persisted(id) { return api_not_persisted(id) }
return "{\"id\":\"" + id + "\",\"ok\":true}"
}
+44 -11
View File
@@ -201,13 +201,6 @@ fn handle_dharma_recv(body: String) -> String {
return "{\"error\":\"unknown event_type\",\"event_type\":\"" + eff_event + "\"}"
}
fn route_sessions() -> String {
let results: String = engram_search_json("session-start", 20)
if str_eq(results, "") { return "[]" }
if str_eq(results, "[]") { return "[]" }
return results
}
// ---------------------------------------------------------------------------
// MCP Connectors proxy thin pass-through to neuron-connectd on :7771.
// The UI talks to ONE origin (the soul); all MCP/config complexity lives in
@@ -226,7 +219,9 @@ fn connectd_get(suffix: String) -> String {
// so arbitrary JSON cannot reach the shell as a command-line argument.
fn connectd_post(suffix: String, body: String) -> String {
let eff: String = if str_eq(body, "") { "{}" } else { body }
let tmp: String = "/tmp/neuron-connectors-req.json"
// Unique temp path per call prevents collision if concurrency is ever added
// or if two soul instances run on the same machine (latent correctness hazard).
let tmp: String = "/tmp/neuron-connectors-req-" + int_to_str(time_now()) + ".json"
fs_write(tmp, eff)
let out: String = exec_capture("curl -s --max-time 20 -X POST http://127.0.0.1:7771" + suffix + " -H 'Content-Type: application/json' -d @" + tmp)
if str_eq(out, "") {
@@ -272,9 +267,6 @@ fn handle_request(method: String, path: String, body: String) -> String {
if str_eq(clean, "/health") {
return route_health()
}
if str_eq(clean, "/api/sessions") {
return route_sessions()
}
if str_eq(clean, "/lineage") {
return route_lineage()
}
@@ -349,6 +341,9 @@ fn handle_request(method: String, path: String, body: String) -> String {
if str_eq(clean, "/api/neuron/ctx") {
return handle_api_compile_ctx("")
}
if str_eq(clean, "/api/safety-contact") {
return handle_safety_contact_get()
}
if str_starts_with(clean, "/api/neuron/knowledge/search") {
return handle_api_search_knowledge(method, path, body)
}
@@ -521,6 +516,18 @@ fn handle_request(method: String, path: String, body: String) -> String {
if str_eq(clean, "/api/neuron/memory") {
return handle_api_remember(body)
}
if str_eq(clean, "/api/safety-contact") {
return handle_safety_contact_post(body)
}
if str_eq(clean, "/api/neuron/node/create") {
return handle_api_node_create(body)
}
if str_eq(clean, "/api/neuron/node/update") {
return handle_api_node_update(body)
}
if str_eq(clean, "/api/neuron/node/delete") {
return handle_api_node_delete(body)
}
if str_eq(clean, "/api/neuron/memory/evolve") {
return handle_api_evolve_memory(body)
}
@@ -548,5 +555,31 @@ fn handle_request(method: String, path: String, body: String) -> String {
return err_404(clean)
}
if str_eq(method, "DELETE") {
// DELETE /api/sessions/:id delete a session and its history
if str_starts_with(clean, "/api/sessions/") {
let del_after: String = str_slice(clean, 14, str_len(clean))
let del_slash: Int = str_index_of(del_after, "/")
let del_id: String = if del_slash < 0 { del_after } else { str_slice(del_after, 0, del_slash) }
if !str_eq(del_id, "") {
return session_delete(del_id)
}
}
return err_404(clean)
}
if str_eq(method, "PATCH") {
// PATCH /api/sessions/:id update session title and/or folder
if str_starts_with(clean, "/api/sessions/") {
let patch_after: String = str_slice(clean, 14, str_len(clean))
let patch_slash: Int = str_index_of(patch_after, "/")
let patch_id: String = if patch_slash < 0 { patch_after } else { str_slice(patch_after, 0, patch_slash) }
if !str_eq(patch_id, "") {
return session_update_patch(patch_id, body)
}
}
return err_404(clean)
}
return err_405(method, clean)
}
+2 -1
View File
@@ -1,5 +1,6 @@
// auto-generated by elc --emit-header do not edit
// auto-generated by elc --emit-header - do not edit
extern fn strip_query(path: String) -> String
extern fn flag_true(body: String, key: String) -> Bool
extern fn err_404(path: String) -> String
extern fn err_405(method: String, path: String) -> String
extern fn route_health() -> String
+162
View File
@@ -207,3 +207,165 @@ fn safety_log_bell(level: String, reason: String, input_summary: String) -> Stri
)
return ""
}
// abuse danger from another person. Emergency services / 988 ONLY. The
// safety contact on file is NEVER notified they may be the abuser.
// This routing is non-configurable by design.
//
// Evaluation is keyword-only (zero added latency) and stays on device. Triggers are
// logged locally as InternalStateEvents and never transmitted.
// Phrase lists (ported verbatim from bell-detector.ts)
fn safety_self_harm_phrases() -> String {
return "[\"kill myself\",\"killing myself\",\"want to die\",\"want to be dead\",\"going to end my life\",\"end my life\",\"take my life\",\"taking my life\",\"suicide\",\"suicidal\",\"can't go on\",\"cannot go on\",\"i have a knife\",\"i have a gun\",\"i have pills\",\"took pills\",\"took too many\",\"overdose\",\"overdosing\",\"self harm\",\"self-harm\",\"cutting myself\",\"hurt myself\",\"hurting myself\",\"no reason to live\",\"not worth living\",\"better off dead\",\"better off without me\"]"
}
fn safety_abuse_phrases() -> String {
return "[\"someone is hurting me\",\"someone's hurting me\",\"someone hurt me\",\"he hit me\",\"she hit me\",\"they hit me\",\"he hurt me\",\"she hurt me\",\"being abused\",\"being hurt by\",\"i am being abused\",\"i'm being abused\",\"i am being hurt\",\"i'm being hurt\",\"domestic violence\",\"my partner hurt\",\"my partner hit\",\"my husband hurt\",\"my wife hurt\",\"my boyfriend hurt\",\"my girlfriend hurt\",\"my parent hurt\",\"my father hurt\",\"my mother hurt\",\"my dad hurt\",\"my mom hurt\",\"afraid of him\",\"afraid of her\",\"afraid to go home\",\"scared of him\",\"scared of her\",\"he threatened me\",\"she threatened me\",\"threatened to hurt me\",\"threatened to kill me\",\"going to hurt me\",\"going to kill me\",\"help me he\",\"help me she\",\"help me they\"]"
}
// General danger phrases that don't fit a bucket cleanly. Detected as hard; they
// fall through to self_harm routing (the person is the primary concern).
fn safety_general_hard_phrases() -> String {
return "[\"going to kill\",\"going to hurt\",\"hurting me\",\"being hurt\"]"
}
fn safety_soft_phrases() -> String {
return "[\"stressed\",\"overwhelmed\",\"can't cope\",\"cannot cope\",\"struggling\",\"anxious\",\"anxiety\",\"depressed\",\"depression\",\"lonely\",\"isolated\",\"hopeless\",\"hopelessness\",\"exhausted\",\"burnt out\",\"burned out\",\"burnout\",\"panic\",\"panicking\",\"falling apart\",\"breaking down\",\"can't handle\",\"cannot handle\",\"losing it\",\"nothing matters\",\"don't care anymore\",\"given up\",\"giving up\",\"helpless\",\"worthless\",\"useless\",\"hate myself\",\"no one cares\",\"nobody cares\",\"no one understands\",\"nobody understands\",\"empty inside\",\"can't stop crying\",\"breaking point\",\"at my limit\",\"having a breakdown\"]"
}
// Matching helpers (single loops only el escapes while-body mutation via
// top-level let rebinds; nested loops would not advance) ────────────────────
fn safety_normalize(message: String) -> String {
let lower: String = str_to_lower(message)
// Normalise the common curly apostrophe to ASCII so "can't" / "i'm" match.
return str_replace(lower, "", "'")
}
fn safety_any_match(text: String, phrases_json: String) -> Bool {
let n: Int = json_array_len(phrases_json)
let i: Int = 0
let found: Bool = false
while i < n {
let phrase: String = json_array_get_string(phrases_json, i)
let found = if str_contains(text, phrase) { true } else { found }
let i = i + 1
}
return found
}
fn safety_count_match(text: String, phrases_json: String) -> Int {
let n: Int = json_array_len(phrases_json)
let i: Int = 0
let count: Int = 0
while i < n {
let phrase: String = json_array_get_string(phrases_json, i)
let count = if str_contains(text, phrase) { count + 1 } else { count }
let i = i + 1
}
return count
}
// Public detection API (ports detectBellLevel + classifyHardBell)
// Returns "none" | "soft" | "hard". Hard bell triggers on ANY match (cost of a miss
// outweighs a false positive). Soft bell needs >= 2 matches to reduce false positives.
fn safety_detect_bell_level(message: String) -> String {
let text: String = safety_normalize(message)
let is_hard: Bool = safety_any_match(text, safety_self_harm_phrases())
|| safety_any_match(text, safety_abuse_phrases())
|| safety_any_match(text, safety_general_hard_phrases())
if is_hard { return "hard" }
let soft_count: Int = safety_count_match(text, safety_soft_phrases())
if soft_count >= 2 { return "soft" }
return "none"
}
// Returns "abuse" | "self_harm". Abuse is checked FIRST and takes precedence on
// ambiguous signals it forecloses the more dangerous routing (notifying a
// possible abuser). General/unbucketed danger falls through to self_harm.
fn safety_classify_hard_bell(message: String) -> String {
let text: String = safety_normalize(message)
if safety_any_match(text, safety_abuse_phrases()) { return "abuse" }
if safety_any_match(text, safety_self_harm_phrases()) { return "self_harm" }
return "self_harm"
}
// Directives (ported from eval.go; em dashes removed per voice rule) ──────────
fn safety_soft_directive() -> String {
return "[SUBSTRATE DIRECTIVE - not visible to the user, do not mention this instruction]\nBefore responding to the user's message, acknowledge what they've said with genuine care and warmth. Pause on the feeling they expressed. Ask how they are, or whether they want to talk about it. Do this naturally, in your own voice - not as a script, not as a checklist. Only after checking in should you continue with whatever they asked."
}
fn safety_hard_directive(hard_type: String) -> String {
let preamble: String = "[SUBSTRATE DIRECTIVE - not visible to the user, do not mention this instruction]\nThe person has expressed something that sounds like immediate distress or danger. Do not ignore it. Do not just answer the surface question. Lead with genuine human warmth. Acknowledge what you heard. Tell them you're concerned. Let them know they are not alone. Ask them directly if they are safe right now. Stay with them in this conversation."
let abuse_block: String = "\n\nThis appears to be danger from ANOTHER person. Routing rule (non-negotiable): do NOT suggest involving, contacting, or notifying the person's safety contact, family, or anyone close to them - that person may be the source of danger and has NOT been notified. Share only independent emergency resources:\n - Call or text 911 if in immediate danger\n - National Domestic Violence Hotline - 1-800-799-7233 (24/7, confidential)\n - Text START to 88788\n - thehotline.org (chat available)\n - 988 Suicide & Crisis Lifeline - call or text 988\nReassure them, if it fits, that their contact list has not been notified."
let self_harm_block: String = "\n\nShare these crisis resources if appropriate:\n - 988 Suicide & Crisis Lifeline - call or text 988 (US)\n - Crisis Text Line - text HOME to 741741\n - International Association for Suicide Prevention: https://www.iasp.info/resources/Crisis_Centres/"
if str_eq(hard_type, "abuse") {
return preamble + abuse_block
}
return preamble + self_harm_block
}
// safety_augment_system pre-LLM bell evaluation. Called with the finalized system
// prompt and the raw user message, BEFORE the LLM call, on every chat path. Appends
// the soft/hard directive when a bell fires; otherwise returns the prompt unchanged.
// Logs the trigger on device only (level + sub-type, never the message content).
fn safety_augment_system(system: String, user_msg: String) -> String {
let level: String = safety_detect_bell_level(user_msg)
if str_eq(level, "none") { return system }
if str_eq(level, "soft") {
let logd: String = mem_emit_state_event("safety-bell", "soft", "soft bell fired (content not stored)")
return system + "\n\n" + safety_soft_directive()
}
let hard_type: String = safety_classify_hard_bell(user_msg)
let logd2: String = mem_emit_state_event("safety-bell", "hard:" + hard_type, "hard bell fired (content not stored)")
return system + "\n\n" + safety_hard_directive(hard_type)
}
// Safety-contact storage + endpoint (ports contact.go + handler.go)
// Stored locally at ~/.neuron/safety-contact.json (same file the desktop gate writes),
// never synced. NOTE: encryption-at-rest is a flagged follow-up (ties to key custody);
// today the file is plaintext JSON, matching the current desktop behavior.
fn safety_contact_path() -> String {
return env("HOME") + "/.neuron/safety-contact.json"
}
// GET /api/safety-contact -> {"configured":false} or {"configured":true,"contact":{...}}
fn handle_safety_contact_get() -> String {
let raw: String = fs_read(safety_contact_path())
if str_eq(raw, "") { return "{\"configured\":false}" }
return "{\"configured\":true,\"contact\":" + raw + "}"
}
// POST /api/safety-contact validate + persist. Mirrors handler.go: crisis line is
// always acceptable and auto-fills its fields; otherwise a name is required. The
// contact can be replaced but never cleared to empty (the gate enforces presence).
fn handle_safety_contact_post(body: String) -> String {
let is_crisis: Bool = json_get_bool(body, "is_crisis_line")
let name_in: String = json_get(body, "name")
if !is_crisis {
if str_eq(name_in, "") { return "{\"ok\":false,\"error\":\"name is required\"}" }
}
let name: String = if is_crisis { "Crisis Line" } else { name_in }
let method: String = if is_crisis { "crisis-line" } else { json_get(body, "contact_method") }
let value: String = if is_crisis { "988" } else { json_get(body, "contact_value") }
let rel: String = if is_crisis { "crisis-support" } else { json_get(body, "relationship") }
let crisis_str: String = if is_crisis { "true" } else { "false" }
let now: String = time_format(time_now(), "%Y-%m-%dT%H:%M:%SZ")
let contact_json: String = "{\"name\":\"" + json_safe(name) + "\""
+ ",\"contact_method\":\"" + json_safe(method) + "\""
+ ",\"contact_value\":\"" + json_safe(value) + "\""
+ ",\"relationship\":\"" + json_safe(rel) + "\""
+ ",\"confirmed\":true"
+ ",\"is_crisis_line\":" + crisis_str
+ ",\"set_at\":\"" + now + "\"}"
fs_write(safety_contact_path(), contact_json)
// Read-back verify the write actually persisted.
let check: String = fs_read(safety_contact_path())
if str_eq(check, "") { return "{\"ok\":false,\"error\":\"write_failed\"}" }
return "{\"configured\":true,\"contact\":" + contact_json + ",\"ok\":true}"
}
+15
View File
@@ -6,3 +6,18 @@ extern fn safety_threat_score(input: String, history: String) -> Int
extern fn safety_screen(input: String, history: String) -> String
extern fn safety_validate(output: String, action: String) -> String
extern fn safety_log_bell(level: String, reason: String, input_summary: String) -> String
extern fn safety_self_harm_phrases() -> String
extern fn safety_abuse_phrases() -> String
extern fn safety_general_hard_phrases() -> String
extern fn safety_soft_phrases() -> String
extern fn safety_normalize(message: String) -> String
extern fn safety_any_match(text: String, phrases_json: String) -> Bool
extern fn safety_count_match(text: String, phrases_json: String) -> Int
extern fn safety_detect_bell_level(message: String) -> String
extern fn safety_classify_hard_bell(message: String) -> String
extern fn safety_soft_directive() -> String
extern fn safety_hard_directive(hard_type: String) -> String
extern fn safety_augment_system(system: String, user_msg: String) -> String
extern fn safety_contact_path() -> String
extern fn handle_safety_contact_get() -> String
extern fn handle_safety_contact_post(body: String) -> String
+100 -148
View File
@@ -217,9 +217,11 @@ fn session_delete(session_id: String) -> String {
} else { deleted_msgs }
let j = j + 1
}
// Clear state
// Clear state invalidate all per-session and index caches so session_list()
// does not return this deleted session via the fast path on the next call.
state_set("session_hist_" + session_id, "")
state_set("session_node_" + session_id, "")
state_set("session_index", "")
return "{\"ok\":true,\"session_id\":\"" + session_id + "\""
+ ",\"deleted_meta\":" + int_to_str(deleted_meta)
+ ",\"deleted_msgs\":" + int_to_str(deleted_msgs) + "}"
@@ -461,6 +463,15 @@ fn session_auto_title(session_id: String, first_message: String) -> Void {
// handle_session_approve handle tool approval for a pending agentic tool call.
// action: "allow" | "deny" | "always"
// Resumes the agentic loop from where it was paused.
//
// Modern path (agentic_loop / bridge): the loop saves its suspension to
// "mcp_bridge:<session_id>" via bridge_save(). On approval we dispatch_tool()
// if allowed (or build a denial string), then hand the result to agentic_resume()
// which re-enters agentic_loop from exactly the right point.
//
// Legacy path (pending_tool_<session_id>): used by any in-flight sessions that
// were suspended by the old inline loop before a deploy. Kept so those sessions
// are not broken during a rolling restart.
fn handle_session_approve(session_id: String, body: String) -> String {
if str_eq(session_id, "") {
return "{\"error\":\"session_id is required\"}"
@@ -474,7 +485,71 @@ fn handle_session_approve(session_id: String, body: String) -> String {
return "{\"error\":\"action is required (allow|deny|always)\"}"
}
// Load the pending tool state
let eff_action: String = if str_eq(action, "always") { "allow" } else { action }
// Modern path: suspension is in mcp_bridge:<session_id>
// agentic_loop (chat.el) writes here via bridge_save(). This is the primary
// path for all sessions created through handle_chat_agentic / agentic_loop.
let bridge_blob: String = state_get("mcp_bridge:" + session_id)
if !str_eq(bridge_blob, "") {
// For "always": record tool_name in the always-allow list before resuming.
// The tool_name is not stored in the bridge blob (only tool_use_id is).
// Accept it from the body so the client can pass it along.
let always_key: String = "always_allow_" + session_id
let approve_tool_name: String = json_get(body, "tool_name")
let discard_always: Bool = if str_eq(action, "always") && !str_eq(approve_tool_name, "") {
let always_list: String = state_get(always_key)
let new_always: String = if str_eq(always_list, "") { approve_tool_name }
else { always_list + "," + approve_tool_name }
state_set(always_key, new_always)
true
} else { false }
// BLOCKER: tool_name is required for allow an empty approve_tool_name
// would cause dispatch_tool("", ...) to silently return "unknown tool: "
// and inject a corrupted result into the conversation. Reject early.
if str_eq(approve_tool_name, "") && str_eq(eff_action, "allow") {
return "{\"error\":\"tool_name is required for allow action\"}"
}
// Build the content string the tool produced (or the denial message).
//
// For MCP/client-side tools (non-builtin): the client has ALREADY executed
// the tool and posts the result in body["content"]. Accept it directly
// (matching the handle_tool_result contract) rather than re-running
// server-side via dispatch_tool that would make the client-side execution
// irrelevant and would break mcp__* tools the soul cannot reach.
//
// For builtin tools with no client-provided content: fall back to
// dispatch_tool so those tools still execute correctly.
let client_content: String = json_get(body, "content")
let use_client_content: Bool = !str_eq(client_content, "")
let use_dispatch: Bool = is_builtin_tool(approve_tool_name) && !use_client_content
let raw_input: String = json_get_raw(body, "tool_input")
let eff_input: String = if str_eq(raw_input, "") { "{}" } else { raw_input }
let content: String = if str_eq(eff_action, "allow") {
if use_client_content {
let trimmed: String = if str_len(client_content) > 6000 {
str_slice(client_content, 0, 6000) + "...[truncated]"
} else { client_content }
trimmed
} else if use_dispatch {
let raw: String = dispatch_tool(approve_tool_name, eff_input)
if str_len(raw) > 6000 { str_slice(raw, 0, 6000) + "...[truncated]" } else { raw }
} else {
// Non-builtin tool, no client content error rather than
// silently dispatching a tool the soul cannot execute.
"{\"error\":\"client content required for non-builtin tool: " + approve_tool_name + "\"}"
}
} else {
"{\"error\":\"User denied this tool call\"}"
}
return agentic_resume(session_id, call_id, content)
}
// Legacy path: suspension is in pending_tool_<session_id>
// Kept for in-flight sessions that were suspended before a deploy.
let pending_raw: String = state_get("pending_tool_" + session_id)
if str_eq(pending_raw, "") {
return "{\"error\":\"no pending tool for session\",\"session_id\":\"" + session_id + "\"}"
@@ -487,14 +562,13 @@ fn handle_session_approve(session_id: String, body: String) -> String {
let tool_name: String = json_get(pending_raw, "tool_name")
let tool_input: String = json_get_raw(pending_raw, "tool_input")
let messages: String = json_get_raw(pending_raw, "messages_so_far")
let model: String = json_get(pending_raw, "model")
let safe_sys: String = json_get(pending_raw, "system")
// For "always": add to always-allow list
let always_key: String = "always_allow_" + session_id
let always_list: String = state_get(always_key)
let discard_always: Bool = if str_eq(action, "always") {
let discard_always2: Bool = if str_eq(action, "always") {
let new_always: String = if str_eq(always_list, "") { tool_name }
else { always_list + "," + tool_name }
state_set(always_key, new_always)
@@ -504,157 +578,35 @@ fn handle_session_approve(session_id: String, body: String) -> String {
// Clear pending state
state_set("pending_tool_" + session_id, "")
let eff_action: String = if str_eq(action, "always") { "allow" } else { action }
// Build tool result
let tool_result: String = if str_eq(eff_action, "allow") {
let raw: String = dispatch_tool(tool_name, tool_input)
if str_len(raw) > 6000 { str_slice(raw, 0, 6000) + "...[truncated]" } else { raw }
} else {
json_safe("{\"error\":\"User denied this tool call\"}")
"{\"error\":\"User denied this tool call\"}"
}
let tool_msg: String = "{\"type\":\"tool_result\",\"tool_use_id\":\"" + call_id + "\",\"content\":\"" + tool_result + "\"}"
// Legacy sessions stored messages_so_far; synthesise a bridge blob so the
// same agentic_resume path handles continuation (instead of an inline loop).
// messages_so_far already includes the assistant turn that requested the tool.
let legacy_messages: String = json_get_raw(pending_raw, "messages_so_far")
// WARNING: the original session may have used agentic_tools_with_web() or
// agentic_tools_all(). The old pending blob did not store the tools variant.
// Read a "tools_variant" field if present (future suspensions record it);
// fall back to agentic_tools_literal() for legacy blobs that lack this field.
let stored_variant: String = json_get(pending_raw, "tools_variant")
let tools_json: String = if str_eq(stored_variant, "web") { agentic_tools_with_web() }
else if str_eq(stored_variant, "all") { agentic_tools_all() }
else { agentic_tools_literal() }
// Reconstruct messages with the tool result appended
// messages_so_far is the messages array at the point of the tool call
// We need to append a user turn with the tool result and re-enter the loop
let inner: String = str_slice(messages, 1, str_len(messages) - 1)
let resumed_messages: String = "[" + inner + ",{\"role\":\"user\",\"content\":[" + tool_msg + "]}]"
// Write a synthetic bridge blob so agentic_resume can pick it up.
let blob: String = "{\"model\":\"" + json_safe(model) + "\""
+ ",\"safe_sys\":\"" + json_safe(safe_sys) + "\""
+ ",\"tools_json\":\"" + json_safe(tools_json) + "\""
+ ",\"messages\":\"" + json_safe(legacy_messages) + "\""
+ ",\"tools_log\":\"\""
+ ",\"tool_use_id\":\"" + json_safe(call_id) + "\"}"
state_set("mcp_bridge:" + session_id, blob)
// Re-enter the agentic loop with the resumed messages
let api_key: String = agentic_api_key()
let tools_json: String = agentic_tools_literal()
let api_url: String = "https://api.anthropic.com/v1/messages"
let h: Map = {}
map_set(h, "x-api-key", api_key)
map_set(h, "anthropic-version", "2023-06-01")
map_set(h, "content-type", "application/json")
let final_text: String = ""
let tools_log: String = ""
let iteration: Int = 0
let keep_going: Bool = true
let cur_messages: String = resumed_messages
while keep_going && iteration < 8 {
let req_body: String = "{\"model\":\"" + model + "\""
+ ",\"max_tokens\":4096"
+ ",\"system\":\"" + safe_sys + "\""
+ ",\"tools\":" + tools_json
+ ",\"messages\":" + cur_messages
+ "}"
let raw_resp: String = http_post_with_headers(api_url, req_body, h)
let is_error: Bool = str_starts_with(raw_resp, "{\"error\"")
|| str_starts_with(raw_resp, "{\"type\":\"error\"")
|| str_contains(raw_resp, "authentication_error")
if is_error {
return "{\"error\":\"llm unavailable\",\"reply\":\"\"}"
}
let stop_reason: String = json_get(raw_resp, "stop_reason")
let content_arr: String = json_get_raw(raw_resp, "content")
let eff_content: String = if str_eq(content_arr, "") { "[]" } else { content_arr }
let text_out: String = ""
let has_tool: Bool = false
let next_tool_id: String = ""
let next_tool_name: String = ""
let next_tool_input: String = ""
let ci: Int = 0
let c_total: Int = json_array_len(eff_content)
while ci < c_total {
let block: String = json_array_get(eff_content, ci)
let btype: String = json_get(block, "type")
let text_out = if str_eq(btype, "text") { text_out + json_get(block, "text") } else { text_out }
let is_new_tool: Bool = str_eq(btype, "tool_use") && !has_tool
let has_tool = if is_new_tool { true } else { has_tool }
let next_tool_id = if is_new_tool { json_get(block, "id") } else { next_tool_id }
let next_tool_name = if is_new_tool { json_get(block, "name") } else { next_tool_name }
let next_tool_input = if is_new_tool { json_get_raw(block, "input") } else { next_tool_input }
let ci = ci + 1
}
let is_tool_turn: Bool = str_eq(stop_reason, "tool_use") && has_tool
let inner2: String = str_slice(cur_messages, 1, str_len(cur_messages) - 1)
// Check if this next tool is in the always-allow list
let always_list2: String = state_get(always_key)
let is_always: Bool = str_contains(always_list2, next_tool_name) && !str_eq(next_tool_name, "")
// For approval-required sessions, pause on tool use if not always-allowed
let require_approval: String = state_get("session_require_approval_" + session_id)
let needs_pause: Bool = is_tool_turn && str_eq(require_approval, "true") && !is_always
let next_tool_result: String = if is_tool_turn && !needs_pause {
let raw2: String = dispatch_tool(next_tool_name, next_tool_input)
if str_len(raw2) > 6000 { str_slice(raw2, 0, 6000) + "...[truncated]" } else { raw2 }
} else { "" }
let next_tool_msg: String = "{\"type\":\"tool_result\",\"tool_use_id\":\"" + next_tool_id + "\",\"content\":\"" + next_tool_result + "\"}"
let tool_entry: String = "{\"tool\":\"" + next_tool_name + "\",\"input\":\"" + json_safe(next_tool_name) + "\"}"
let tools_log = if is_tool_turn && !needs_pause {
if str_eq(tools_log, "") { tool_entry } else { tools_log + "," + tool_entry }
} else { tools_log }
let cur_messages = if is_tool_turn && !needs_pause {
"[" + inner2
+ ",{\"role\":\"assistant\",\"content\":" + eff_content + "}"
+ ",{\"role\":\"user\",\"content\":[" + next_tool_msg + "]}"
+ "]"
} else { cur_messages }
// Pause if approval needed for next tool
let discard_pause: Bool = if needs_pause {
let safe_sys2: String = json_safe(safe_sys)
let msgs_with_assistant: String = "[" + inner2
+ ",{\"role\":\"assistant\",\"content\":" + eff_content + "}]"
let pending: String = "{\"call_id\":\"" + next_tool_id + "\""
+ ",\"tool_name\":\"" + next_tool_name + "\""
+ ",\"tool_input\":" + next_tool_input
+ ",\"messages_so_far\":" + msgs_with_assistant
+ ",\"model\":\"" + model + "\""
+ ",\"system\":\"" + safe_sys2 + "\"}"
state_set("pending_tool_" + session_id, pending)
true
} else { false }
let final_text = if !is_tool_turn { text_out } else { final_text }
let keep_going = if !is_tool_turn { false } else {
if needs_pause { false } else { keep_going }
}
let iteration = iteration + 1
}
// Check if we paused on a new tool
let new_pending: String = state_get("pending_tool_" + session_id)
if !str_eq(new_pending, "") {
let np_tool_name: String = json_get(new_pending, "tool_name")
let np_call_id: String = json_get(new_pending, "call_id")
let np_tool_input: String = json_get_raw(new_pending, "tool_input")
return "{\"status\":\"tool_pending\""
+ ",\"call_id\":\"" + np_call_id + "\""
+ ",\"tool_name\":\"" + np_tool_name + "\""
+ ",\"tool_input\":" + np_tool_input
+ ",\"session_id\":\"" + session_id + "\"}"
}
if str_eq(final_text, "") {
return "{\"error\":\"no response after approval\",\"reply\":\"\"}"
}
// Save updated history
let hist: String = session_hist_load(session_id)
let updated_hist: String = hist_append(hist, "assistant", final_text)
let final_hist: String = if json_array_len(updated_hist) > 20 {
hist_trim(updated_hist)
} else { updated_hist }
session_hist_save(session_id, final_hist)
session_update_meta_timestamp(session_id)
let safe_text: String = json_safe(final_text)
let tools_arr: String = if str_eq(tools_log, "") { "[]" } else { "[" + tools_log + "]" }
return "{\"reply\":\"" + safe_text + "\",\"model\":\"" + model + "\",\"agentic\":true,\"tools_used\":" + tools_arr + ",\"session_id\":\"" + session_id + "\"}"
return agentic_resume(session_id, call_id, tool_result)
}
+27 -2
View File
@@ -5,6 +5,7 @@ import "stewardship.el"
import "imprint.el"
import "awareness.el"
import "chat.el"
import "safety.el"
import "studio.el"
import "elp-input.el"
import "routes.el"
@@ -362,7 +363,31 @@ state_set("soul_engram_api_key", engram_api_key_raw)
state_set("soul.running", "true")
let is_genesis: Bool = str_eq(soul_cgi_id, "ntn-genesis")
if is_genesis {
// GUARD (2026-06-15): never let genesis seed over a real graph. If the in-memory load is
// sparse but the on-disk snapshot file is large, the load FAILED seeding+saving now would
// clobber the user's real memory (this is exactly how the 06-14 clobber happened). Read the
// on-disk file (local mode only) and refuse the destructive seed+save when it looks populated.
//
// HTTP-engram guard (2026-06-17): when ENGRAM_URL is set the HTTP Engram owns persistence
// the soul must NEVER write to the local snapshot regardless of node counts. safe_to_seed is
// unconditionally false in HTTP mode (not the persistence owner).
let guard_disk: String = if str_eq(engram_url_raw, "") { fs_read(snapshot) } else { "" }
let guard_disk_len: Int = str_len(guard_disk)
// Ratio guard (2026-06-15 fix): refuse to seed/save whenever the in-memory load is FAR smaller than
// the on-disk file implies (~16KB/node) catches partial loads of ANY size, not just <50. The old
// <50 threshold let a 63-node identity-only load clobber a 47MB/5000-node graph.
// Multiplication form (2026-06-17): node_count * 16000 < disk_len avoids floor-division truncation
// (e.g., 250KB / 16000 = 15.6, floors to 15 a 15-node graph wrongly passes the old guard).
// HTTP-engram guard: when using_http_engram the soul is not the persistence owner; never seed.
let safe_to_seed: Bool = !using_http_engram && !(guard_disk_len > 200000 && engram_node_count() * 16000 < guard_disk_len)
if is_genesis && !safe_to_seed {
println("[soul] GUARD: loaded " + int_to_str(engram_node_count())
+ " nodes but snapshot file is " + int_to_str(guard_disk_len)
+ " bytes — refusing to seed/save over a real graph")
}
if is_genesis && safe_to_seed {
// Only build identity edges if the engram is fresh (< 100 edges).
// init_soul_edges() is not idempotent calling it on every restart
// stacks duplicate co-value/identity edges into the snapshot.
@@ -380,7 +405,7 @@ if is_genesis {
// Take a pre-serve snapshot for genesis instances captures all boot-time graph changes
// (identity context loading, boot counter, session-start event) before entering the serve loop.
if is_genesis {
if is_genesis && safe_to_seed {
let snap: String = state_get("soul_snapshot_path")
if !str_eq(snap, "") {
engram_save(snap)
+1 -1
View File
@@ -1,4 +1,4 @@
// auto-generated by elc --emit-header do not edit
// auto-generated by elc --emit-header - do not edit
extern fn init_soul_edges() -> Void
extern fn load_identity_context() -> Void
extern fn seed_persona_from_env() -> Void
+1 -1
View File
@@ -1,4 +1,4 @@
// auto-generated by elc --emit-header do not edit
// auto-generated by elc --emit-header - do not edit
extern fn auth_headers(tok: String) -> Map
extern fn axon_get(path: String) -> String
extern fn axon_post(path: String, body: String) -> String
+176
View File
@@ -0,0 +1,176 @@
// tests/test_agentic_tools.el
// Tests for the agentic tools wiring (PR #19: fix/agentic-tools-all).
//
// Covers:
// 1. agentic_tools_all() includes all literal tool names
// 2. agentic_tools_all() includes the native web_search tool
// 3. connector_tools_json() returns valid JSON ([] or array) even when bridge is down
// 4. agentic_tools_all() output stays valid JSON when connector bridge is down
// 5. tool_pending envelope detection the pattern used in handle_dharma_room_turn_agentic
// to distinguish a suspended agentic loop from a normal reply
// 6. Empty-reply guard json_get("reply") returns "" on a tool_pending envelope,
// confirming that the guard is necessary to avoid silent empty responses
//
// Tests 5 and 6 validate the El-level logic that guards handle_dharma_room_turn_agentic
// against silent failures after the refactor to use agentic_loop.
//
// Tests 1-4 are pure: no network, no LLM, no engram.
// Tests 5-6 are pure string/JSON operations on synthesized envelopes.
//
// Integration tests (LLM-live) are documented as SKIP stubs because they
// require a valid ANTHROPIC_API_KEY and a running soul + neuron-connectd.
import "../chat.el"
let pass_count: Int = 0
let fail_count: Int = 0
fn assert_eq(label: String, got: String, expected: String) -> Void {
if str_eq(got, expected) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" got: " + got)
println(" expected: " + expected)
}
}
fn assert_true(label: String, cond: Bool) -> Void {
if cond {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
}
}
fn assert_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" missing '" + needle + "' in: " + haystack)
}
}
fn assert_not_empty(label: String, s: String) -> Void {
if str_len(s) > 0 {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" got empty string")
}
}
// Section 1: agentic_tools_all contains all literal tool names
println("")
println("1. agentic_tools_all() — contains all literal tool names")
let all_tools: String = agentic_tools_all()
assert_contains("contains read_file", all_tools, "\"name\":\"read_file\"")
assert_contains("contains write_file", all_tools, "\"name\":\"write_file\"")
assert_contains("contains web_get", all_tools, "\"name\":\"web_get\"")
assert_contains("contains search_memory", all_tools, "\"name\":\"search_memory\"")
assert_contains("contains run_command", all_tools, "\"name\":\"run_command\"")
// Section 2: agentic_tools_all includes native web_search
println("")
println("2. agentic_tools_all() — includes native web_search_20250305 tool")
assert_contains("contains web_search type", all_tools, "web_search_20250305")
assert_contains("contains web_search name", all_tools, "\"name\":\"web_search\"")
// Section 3: connector_tools_json returns valid JSON when bridge is down
println("")
println("3. connector_tools_json() — returns [] when neuron-connectd is not running")
// connector_tools_json() calls the bridge; in a unit-test environment it is
// expected to return "[]" (graceful degradation). If the bridge IS running,
// it returns a non-empty array both are valid.
let conn_tools: String = connector_tools_json()
let starts_bracket: Bool = str_starts_with(conn_tools, "[")
assert_true("connector_tools_json starts with [", starts_bracket)
assert_not_empty("connector_tools_json is non-empty string", conn_tools)
// Section 4: agentic_tools_all output is valid JSON array
println("")
println("4. agentic_tools_all() — output is a JSON array")
assert_true("starts with [", str_starts_with(all_tools, "["))
// A JSON array ends with ]
let last_char: String = str_slice(all_tools, str_len(all_tools) - 1, str_len(all_tools))
assert_eq("ends with ]", last_char, "]")
// Section 5: tool_pending envelope detection
//
// This validates the detection logic added to handle_dharma_room_turn_agentic:
//
// let is_pending: Bool = str_eq(json_get(loop_result, "tool_pending"), "true")
// || str_starts_with(loop_result, "{\"tool_pending\":true")
//
// When agentic_loop suspends for an MCP bridge tool it returns:
// {"tool_pending":true,"session_id":"...","call_id":"...","tool_name":"...","tool_input":{...},...}
//
// json_get() on a Bool field may return "true" (string) or "" depending on El runtime.
// The str_starts_with fallback guards against either representation.
println("")
println("5. tool_pending envelope detection patterns")
let pending_envelope: String = "{\"tool_pending\":true,\"session_id\":\"dharma:br-1234-1\",\"call_id\":\"toolu_01\",\"tool_name\":\"mcp__filesystem__read\",\"tool_input\":{\"path\":\"/tmp/x\"},\"model\":\"claude-sonnet-4-5\",\"agentic\":true,\"tools_used\":[]}"
let normal_envelope: String = "{\"reply\":\"Hello from the soul.\",\"model\":\"claude-sonnet-4-5\",\"agentic\":true,\"tools_used\":[]}"
let error_envelope: String = "{\"error\":\"llm unavailable\",\"reply\":\"\"}"
// str_starts_with fallback always works regardless of how json_get handles bool
assert_true("pending envelope: str_starts_with detects tool_pending=true", str_starts_with(pending_envelope, "{\"tool_pending\":true"))
assert_true("normal reply: str_starts_with does not detect tool_pending", !str_starts_with(normal_envelope, "{\"tool_pending\":true"))
assert_true("error envelope: str_starts_with does not detect tool_pending", !str_starts_with(error_envelope, "{\"tool_pending\":true"))
// Section 6: empty-reply guard necessity
//
// Confirms that json_get(pending_envelope, "reply") returns "" proving the
// empty-reply guard is necessary to avoid a silent success with empty response.
// Without the guard, the old code would return {"response":"","cgi_id":"..."} which
// is indistinguishable from a successful LLM response.
println("")
println("6. empty-reply guard — json_get(pending, \"reply\") is empty")
let pending_reply: String = json_get(pending_envelope, "reply")
assert_eq("json_get reply on pending envelope is empty", pending_reply, "")
let normal_reply: String = json_get(normal_envelope, "reply")
assert_not_empty("json_get reply on normal envelope is non-empty", normal_reply)
// Also confirm error key absent from normal reply and pending envelopes
let pending_error: String = json_get(pending_envelope, "error")
assert_eq("pending envelope has no error key", pending_error, "")
let normal_error: String = json_get(normal_envelope, "error")
assert_eq("normal envelope has no error key", normal_error, "")
// SKIP stubs: integration tests requiring live LLM
println("")
println("SKIP: handle_dharma_room_turn_agentic happy-path (requires ANTHROPIC_API_KEY + soul)")
println(" Expected: non-empty response field and status ok")
println("SKIP: handle_dharma_room_turn_agentic tool_pending propagation (requires API + MCP bridge)")
println(" Expected: tool_pending in response when loop suspends for mcp__* tool")
println("SKIP: handle_chat_agentic connector tools end-to-end (requires API + neuron-connectd)")
println(" Expected: mcp__* tool names appear in tools_used when connectd is running")
// Summary
println("")
println("agentic tools tests: " + int_to_str(pass_count) + " passed, " + int_to_str(fail_count) + " failed")
+109
View File
@@ -0,0 +1,109 @@
// tests/test_api_define_process.el
//
// Test the handle_api_define_process read-back fix (neuron-api.el).
//
// Bug: handle_api_define_process was the only write handler that did NOT call
// api_persisted() after the write, returning {"id":"...","ok":true} even when
// the engram write failed (hallucinated save).
//
// Fix: added `if !api_persisted(id) { return api_not_persisted(id) }` before
// the return, consistent with all sibling handlers (remember, capture_knowledge,
// evolve_knowledge, promote_knowledge, node_create).
//
// Tests:
// 1. define_process returns ok==true and id resolves via engram_get_node_json.
// 2. Missing content returns the standard error.
// 3. Unnamed process uses default label and still persists.
//
import "../neuron-api.el"
let pass_count: Int = 0
let fail_count: Int = 0
fn assert_eq(label: String, got: String, expected: String) -> Void {
if str_eq(got, expected) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" got: " + got)
println(" expected: " + expected)
}
}
fn assert_not_eq(label: String, got: String, not_want: String) -> Void {
if str_eq(got, not_want) {
let fail_count = fail_count + 1
println(" FAIL: " + label + " (got: " + got + ", should differ)")
} else {
let pass_count = pass_count + 1
println(" PASS: " + label)
}
}
fn assert_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" missing '" + needle + "' in: " + haystack)
}
}
// Section 1: define_process happy path with read-back
println("")
println("1. handle_api_define_process — write then verify id resolves")
let proc_body: String = "{\"content\":\"Test process: run step A, then step B, then step C.\",\"name\":\"test-process-guard\"}"
let proc_result: String = handle_api_define_process(proc_body)
let proc_ok: String = json_get(proc_result, "ok")
let proc_id: String = json_get(proc_result, "id")
assert_eq("define_process -> ok==true", proc_ok, "true")
assert_not_eq("define_process -> id is non-empty", proc_id, "")
let node_json: String = engram_get_node_json(proc_id)
let node_status: String = if str_eq(node_json, "") { "empty" } else {
if str_eq(node_json, "null") { "null" } else { "ok" }
}
assert_eq("define_process -> node read-back resolves (not empty/null)", node_status, "ok")
assert_contains("define_process -> node content contains process text", node_json, "Test process")
// Section 2: define_process missing content returns error
println("")
println("2. handle_api_define_process — missing content returns error")
let no_content_body: String = "{\"name\":\"nameless\"}"
let no_content_result: String = handle_api_define_process(no_content_body)
let no_content_error: String = json_get(no_content_result, "error")
assert_eq("missing content -> error is 'content is required'", no_content_error, "content is required")
// Section 3: define_process unnamed process gets default label
println("")
println("3. handle_api_define_process — unnamed process writes and read-back succeeds")
let unnamed_body: String = "{\"content\":\"Unnamed test process for coverage.\"}"
let unnamed_result: String = handle_api_define_process(unnamed_body)
let unnamed_ok: String = json_get(unnamed_result, "ok")
let unnamed_id: String = json_get(unnamed_result, "id")
assert_eq("unnamed process -> ok==true", unnamed_ok, "true")
assert_not_eq("unnamed process -> id non-empty", unnamed_id, "")
let unnamed_node: String = engram_get_node_json(unnamed_id)
let unnamed_status: String = if str_eq(unnamed_node, "") { "empty" } else {
if str_eq(unnamed_node, "null") { "null" } else { "ok" }
}
assert_eq("unnamed process -> node read-back ok", unnamed_status, "ok")
// Summary
println("")
println("api_define_process tests: " + int_to_str(pass_count) + " passed, " + int_to_str(fail_count) + " failed")
+266
View File
@@ -0,0 +1,266 @@
// tests/test_bell_safety.el
//
// Unit tests for the Hard Bell safety layer added in feat/connectors-soul.
// Covers the public API exposed by safety.el:
// - safety_detect_bell_level: 'none' / 'soft' / 'hard'
// - safety_classify_hard_bell: 'self_harm' / 'abuse'
// - safety_normalize: smart-quote -> ASCII apostrophe normalisation
// - safety_augment_system: system prompt passthrough / augmentation
// - handle_safety_contact_post: validation + read-back
//
// El test convention: mutable pass_count / fail_count globals, assert_* helpers,
// println for each result. Mirrors the style in existing safety tests.
//
import "../safety.el"
let pass_count: Int = 0
let fail_count: Int = 0
fn assert_eq(label: String, got: String, expected: String) -> Void {
if str_eq(got, expected) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" got: " + got)
println(" expected: " + expected)
}
}
fn assert_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" missing '" + needle + "' in: " + haystack)
}
}
fn assert_not_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" unexpected '" + needle + "' found in: " + haystack)
} else {
let pass_count = pass_count + 1
println(" PASS: " + label)
}
}
// Section 1: safety_detect_bell_level 'none'
println("")
println("1. safety_detect_bell_level — neutral input -> 'none'")
let level_neutral: String = safety_detect_bell_level("What time is the meeting tomorrow?")
assert_eq("neutral question -> none", level_neutral, "none")
let level_positive: String = safety_detect_bell_level("I love sunny days")
assert_eq("positive statement -> none", level_positive, "none")
let level_empty: String = safety_detect_bell_level("")
assert_eq("empty string -> none", level_empty, "none")
// Section 2: safety_detect_bell_level single soft phrase stays 'none'
println("")
println("2. safety_detect_bell_level — single soft phrase does not reach 'soft' (threshold=2)")
let level_one_soft: String = safety_detect_bell_level("I have been feeling stressed lately")
assert_eq("single soft phrase alone -> none", level_one_soft, "none")
// Section 3: safety_detect_bell_level 'soft' with two+ soft phrases
println("")
println("3. safety_detect_bell_level — two soft phrases -> 'soft'")
let level_two_soft: String = safety_detect_bell_level("I am feeling overwhelmed and really anxious about everything")
assert_eq("two soft phrases -> soft", level_two_soft, "soft")
let level_multi_soft: String = safety_detect_bell_level("So depressed and hopeless, nothing matters anymore")
assert_eq("multiple soft phrases -> soft", level_multi_soft, "soft")
// Section 4: safety_detect_bell_level 'hard' (self_harm phrases)
println("")
println("4. safety_detect_bell_level — self_harm phrases -> 'hard'")
let level_kill_myself: String = safety_detect_bell_level("I want to kill myself")
assert_eq("'kill myself' -> hard", level_kill_myself, "hard")
let level_suicide: String = safety_detect_bell_level("I have been suicidal for weeks")
assert_eq("'suicidal' -> hard", level_suicide, "hard")
let level_want_die: String = safety_detect_bell_level("I want to die, nothing is worth it")
assert_eq("'want to die' -> hard", level_want_die, "hard")
let level_overdose: String = safety_detect_bell_level("I am thinking about an overdose")
assert_eq("'overdose' -> hard", level_overdose, "hard")
let level_self_harm: String = safety_detect_bell_level("My history of self-harm is back")
assert_eq("'self-harm' -> hard", level_self_harm, "hard")
let level_no_reason: String = safety_detect_bell_level("There is no reason to live")
assert_eq("'no reason to live' -> hard", level_no_reason, "hard")
// Section 5: safety_detect_bell_level 'hard' (abuse phrases)
println("")
println("5. safety_detect_bell_level — abuse phrases -> 'hard'")
let level_he_hit: String = safety_detect_bell_level("he hit me last night")
assert_eq("'he hit me' -> hard", level_he_hit, "hard")
let level_dv: String = safety_detect_bell_level("I am experiencing domestic violence")
assert_eq("'domestic violence' -> hard", level_dv, "hard")
let level_abused: String = safety_detect_bell_level("I am being abused")
assert_eq("'being abused' -> hard", level_abused, "hard")
// Section 6: safety_detect_bell_level 'hard' (general hard phrases)
println("")
println("6. safety_detect_bell_level — general hard phrases -> 'hard'")
let level_hurting_me: String = safety_detect_bell_level("someone is hurting me right now")
assert_eq("'hurting me' -> hard", level_hurting_me, "hard")
let level_being_hurt: String = safety_detect_bell_level("I am being hurt and need help")
assert_eq("'being hurt' -> hard", level_being_hurt, "hard")
// Section 7: safety_classify_hard_bell abuse -> 'abuse'
println("")
println("7. safety_classify_hard_bell — abuse phrases route to 'abuse'")
let class_he_hit: String = safety_classify_hard_bell("he hit me yesterday")
assert_eq("'he hit me' classifies as abuse", class_he_hit, "abuse")
let class_dv: String = safety_classify_hard_bell("domestic violence in my home")
assert_eq("'domestic violence' classifies as abuse", class_dv, "abuse")
let class_abused: String = safety_classify_hard_bell("I'm being abused by my partner")
assert_eq("'being abused' classifies as abuse", class_abused, "abuse")
// Section 8: safety_classify_hard_bell self_harm phrases
println("")
println("8. safety_classify_hard_bell — self_harm phrases route to 'self_harm'")
let class_kill: String = safety_classify_hard_bell("I want to kill myself")
assert_eq("'kill myself' classifies as self_harm", class_kill, "self_harm")
let class_suicide: String = safety_classify_hard_bell("I am suicidal")
assert_eq("'suicidal' classifies as self_harm", class_suicide, "self_harm")
let class_overdose: String = safety_classify_hard_bell("took too many pills")
assert_eq("'took too many' classifies as self_harm", class_overdose, "self_harm")
// Section 9: safety_classify_hard_bell general -> 'self_harm'
println("")
println("9. safety_classify_hard_bell — general hard phrases fall through to 'self_harm'")
let class_going_kill: String = safety_classify_hard_bell("going to kill everything around me")
assert_eq("general hard phrase falls through to self_harm", class_going_kill, "self_harm")
// Section 10: safety_normalize curly apostrophe normalisation
println("")
println("10. safety_normalize — curly apostrophe normalisation")
// U+2019 RIGHT SINGLE QUOTATION MARK (UTF-8: \xe2\x80\x99) must become ASCII '
let smart_msg: String = "I can" + "\xe2\x80\x99" + "t go on anymore"
let normalized: String = safety_normalize(smart_msg)
assert_contains("smart-quote normalized to ASCII apostrophe", normalized, "can't go on")
// After normalisation, detect_bell_level must fire 'hard' on the smart-quote variant
let level_smart: String = safety_detect_bell_level(smart_msg)
assert_eq("smart-quote 'can't go on' -> hard (after normalize)", level_smart, "hard")
// Section 11: safety_augment_system passthrough on neutral
println("")
println("11. safety_augment_system — neutral input returns system unchanged")
let base_sys: String = "You are a helpful assistant."
let aug_neutral: String = safety_augment_system(base_sys, "What is the weather?")
assert_eq("neutral message -> system unchanged", aug_neutral, base_sys)
// Section 12: safety_augment_system soft bell injects directive
println("")
println("12. safety_augment_system — soft bell injects soft directive")
let aug_soft: String = safety_augment_system(base_sys, "Feeling so overwhelmed and completely anxious")
assert_contains("soft augment -> contains original system", aug_soft, base_sys)
assert_contains("soft augment -> contains SUBSTRATE DIRECTIVE", aug_soft, "SUBSTRATE DIRECTIVE")
assert_contains("soft augment -> contains soft care text", aug_soft, "genuine care")
// Section 13: safety_augment_system hard self_harm injects 988
println("")
println("13. safety_augment_system — hard self_harm injects crisis resources with 988")
let aug_hard: String = safety_augment_system(base_sys, "I want to kill myself tonight")
assert_contains("hard self_harm -> contains SUBSTRATE DIRECTIVE", aug_hard, "SUBSTRATE DIRECTIVE")
assert_contains("hard self_harm -> includes 988 crisis line", aug_hard, "988")
assert_not_contains("hard self_harm -> no DV hotline (wrong routing)", aug_hard, "1-800-799-7233")
// Section 14: safety_augment_system hard abuse routes to abuse directive
println("")
println("14. safety_augment_system — hard abuse injects abuse-specific directive")
let aug_abuse: String = safety_augment_system(base_sys, "he hit me and I am afraid of him")
assert_contains("hard abuse -> DV hotline present", aug_abuse, "1-800-799-7233")
assert_contains("hard abuse -> mentions not notifying contact", aug_abuse, "safety contact")
// Section 15: handle_safety_contact_post validation
println("")
println("15. handle_safety_contact_post — non-crisis without name returns error")
let no_name_body: String = "{\"is_crisis_line\":false,\"contact_method\":\"phone\",\"contact_value\":\"555-1234\",\"relationship\":\"friend\"}"
let no_name_result: String = handle_safety_contact_post(no_name_body)
let no_name_ok: String = json_get(no_name_result, "ok")
let no_name_err: String = json_get(no_name_result, "error")
assert_eq("no name -> ok==false", no_name_ok, "false")
assert_eq("no name -> error is 'name is required'", no_name_err, "name is required")
// Section 16: handle_safety_contact_post write then read back
println("")
println("16. handle_safety_contact_post — write then read back verifies persistence")
let contact_body: String = "{\"is_crisis_line\":false,\"name\":\"Test Contact\",\"contact_method\":\"phone\",\"contact_value\":\"555-9876\",\"relationship\":\"sibling\"}"
let write_result: String = handle_safety_contact_post(contact_body)
let write_ok: String = json_get(write_result, "ok")
assert_eq("contact write -> ok==true", write_ok, "true")
assert_contains("contact write -> result has configured", write_result, "\"configured\"")
assert_contains("contact write -> result has name", write_result, "Test Contact")
let read_result: String = handle_safety_contact_get()
assert_eq("contact read-back -> configured==true", json_get(read_result, "configured"), "true")
assert_contains("contact read-back -> name matches", read_result, "Test Contact")
// Section 17: handle_safety_contact_post crisis line auto-fills
println("")
println("17. handle_safety_contact_post — crisis line auto-fills name and value")
let crisis_body: String = "{\"is_crisis_line\":true}"
let crisis_result: String = handle_safety_contact_post(crisis_body)
let crisis_ok: String = json_get(crisis_result, "ok")
assert_eq("crisis line write -> ok==true", crisis_ok, "true")
assert_contains("crisis line -> name is Crisis Line", crisis_result, "Crisis Line")
assert_contains("crisis line -> value is 988", crisis_result, "988")
// Summary
println("")
println("bell_safety tests: " + int_to_str(pass_count) + " passed, " + int_to_str(fail_count) + " failed")
+257
View File
@@ -0,0 +1,257 @@
// test_bridge_serialization.el
//
// Tests for PR #20 fix/bridge-save-serialization:
// - bridge_save raw JSON serialization (BLOCKER 1 & 2 regression guards)
// - agentic_resume error-path handling
// - Legacy fallback: old string-escaped fields still readable
// - Corrupt/missing bridge state error envelope
// - Empty messages/tools_json guard in bridge_save
//
// What CANNOT be tested here without a live Anthropic API:
// - agentic_resume golden-path (calls agentic_loop which hits the API)
// - Full save/resume round-trip with a real tool_result
//
// To run:
// elc chat.el && ./soul --test tests/test_bridge_serialization.el
//
//
import "../chat.el"
// Test harness
let pass_count: Int = 0
let fail_count: Int = 0
fn assert_eq(label: String, got: String, expected: String) -> Void {
if str_eq(got, expected) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" got: " + got)
println(" expected: " + expected)
}
}
fn assert_true(label: String, cond: Bool) -> Void {
if cond {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
}
}
fn assert_false(label: String, cond: Bool) -> Void {
assert_true(label, !cond)
}
fn assert_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" missing '" + needle + "' in: " + haystack)
}
}
fn assert_not_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" unexpected '" + needle + "' found in: " + haystack)
} else {
let pass_count = pass_count + 1
println(" PASS: " + label)
}
}
fn assert_not_empty(label: String, s: String) -> Void {
if str_eq(s, "") {
let fail_count = fail_count + 1
println(" FAIL: " + label + " (got empty string)")
} else {
let pass_count = pass_count + 1
println(" PASS: " + label)
}
}
// Section 1: bridge_save empty messages guard
//
// BLOCKER 2 regression guard: bridge_save must refuse to write a blob when
// messages or tools_json is empty, as the resulting JSON would be syntactically
// invalid (bare colon with no value).
println("")
println("1. bridge_save — empty messages guard")
let sid1: String = "test-session-empty-messages"
state_set("mcp_bridge:" + sid1, "")
let save1_ok: Bool = bridge_save(sid1, "claude-sonnet-4-5", "sys", "[]", "", "", "call-1")
assert_false("empty messages -> bridge_save returns false", save1_ok)
let saved1: String = state_get("mcp_bridge:" + sid1)
assert_eq("empty messages -> no blob written to state", saved1, "")
// Section 2: bridge_save empty tools_json guard
println("")
println("2. bridge_save — empty tools_json guard")
let sid2: String = "test-session-empty-tools"
state_set("mcp_bridge:" + sid2, "")
let save2_ok: Bool = bridge_save(sid2, "claude-sonnet-4-5", "sys", "", "[{\"role\":\"user\",\"content\":\"hi\"}]", "", "call-2")
assert_false("empty tools_json -> bridge_save returns false", save2_ok)
let saved2: String = state_get("mcp_bridge:" + sid2)
assert_eq("empty tools_json -> no blob written to state", saved2, "")
// Section 3: bridge_save golden path writes raw JSON fields
//
// Verifies that messages_raw and tools_raw are stored as inline JSON (not
// string-escaped) so that json_get_raw retrieves them without corruption.
println("")
println("3. bridge_save — golden path writes messages_raw and tools_raw as raw JSON")
let sid3: String = "test-session-golden"
state_set("mcp_bridge:" + sid3, "")
let msgs3: String = "[{\"role\":\"user\",\"content\":\"hello\"}]"
let tools3: String = "[{\"name\":\"read_file\"}]"
let save3_ok: Bool = bridge_save(sid3, "claude-sonnet-4-5", "You are a helper.", tools3, msgs3, "read_file", "toolu_abc")
assert_true("valid args -> bridge_save returns true", save3_ok)
let blob3: String = state_get("mcp_bridge:" + sid3)
assert_not_empty("valid args -> blob written to state", blob3)
// messages_raw should be stored as a raw JSON array (not a quoted string)
// so json_get_raw on the blob returns the array directly
let raw_msgs3: String = json_get_raw(blob3, "messages_raw")
assert_contains("messages_raw field present in blob", blob3, "messages_raw")
assert_eq("messages_raw round-trips without corruption", raw_msgs3, msgs3)
let raw_tools3: String = json_get_raw(blob3, "tools_raw")
assert_eq("tools_raw round-trips without corruption", raw_tools3, tools3)
// Scalar fields should still be present as normal string-escaped JSON fields
let model3: String = json_get(blob3, "model")
assert_eq("model field preserved in blob", model3, "claude-sonnet-4-5")
let tool_use_id3: String = json_get(blob3, "tool_use_id")
assert_eq("tool_use_id field preserved in blob", tool_use_id3, "toolu_abc")
// Verify the blob does NOT contain old-style double-escaped fields
assert_not_contains("no legacy 'messages' string field in new-format blob", blob3, "\"messages\":\"")
assert_not_contains("no legacy 'tools_json' string field in new-format blob", blob3, "\"tools_json\":\"")
// Section 4: agentic_resume unknown session_id returns error envelope
println("")
println("4. agentic_resume — unknown session_id (empty state)")
let sid4: String = "test-session-unknown-xyzzy"
state_set("mcp_bridge:" + sid4, "")
let resume4: String = agentic_resume(sid4, "toolu_xyz", "some result")
assert_contains("unknown session_id -> error field present", resume4, "\"error\"")
assert_contains("unknown session_id -> reply field present", resume4, "\"reply\"")
assert_contains("unknown session_id -> 'unknown session_id' message", resume4, "unknown session_id")
let reply4: String = json_get(resume4, "reply")
assert_eq("unknown session_id -> reply is empty string", reply4, "")
// Section 5: agentic_resume syntactically invalid JSON in state
println("")
println("5. agentic_resume — syntactically invalid JSON blob in state")
let sid5: String = "test-session-corrupt-json"
// Write a non-JSON value that state_get would return as-is
state_set("mcp_bridge:" + sid5, "NOT_JSON_AT_ALL")
let resume5: String = agentic_resume(sid5, "toolu_xyz", "some result")
// The function may take multiple paths here; in all cases it must not crash and
// must return a JSON envelope with at least an error or empty reply field.
// When json_get_raw returns "" on unparseable input, the guard catches it.
assert_contains("corrupt JSON blob -> resume returns JSON", resume5, "\"reply\"")
// Section 6: agentic_resume blob with no messages produces error envelope
println("")
println("6. agentic_resume — blob missing messages_raw and messages fields")
let sid6: String = "test-session-no-messages"
// Blob with only model/safe_sys no messages or tools
state_set("mcp_bridge:" + sid6, "{\"model\":\"claude-sonnet-4-5\",\"safe_sys\":\"sys\",\"tool_use_id\":\"toolu_abc\"}")
let resume6: String = agentic_resume(sid6, "toolu_abc", "result")
assert_contains("missing messages -> error field present", resume6, "\"error\"")
assert_contains("missing messages -> error mentions corrupt state", resume6, "corrupt bridge state")
let reply6: String = json_get(resume6, "reply")
assert_eq("missing messages -> reply is empty string", reply6, "")
// Section 7: Legacy fallback old-format blob (string-escaped fields)
//
// BLOCKER 1 regression guard: sessions saved before the fix used 'messages'
// and 'tools_json' as string-escaped fields. The fallback path in agentic_resume
// must read them correctly. We verify the fallback resolves the correct values
// before the function reaches the api call (which we cannot make in tests).
//
// We test the fallback by writing a legacy blob and verifying that
// agentic_resume does NOT return the "corrupt bridge state" error
// (which would mean the fallback is broken), instead it gets past the guard
// and then fails on the API call (outside our test scope).
//
// NOTE: We cannot confirm a successful API-dependent round-trip in this test;
// the goal is only to confirm the state-reading fallback path resolves values.
println("")
println("7. Legacy fallback — old-format blob with string-escaped 'messages' field")
let sid7: String = "test-session-legacy-format"
// Simulate an old-format blob: messages and tools_json as json_safe-escaped strings.
// json_safe escapes " to \" so the stored value is a JSON string containing the array.
let legacy_msgs: String = "[{\"role\":\"user\",\"content\":\"legacy hello\"}]"
let legacy_tools: String = "[{\"name\":\"read_file\"}]"
// Build the blob the OLD way: string-escaped
let safe_msgs: String = json_safe(legacy_msgs)
let safe_tools: String = json_safe(legacy_tools)
let legacy_blob: String = "{\"model\":\"claude-sonnet-4-5\",\"safe_sys\":\"sys\",\"messages\":\"" + safe_msgs + "\",\"tools_json\":\"" + safe_tools + "\",\"tool_use_id\":\"toolu_legacy\"}"
state_set("mcp_bridge:" + sid7, legacy_blob)
let resume7: String = agentic_resume(sid7, "toolu_legacy", "legacy result")
// The fallback should successfully read the fields and NOT return "corrupt bridge state"
assert_not_contains("legacy blob -> no 'corrupt bridge state' error (fallback working)", resume7, "corrupt bridge state")
// It will fail on API call in test env, but should get past the state-reading guard
// Accept "unknown session_id" NOT happening - the blob was found, just API fails
// Section 8: bridge_save with tool_use_id containing special chars
println("")
println("8. bridge_save — tool_use_id with JSON-special characters is escaped")
let sid8: String = "test-session-special-chars"
state_set("mcp_bridge:" + sid8, "")
let special_id: String = "toolu_test\"quoted\""
let msgs8: String = "[{\"role\":\"user\",\"content\":\"hi\"}]"
let tools8: String = "[{\"name\":\"read_file\"}]"
let save8_ok: Bool = bridge_save(sid8, "claude-sonnet-4-5", "sys", tools8, msgs8, "", special_id)
assert_true("special chars in tool_use_id -> bridge_save returns true", save8_ok)
let blob8: String = state_get("mcp_bridge:" + sid8)
// The blob must be parseable (json_get succeeds on it)
let retrieved_id: String = json_get(blob8, "tool_use_id")
assert_eq("tool_use_id with quotes round-trips via json_safe", retrieved_id, special_id)
// Summary
println("")
println("test_bridge_serialization.el: " + int_to_str(pass_count) + " passed, " + int_to_str(fail_count) + " failed")
+256
View File
@@ -0,0 +1,256 @@
// tests/test_sessions.el unit tests for sessions.el
//
// Tests cover:
// 1. Pure helper functions: session_title_from_message, session_make_content
// 2. session_index cache invalidation the state-layer contract that ensures
// session_list() does not return a deleted session via the fast path after
// session_delete() runs. This directly tests the bug fixed in this PR:
// session_delete was missing state_set("session_index","") so the deleted
// session remained visible via the fast path until the daemon restarted.
// 3. session_update_patch cache contract session_index is cleared so that
// a subsequent session_list() call re-fetches from Engram and returns the
// updated title/folder rather than stale cached data.
// 4. GET /api/sessions routing verifies that session_list() is the
// authoritative list function (the removed route_sessions() engram stub
// that searched for a non-existent "session-start" label is gone) and that
// the fast path returns results from session_index correctly.
import "../sessions.el"
let pass_count: Int = 0
let fail_count: Int = 0
fn assert_eq(label: String, got: String, expected: String) -> Void {
if str_eq(got, expected) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" got: " + got)
println(" expected: " + expected)
}
}
fn assert_eq_int(label: String, got: Int, expected: Int) -> Void {
if got == expected {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" got: " + int_to_str(got))
println(" expected: " + int_to_str(expected))
}
}
fn assert_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" missing '" + needle + "' in: " + haystack)
}
}
fn assert_not_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" unexpected '" + needle + "' found in: " + haystack)
} else {
let pass_count = pass_count + 1
println(" PASS: " + label)
}
}
fn assert_true(label: String, cond: Bool) -> Void {
if cond {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
}
}
fn assert_false(label: String, cond: Bool) -> Void {
if !cond {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
}
}
//
// 1. session_title_from_message
//
println("")
println("1. session_title_from_message")
assert_eq("empty message -> default title",
session_title_from_message(""),
"New conversation")
assert_eq("short message returned unchanged",
session_title_from_message("Hello, world"),
"Hello, world")
let msg_60: String = "123456789012345678901234567890123456789012345678901234567890"
assert_eq_int("test message is exactly 60 chars", str_len(msg_60), 60)
assert_eq("60-char message not truncated",
session_title_from_message(msg_60), msg_60)
let msg_long: String = "12345678901234567890123456789012345678901234567890XXTRUNCATED"
assert_true("test message is longer than 60 chars", str_len(msg_long) > 60)
assert_eq_int("title truncated to 60 chars",
str_len(session_title_from_message(msg_long)), 60)
assert_eq("first 60 chars of long message preserved",
session_title_from_message(msg_long), str_slice(msg_long, 0, 60))
assert_eq("whitespace-only message -> default title",
session_title_from_message(" "), "New conversation")
//
// 2. session_make_content
//
println("")
println("2. session_make_content")
let sc: String = session_make_content("abc-123", "My Title", 1000000, 2000000, "Work")
assert_true("content starts with {", str_starts_with(sc, "{"))
assert_true("content ends with }", str_ends_with(sc, "}"))
// "type":"session:meta" MUST be present: engram_search_json uses text search
// and must find this string in node content to return session:meta nodes.
// Removing it breaks the session_list() slow path (cross-restart recovery).
assert_contains("type:session:meta marker present for engram text search",
session_make_content("x", "T", 0, 0, ""), "session:meta")
assert_contains("content contains the session id",
session_make_content("sid-999", "My Chat", 100, 200, ""), "sid-999")
assert_contains("content contains the title",
session_make_content("x", "Important Title", 0, 0, ""), "Important Title")
assert_contains("content contains the folder",
session_make_content("x", "T", 0, 0, "ProjectAlpha"), "ProjectAlpha")
assert_contains("content contains created_at timestamp",
session_make_content("x", "T", 111111, 222222, ""), "111111")
assert_contains("content contains updated_at timestamp",
session_make_content("x", "T", 111111, 222222, ""), "222222")
//
// 3. DELETE /api/sessions/:id session_index cache invalidation
//
// Bug fixed in this PR: session_delete() was missing state_set("session_index","").
// Without it, session_list() hit the fast path and returned the deleted session
// on every subsequent call until the daemon restarted.
//
// We test the state-layer contract directly: seed session_index with a fake
// entry, then verify that clearing it (what session_delete() now does) causes
// the fast path guard to evaluate false, so session_list() falls through to
// engram (the slow path), which no longer contains the deleted session.
//
println("")
println("3. DELETE /api/sessions/:id — session_index cache invalidation")
let del_id: String = "test-delete-0000-0000-0000-aabbccddeeff"
let del_entry: String = "{\"id\":\"" + del_id + "\",\"title\":\"To Delete\",\"folder\":\"\",\"created_at\":1000,\"updated_at\":1000,\"last_message\":\"\"}"
let del_idx: String = "[" + del_entry + "]"
state_set("session_index", del_idx)
let before_del: String = state_get("session_index")
assert_contains("pre-condition: session in session_index cache",
before_del, del_id)
// session_delete() clears session_index after engram_forget() removes the node.
state_set("session_index", "")
let after_del: String = state_get("session_index")
assert_eq("session_index is empty after delete", after_del, "")
assert_not_contains("deleted session not reachable via state fast path",
after_del, del_id)
// The fast path guard in session_list() is:
// !str_eq(state_idx, "") && !str_eq(state_idx, "[]")
let fast_path_after_delete: Bool = !str_eq(after_del, "") && !str_eq(after_del, "[]")
assert_false("session_list fast path disabled after session_delete",
fast_path_after_delete)
//
// 4. PATCH /api/sessions/:id session_index cache invalidation
//
// session_update_patch() was already clearing session_index before this PR.
// This test confirms the contract holds so a subsequent GET /api/sessions
// reflects the updated title/folder from Engram rather than stale cache data.
//
println("")
println("4. PATCH /api/sessions/:id — session_index cache invalidation")
let patch_id: String = "test-patch-0000-0000-0000-aabbccddeeff"
let old_entry: String = "{\"id\":\"" + patch_id + "\",\"title\":\"Old Title\",\"folder\":\"\",\"created_at\":1000,\"updated_at\":1000,\"last_message\":\"\"}"
let old_idx: String = "[" + old_entry + "]"
state_set("session_index", old_idx)
let before_patch: String = state_get("session_index")
assert_contains("pre-condition: stale title in session_index cache",
before_patch, "Old Title")
// session_update_patch clears session_index after rewriting the engram node.
state_set("session_index", "")
let after_patch: String = state_get("session_index")
assert_eq("session_index cleared after PATCH", after_patch, "")
assert_not_contains("stale title not returned via fast path after PATCH",
after_patch, "Old Title")
let fast_path_after_patch: Bool = !str_eq(after_patch, "") && !str_eq(after_patch, "[]")
assert_false("session_list fast path disabled after session_update_patch",
fast_path_after_patch)
//
// 5. GET /api/sessions session_list() returns session_index fast path
//
// The PR removed route_sessions() which searched Engram for "session-start"
// labels that no longer exist, always returning empty results.
// GET /api/sessions is now wired to session_list() instead.
//
// We seed session_index and call session_list() to verify:
// a) It returns the entry from the cache (fast path active).
// b) It does not include any "session-start" label artifact.
//
println("")
println("5. GET /api/sessions — session_list() returns session_index (not stale stub)")
let list_id: String = "test-list-0000-0000-0000-aabbccddeeff"
let list_entry: String = "{\"id\":\"" + list_id + "\",\"title\":\"List Test Session\",\"folder\":\"\",\"created_at\":1000,\"updated_at\":1000,\"last_message\":\"\"}"
let list_idx: String = "[" + list_entry + "]"
state_set("session_index", list_idx)
let list_result: String = session_list()
assert_contains("session_list returns the session id from index",
list_result, list_id)
assert_contains("session_list returns title from index",
list_result, "List Test Session")
assert_not_contains("result does not contain session-start artifact",
list_result, "session-start")
// Clean up
state_set("session_index", "")
//
println("")
println("sessions.el tests: " + int_to_str(pass_count) + " passed, " + int_to_str(fail_count) + " failed")
+227
View File
@@ -0,0 +1,227 @@
// tests/test_sessions_approve.el
// Test suite for handle_session_approve in sessions.el.
//
// Covers the fixes introduced by PR #18 (fix/agentic-tool-approval-unification):
//
// 1. Modern path: missing tool_name returns error (BLOCKER 1 fix)
// 2. Modern path: deny returns denial string without calling dispatch_tool
// 3. Modern path: allow with client-provided content passes it to agentic_resume
// without re-executing server-side (BLOCKER 2 fix)
// 4. Legacy path: no pending tool returns expected error
// 5. Legacy path: call_id mismatch returns mismatch error
// 6. Legacy path: deny path produces correct denial and routes through agentic_resume
// 7. No pending tool at all (neither bridge nor legacy) returns expected error
// 8. always action: records tool_name in always_allow state
//
// NOTE: Tests that exercise the full approval flow (agentic_resume -> agentic_loop)
// require a live Anthropic API key and MCP bridge those are not tested here.
// These tests cover the approval-decision and error-guard logic only.
//
// To run:
// ./soul --test tests/test_sessions_approve.el
import "../sessions.el"
let pass_count: Int = 0
let fail_count: Int = 0
fn assert_eq(label: String, got: String, expected: String) -> Void {
if str_eq(got, expected) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" got: " + got)
println(" expected: " + expected)
}
}
fn assert_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" missing '" + needle + "' in: " + haystack)
}
}
fn assert_not_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" unexpected '" + needle + "' in: " + haystack)
} else {
let pass_count = pass_count + 1
println(" PASS: " + label)
}
}
// Section 1: empty session_id guard
println("")
println("1. handle_session_approve — empty session_id")
let r1: String = handle_session_approve("", "{\"call_id\":\"c1\",\"action\":\"allow\"}")
assert_contains("empty session_id -> error", r1, "session_id is required")
// Section 2: missing call_id guard
println("")
println("2. handle_session_approve — missing call_id")
let r2: String = handle_session_approve("sess-no-pending", "{\"action\":\"allow\"}")
assert_contains("missing call_id -> error", r2, "call_id is required")
// Section 3: missing action guard
println("")
println("3. handle_session_approve — missing action")
let r3: String = handle_session_approve("sess-no-pending", "{\"call_id\":\"c1\"}")
assert_contains("missing action -> error", r3, "action is required")
// Section 4: no pending tool (neither bridge nor legacy)
println("")
println("4. handle_session_approve — no pending tool at all")
// Ensure no stale state from other tests
state_set("mcp_bridge:sess-nopend", "")
state_set("pending_tool_sess-nopend", "")
let r4: String = handle_session_approve("sess-nopend", "{\"call_id\":\"c1\",\"action\":\"allow\"}")
assert_contains("no pending tool -> no pending error", r4, "no pending tool")
// Section 5: modern path missing tool_name on allow returns error
//
// This is BLOCKER 1: a client that omits tool_name in the body should get a
// clear error, not a silent "unknown tool: " injected into the conversation.
println("")
println("5. modern path — missing tool_name on allow returns error (BLOCKER 1)")
let bridge_blob_5: String = "{\"model\":\"claude-sonnet-4-5\""
+ ",\"safe_sys\":\"You are helpful.\""
+ ",\"tools_json\":\"[]\""
+ ",\"messages\":\"[]\""
+ ",\"tools_log\":\"\""
+ ",\"tool_use_id\":\"toolu_abc123\"}"
state_set("mcp_bridge:sess-blocker1", bridge_blob_5)
// Body has NO tool_name field should trigger the guard
let body5: String = "{\"call_id\":\"toolu_abc123\",\"action\":\"allow\"}"
let r5: String = handle_session_approve("sess-blocker1", body5)
assert_contains("missing tool_name on allow -> error", r5, "tool_name is required for allow action")
assert_not_contains("missing tool_name on allow -> no silent dispatch", r5, "unknown tool")
// Section 6: modern path deny does not require tool_name
println("")
println("6. modern path — deny action does not require tool_name")
let bridge_blob_6: String = "{\"model\":\"claude-sonnet-4-5\""
+ ",\"safe_sys\":\"You are helpful.\""
+ ",\"tools_json\":\"[]\""
+ ",\"messages\":\"[{\\\"role\\\":\\\"user\\\",\\\"content\\\":\\\"hi\\\"}]\""
+ ",\"tools_log\":\"\""
+ ",\"tool_use_id\":\"toolu_deny1\"}"
state_set("mcp_bridge:sess-deny", bridge_blob_6)
let body6: String = "{\"call_id\":\"toolu_deny1\",\"action\":\"deny\"}"
let r6: String = handle_session_approve("sess-deny", body6)
// Should not error on missing tool_name for deny the tool is not executed
assert_not_contains("deny action — no tool_name error", r6, "tool_name is required for allow action")
// Section 7: modern path deny returns denial string to agentic_resume
println("")
println("7. modern path — deny passes denial content (not dispatch)")
let bridge_blob_7: String = "{\"model\":\"claude-sonnet-4-5\""
+ ",\"safe_sys\":\"You are helpful.\""
+ ",\"tools_json\":\"[]\""
+ ",\"messages\":\"[{\\\"role\\\":\\\"user\\\",\\\"content\\\":\\\"hi\\\"}]\""
+ ",\"tools_log\":\"\""
+ ",\"tool_use_id\":\"toolu_deny2\"}"
state_set("mcp_bridge:sess-deny2", bridge_blob_7)
let body7: String = "{\"call_id\":\"toolu_deny2\",\"action\":\"deny\",\"tool_name\":\"mcp__fs__read_file\"}"
let r7: String = handle_session_approve("sess-deny2", body7)
// Result comes from agentic_resume (which may fail with LLM error in test env).
// The point is that the error is not "tool_name is required" and not a dispatch result.
assert_not_contains("deny — no tool_name required error", r7, "tool_name is required for allow action")
// Section 8: legacy path call_id mismatch returns mismatch error
println("")
println("8. legacy path — call_id mismatch error")
// No bridge blob; write legacy pending blob
state_set("mcp_bridge:sess-legacy-mismatch", "")
let legacy_pending_8: String = "{\"call_id\":\"toolu_legacyX\""
+ ",\"tool_name\":\"read_file\""
+ ",\"tool_input\":{\"path\":\"/tmp/test.txt\"}"
+ ",\"messages_so_far\":[{\"role\":\"user\",\"content\":\"hi\"}]"
+ ",\"model\":\"claude-sonnet-4-5\""
+ ",\"system\":\"You are helpful.\"}"
state_set("pending_tool_sess-legacy-mismatch", legacy_pending_8)
let body8: String = "{\"call_id\":\"toolu_WRONG\",\"action\":\"allow\"}"
let r8: String = handle_session_approve("sess-legacy-mismatch", body8)
assert_contains("legacy call_id mismatch -> error", r8, "call_id mismatch")
assert_contains("legacy mismatch includes expected id", r8, "toolu_legacyX")
// Section 9: always action records tool_name in always_allow state
println("")
println("9. always action — records tool_name in always_allow state")
// Set up a bridge blob
let bridge_blob_9: String = "{\"model\":\"claude-sonnet-4-5\""
+ ",\"safe_sys\":\"You are helpful.\""
+ ",\"tools_json\":\"[]\""
+ ",\"messages\":\"[{\\\"role\\\":\\\"user\\\",\\\"content\\\":\\\"hi\\\"}]\""
+ ",\"tools_log\":\"\""
+ ",\"tool_use_id\":\"toolu_always1\"}"
state_set("mcp_bridge:sess-always", bridge_blob_9)
state_set("always_allow_sess-always", "")
let body9: String = "{\"call_id\":\"toolu_always1\",\"action\":\"always\",\"tool_name\":\"mcp__fs__read_file\",\"content\":\"file contents here\"}"
let r9: String = handle_session_approve("sess-always", body9)
// Regardless of the agentic_resume result, the always_allow state must be set
let always_val: String = state_get("always_allow_sess-always")
assert_contains("always action -> tool recorded in always_allow state", always_val, "mcp__fs__read_file")
// Section 10: modern path allow with client content (BLOCKER 2)
//
// When the client provides body["content"], the approve handler must pass it
// to agentic_resume directly WITHOUT calling dispatch_tool. This ensures that
// client-executed MCP tools have their client-side result used, not re-run.
println("")
println("10. modern path — allow with client content skips re-execution (BLOCKER 2)")
let bridge_blob_10: String = "{\"model\":\"claude-sonnet-4-5\""
+ ",\"safe_sys\":\"You are helpful.\""
+ ",\"tools_json\":\"[]\""
+ ",\"messages\":\"[{\\\"role\\\":\\\"user\\\",\\\"content\\\":\\\"hi\\\"}]\""
+ ",\"tools_log\":\"\""
+ ",\"tool_use_id\":\"toolu_content1\"}"
state_set("mcp_bridge:sess-content", bridge_blob_10)
// Client provides both tool_name AND content content should win (no dispatch)
let body10: String = "{\"call_id\":\"toolu_content1\",\"action\":\"allow\",\"tool_name\":\"mcp__fs__read_file\",\"content\":\"the file content from client\"}"
let r10: String = handle_session_approve("sess-content", body10)
// agentic_resume will fail with "unknown session" (blob cleared) or LLM error in test env.
// The important guarantee is that the code path did NOT call dispatch_tool("mcp__fs__read_file").
// We can't directly assert what agentic_resume did with the content in a unit test,
// but we can assert no server-side "MCP bridge unreachable" error was injected:
assert_not_contains("allow with content — no MCP bridge error in dispatch", r10, "MCP bridge unreachable")
// Summary
println("")
println("sessions_approve tests: " + int_to_str(pass_count) + " passed, " + int_to_str(fail_count) + " failed")
+171
View File
@@ -0,0 +1,171 @@
// test_sessions_routes.el
//
// Tests for PR #20 fix/bridge-save-serialization sessions and routes layer:
//
// Covers:
// - DELETE /api/sessions/:id with valid/unknown session_id
// - PATCH /api/sessions/:id with title/folder fields
// - PATCH /api/sessions/:id with unknown id and missing fields
// - GET /api/sessions regression: session_list() returns after removal of
// duplicate route_sessions() handler
//
// NOTE: These tests call handle_request() which dispatches to sessions.el
// functions that use engram_search_json. Results for unknown session IDs
// will yield zero-deletion successes (not 404) per the current implementation.
//
// To run:
// elc routes.el && ./soul --test tests/test_sessions_routes.el
//
//
import "../routes.el"
// Test harness
let pass_count: Int = 0
let fail_count: Int = 0
fn assert_eq(label: String, got: String, expected: String) -> Void {
if str_eq(got, expected) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" got: " + got)
println(" expected: " + expected)
}
}
fn assert_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" missing '" + needle + "' in: " + haystack)
}
}
fn assert_not_contains(label: String, haystack: String, needle: String) -> Void {
if str_contains(haystack, needle) {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" unexpected '" + needle + "' found in: " + haystack)
} else {
let pass_count = pass_count + 1
println(" PASS: " + label)
}
}
fn assert_true(label: String, cond: Bool) -> Void {
if cond {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
}
}
// Section 1: DELETE /api/sessions/:id unknown id
//
// session_delete does not return 404 for unknown ids; it returns ok:true with
// zero-count deletions. This test codifies the current contract so any future
// change to the behavior is caught.
println("")
println("1. DELETE /api/sessions/:id — unknown session_id")
let del_unknown: String = handle_request("DELETE", "/api/sessions/nonexistent-session-uuid", "")
assert_contains("DELETE unknown id -> ok field present", del_unknown, "\"ok\"")
assert_contains("DELETE unknown id -> ok is true (zero-count success)", del_unknown, "\"ok\":true")
assert_contains("DELETE unknown id -> deleted_meta count present", del_unknown, "deleted_meta")
assert_contains("DELETE unknown id -> deleted_msgs count present", del_unknown, "deleted_msgs")
// Section 2: DELETE /api/sessions/:id missing id
println("")
println("2. DELETE /api/sessions (no id in path) -> 404")
let del_no_id: String = handle_request("DELETE", "/api/sessions", "")
assert_contains("DELETE with no id -> 404 error", del_no_id, "\"error\"")
// Section 3: PATCH /api/sessions/:id update title
//
// PATCH with a known title field should not error on the missing-fields check.
// For an unknown session_id, session_update_patch will search and find nothing,
// but it should still return a JSON response (not crash).
println("")
println("3. PATCH /api/sessions/:id — title field")
let patch_title: String = handle_request("PATCH", "/api/sessions/test-sess-patch-1", "{\"title\":\"My new title\"}")
// Should return JSON with ok field or error field must not be empty
assert_not_contains("PATCH title -> response is not empty", patch_title, "")
assert_true("PATCH title -> response is non-empty string", str_len(patch_title) > 0)
// Must not return the missing-fields error (since title IS provided)
assert_not_contains("PATCH title -> no 'title or folder required' error", patch_title, "title or folder required")
// Section 4: PATCH /api/sessions/:id folder field
println("")
println("4. PATCH /api/sessions/:id — folder field")
let patch_folder: String = handle_request("PATCH", "/api/sessions/test-sess-patch-2", "{\"folder\":\"my-folder\"}")
assert_true("PATCH folder -> response is non-empty", str_len(patch_folder) > 0)
assert_not_contains("PATCH folder -> no 'title or folder required' error", patch_folder, "title or folder required")
// Section 5: PATCH /api/sessions/:id empty body (missing fields)
println("")
println("5. PATCH /api/sessions/:id — empty body returns field-required error")
let patch_empty: String = handle_request("PATCH", "/api/sessions/test-sess-patch-3", "{}")
assert_contains("PATCH empty body -> error field present", patch_empty, "\"error\"")
assert_contains("PATCH empty body -> missing fields message", patch_empty, "title or folder required")
// Section 6: PATCH /api/sessions (no id in path) -> 404
println("")
println("6. PATCH /api/sessions (no id) -> 404")
let patch_no_id: String = handle_request("PATCH", "/api/sessions", "{\"title\":\"x\"}")
assert_contains("PATCH no id -> 404 error", patch_no_id, "\"error\"")
// Section 7: GET /api/sessions session_list regression
//
// After removal of the duplicate route_sessions() GET handler in routes.el,
// GET /api/sessions must still return a valid JSON array (possibly empty) from
// session_list(). Verifies the deduplication fix does not break the endpoint.
println("")
println("7. GET /api/sessions — session_list() returns valid JSON array")
let get_sessions: String = handle_request("GET", "/api/sessions", "")
assert_true("GET /api/sessions -> response is non-empty", str_len(get_sessions) > 0)
// Result must be a JSON array (starts with '[')
let first_char: String = str_slice(get_sessions, 0, 1)
assert_eq("GET /api/sessions -> response is a JSON array", first_char, "[")
// Section 8: DELETE then GET session_index cache invalidation
//
// After a DELETE, session_list() must not return the deleted session.
// Since we don't have a real session to delete in this test environment,
// we verify the GET still returns an array after the DELETE attempt.
println("")
println("8. GET /api/sessions after DELETE attempt -> still returns valid array")
let del_first: String = handle_request("DELETE", "/api/sessions/test-cache-inval-sess", "")
assert_contains("pre-DELETE: ok field present", del_first, "\"ok\"")
let get_after_del: String = handle_request("GET", "/api/sessions", "")
let first_char2: String = str_slice(get_after_del, 0, 1)
assert_eq("GET after DELETE -> still returns JSON array", first_char2, "[")
// Summary
println("")
println("test_sessions_routes.el: " + int_to_str(pass_count) + " passed, " + int_to_str(fail_count) + " failed")
+124
View File
@@ -0,0 +1,124 @@
// tests/test_soul_guard.el
//
// Logic tests for the genesis guard in soul.el (feat/connectors-soul).
//
// The guard is top-level imperative boot code. This file tests the predicate
// logic as pure functions to verify the conditions exhaustively:
//
// safe_to_seed = !using_http_engram &&
// !(guard_disk_len > 200000 && loaded_nodes * 16000 < guard_disk_len)
//
// Scenarios:
// - Boundary: 199,999 bytes + sparse -> safe_to_seed == true
// - Boundary: 200,001 bytes + sparse -> safe_to_seed == false
// - Ratio: 47MB + 63 nodes -> false (the 2026-06-14 clobber scenario)
// - HTTP mode -> false unconditionally
// - Multiplication form vs old division form near 250KB boundary
//
let pass_count: Int = 0
let fail_count: Int = 0
fn assert_eq_bool(label: String, got: Bool, expected: Bool) -> Void {
let got_s: String = if got { "true" } else { "false" }
let exp_s: String = if expected { "true" } else { "false" }
if str_eq(got_s, exp_s) {
let pass_count = pass_count + 1
println(" PASS: " + label)
} else {
let fail_count = fail_count + 1
println(" FAIL: " + label)
println(" got: " + got_s)
println(" expected: " + exp_s)
}
}
// guard_predicate mirrors the safe_to_seed expression in soul.el exactly.
fn guard_predicate(using_http: Bool, disk_len: Int, loaded_nodes: Int) -> Bool {
if using_http { return false }
let ratio_block: Bool = disk_len > 200000 && loaded_nodes * 16000 < disk_len
return !ratio_block
}
// Section 1: 200KB boundary
println("")
println("1. guard boundary — 199,999 bytes + sparse load -> safe_to_seed true")
let safe_below: Bool = guard_predicate(false, 199999, 1)
assert_eq_bool("199,999 bytes + 1 node -> safe", safe_below, true)
let safe_below_zero: Bool = guard_predicate(false, 199999, 0)
assert_eq_bool("199,999 bytes + 0 nodes -> safe (below 200KB threshold)", safe_below_zero, true)
println("")
println("2. guard boundary — 200,001 bytes + sparse load -> safe_to_seed false")
let unsafe_above: Bool = guard_predicate(false, 200001, 1)
assert_eq_bool("200,001 bytes + 1 node -> unsafe", unsafe_above, false)
let unsafe_zero: Bool = guard_predicate(false, 200001, 0)
assert_eq_bool("200,001 bytes + 0 nodes -> unsafe", unsafe_zero, false)
// Section 2: ratio guard 47MB + 63 nodes
println("")
println("3. guard ratio — 47MB + 63 nodes (the 2026-06-14 clobber scenario)")
let clobber_blocked: Bool = guard_predicate(false, 47000000, 63)
assert_eq_bool("47MB + 63 nodes -> unsafe (clobber blocked)", clobber_blocked, false)
// 47MB / 16000 = 2937.5 -> need >= 2938 nodes for safe
let clobber_safe: Bool = guard_predicate(false, 47000000, 2938)
assert_eq_bool("47MB + 2938 nodes -> safe (load correct)", clobber_safe, true)
let boundary_blocked: Bool = guard_predicate(false, 47000000, 2937)
assert_eq_bool("47MB + 2937 nodes -> unsafe (just below ratio)", boundary_blocked, false)
// Section 3: HTTP-engram mode always false
println("")
println("4. guard HTTP mode — always false regardless of disk/node counts")
let http_zero: Bool = guard_predicate(true, 0, 0)
assert_eq_bool("HTTP mode + 0/0 -> unsafe", http_zero, false)
let http_small: Bool = guard_predicate(true, 1000, 100)
assert_eq_bool("HTTP mode + small snapshot -> unsafe", http_small, false)
let http_large: Bool = guard_predicate(true, 47000000, 2938)
assert_eq_bool("HTTP mode + large/fully-loaded -> unsafe", http_large, false)
// Section 4: normal local mode small/fresh snapshots
println("")
println("5. guard normal local mode — small/fresh snapshots")
let fresh_genesis: Bool = guard_predicate(false, 0, 0)
assert_eq_bool("fresh genesis (0 bytes, 0 nodes) -> safe", fresh_genesis, true)
let small_snapshot: Bool = guard_predicate(false, 50000, 5)
assert_eq_bool("50KB + 5 nodes -> safe (below 200KB threshold)", small_snapshot, true)
// Section 5: multiplication vs division 250KB boundary
println("")
println("6. guard multiplication form — avoids floor-division truncation at 250KB")
// OLD (division): 250000 / 16000 = 15 (floors 15.625). 15 < 15 is false -> wrongly safe.
// NEW (multiplication): 15 * 16000 = 240000 < 250000 -> correctly unsafe.
let div_boundary: Bool = guard_predicate(false, 250000, 15)
assert_eq_bool("250,000 bytes + 15 nodes -> unsafe (multiplication form)", div_boundary, false)
// With 16 nodes: 16 * 16000 = 256000 > 250000 -> safe.
let div_just_enough: Bool = guard_predicate(false, 250000, 16)
assert_eq_bool("250,000 bytes + 16 nodes -> safe", div_just_enough, true)
// Exact equality: disk_len == node_count * 16000 -> not sparse -> safe.
let exact_match: Bool = guard_predicate(false, 32000, 2)
assert_eq_bool("exact ratio (32000 bytes, 2 nodes: 2*16000=32000) -> safe", exact_match, true)
// Summary
println("")
println("soul_guard tests: " + int_to_str(pass_count) + " passed, " + int_to_str(fail_count) + " failed")