Merge propose/agent-workspace-root-read (Tim's PR #28):
- path_within_root now appends '/' to root before prefix check (closes proj_evil bypass)
- edit_file in dispatch_tool now checks agent_workspace_root() and resolves path
- handle_chat_agentic reads agent_workspace_root from request body, only persists if non-empty
- Safety screen preserved after workspace root read (conflict resolved)
Merge improve/safety-crisis-detection (PR #31): reads layered_cycle_safety_system_addendum
from state and appends to system prompt on each turn (cleared after use to prevent bleed).
Safety ts extraction falls back to updated_at. Affective prefix now wires into system build.
Conflict with PR #33 resolved: capability_rules and session_preload both preserved.
- engram_compile: BellEvent nodes do not carry created_at in the engram
node JSON; extract the unix timestamp from the embedded ' | ts:NNNNN'
pattern in the content string instead. Fall back to created_at/updated_at
if the marker is absent. Guard str_to_int against empty string so the 72h
recency check never silently treats every node as epoch-0 stale.
- auto_persist: append the current unix timestamp to the BellEvent label
('bell:soft:1749876543') to make it unique per turn. The previous label
('bell:soft') was the same for every soft bell, causing engram to treat
all subsequent writes as updates to the same node.
- Remove dead soft_bell block in layered_cycle that wrote soul_safety_system_augment
to state but was never read; safety augmentation now goes through the correct
layered_cycle_safety_system_addendum state key read by build_system_prompt
- build_system_prompt now reads layered_cycle_safety_system_addendum and appends
it to the system prompt, clearing the key after consumption
- Timestamp extraction for distress nodes falls back to updated_at when created_at
is empty, preventing the 72h recency check from always treating nodes as stale
- auto_persist: detect bell level (soft/hard) on every user message using
safety_detect_bell_level; write a dedicated BellEvent engram node with
calibrated salience alongside the Conversation node when a bell fires.
Tag the Conversation node with bell:soft/bell:hard and 'affective' for
direct discovery without scanning all chat nodes.
- auto_persist: track per-session bell count, dominant level, and last
signal in state (session_bell_count/level/signal keys) so downstream
functions can act on the emotional history without re-scanning engram.
- engram_compile: include the top-1 most recent BellEvent node within 72h
in every context build. Distress context from earlier turns (same or
recent session) automatically travels into all subsequent LLM calls.
- hist_trim_with_bell_guard: replace hist_trim at the handle_chat call site.
Before evicting the oldest turn from the 20-turn window, inspect the user
message for bell signals. If a bell was present, write a preservation
BellEvent to engram before dropping the turn so the full message survives
the rolling window.
- session_hist_save: after writing the history node, check session bell
counters. On the first save where bell_count > 0, write a
session:emotional-summary BellEvent node with distress signal, count,
and dominant level. A state flag prevents duplicate writes on subsequent
saves in the same session.
- engram_compile: rank search results by recency x relevance before including
in context. Pulls 20 candidates, scores each (salience * importance * recency
decay), keeps top 8. Eliminates stale/low-signal nodes that diluted context.
- handle_chat: on hist_len==0 (session start), proactively load user profile
and active-work context from engram and inject as brief bullets in the system
prompt. Gives the soul grounding before any conversation history exists.
- build_system_prompt: add [CAPABILITY GAPS] directive instructing the soul to
offer partial help and reasoning instead of flat "I don't have access to that"
refusals when a tool is missing.
- handle_chat_agentic: run safety_screen at entry, mirroring layered_cycle.
Hard bell exits immediately with the crisis response without entering the loop.
- agentic_loop: surface the 8-iteration cap explicitly in the error envelope
("agentic loop hit the 8-iteration cap...") rather than the opaque "no response".
Add iterations count to both the error and success envelopes for observability.
- soul.el: fix state key bug in layered_cycle (conversation_history -> conv_history)
- safety.el: add indirect crisis location patterns to soft_bell phrase list
- soul.el: wire safety_augment_system into layered_cycle for soft_bell turns
- chat.el: load cross-session affective context at session start when distress signals found within 72h
REPRODUCED: in the non-agentic path (Tools off / 'Just chat'), asking for
tool-work makes the model role-play tool use — it emits a fake ```json {...}```
'tool call' and says 'let me search/query/pull your sessions' while NOTHING
runs. Reads as a broken/lying app. (The agentic path is fine: verified it
calls search_memory and reports honestly.)
Root cause: build_system_prompt (handle_chat, the tool-less path) never told
the model it has no tools this turn, so it fabricated.
Fix: add a NO-TOOLS directive to the non-agentic system prompt — never emit
tool calls / JSON tool blocks / 'let me pull...' narration; answer from context
only; if a tool is truly needed, say so in one sentence and tell the user to
turn Tools on. Applied to chat.el (source) AND dist/soul.c (the curated TU the
CI compiles), so the CI-built binary carries it.
Verified the FABRICATION repro on the live local soul; could not verify the
patched binary locally (no matching el-runtime version on this machine — a
hand-link against origin/main runtime 404s on all routes). Builds correctly via
CI, which links soul.c against the pinned runtime.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Completes the UI<->soul contract for #23 (scope file/command tools to an agent
workspace root). #23 made the tools read state_get("agent_workspace_root"), but
nothing set that key from the desktop UI, so the agent panel's Workspace Folder
was cosmetic and tools ran unscoped (default-allow). This reads the root the UI
now sends on each agentic request and state_sets it before tool dispatch, so
agent_workspace_root() picks it up for the turn.
Minimal + pattern-matching (same json_get/state_set shape used throughout chat.el).
Empty body field => unscoped (backward-compatible) and preserves the env fallback.
FOR WILL'S REVIEW — do not merge without sign-off:
- Ownership model: set state from body each turn (so clearing the folder un-scopes)
vs. only-when-nonempty. Flagged inline.
- Pairs with neuron-ui PR #32 (ChatRequest.agentWorkspaceRoot).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Confine the agentic file tools (read_file, write_file, list_files, grep)
to a configured workspace subtree via a lexical path check, and run
run_command with its cwd set to that root. Root comes from state key
"agent_workspace_root" or env NEURON_AGENT_ROOT. When no root is set,
behavior is unchanged (unscoped) for backward compatibility.
Defense-in-depth, NOT a hard boundary: the lexical guard does not resolve
symlinks and cannot stop an arbitrary shell command from cd-ing out of the
root. Real confinement needs runtime support (cwd-locked exec / sandbox-exec
/ chroot) in el_runtime.c.
Compile-checked with elc (darwin arm64); not link/run-gated locally
(darwin elb unavailable). Needs a soul build + smoke test before merge.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
agentic_tools_literal() already contains a custom web_search tool.
agentic_tools_with_web() adds the Anthropic server-side web_search_20250305
tool (also named web_search). Combining them caused Anthropic to reject
every agentic request with 'Tool names must be unique.'
agentic_tools_all() now calls agentic_tools_literal() directly. Connector
tools splice in as before. The web_search-only variant (agentic_tools_with_web)
is unchanged for callers that specifically want native search without connectors.
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.
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
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)
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)
handle_chat_agentic was calling agentic_tools_with_web(), which omits
MCP connector tools, so mcp__* calls were never available in agentic
mode even when neuron-connectd is running.
Switch both agentic entry points to agentic_tools_all(). For
handle_dharma_room_turn_agentic, also replace the inline 8-iteration
loop with a call to agentic_loop() so bridge suspension and the full
connector tool set work consistently. Session IDs are prefixed with
'dharma:' + room_id so suspensions stay room-scoped.
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.
Short/ambiguous messages (< 50 chars) now use the last reply as the
engram activation seed instead of the bare message. Prevents strong
off-topic memory nodes from hijacking replies when the user is clearly
continuing an existing thread.
Also gives handle_chat_agentic session continuity: reads/writes history
keyed by session_id (falling back to global conv_history), seeds the
LLM messages array with prior turns, and saves replies back so the
next turn has context.
Applies connector-specific additions from feat/connectors-soul:
- chat.el: connector_tools_json(), agentic_tools_all(), call_mcp_bridge(),
tool_auto_approved() and mcp__ dispatch in dispatch_tool()
- routes.el: connectd_get/post, handle_connectors(), /api/connectors routing
in GET and POST sections
- MEMORY_RECALL_BUG.md: investigation notes on memory retrieval failure
The agentic loop rewrite in the source branch was not applied — it conflicts
with the tool-bridge pattern from PR #5 which is the chosen design for
client-side MCP tool execution. The connectors themselves are now fully
wired: connector tools surface as mcp__<server>__<tool> in the tools array
and dispatch to neuron-connectd via call_mcp_bridge().
When handle_chat_agentic hits a tool the soul cannot run in-process (an MCP
connector/plugin surfaced by the Kotlin desktop app), instead of returning
"unknown tool" it now suspends the agentic loop and returns a tool_pending
envelope so the CLIENT executes the tool and posts the result back. Built-in
tools (read_file/write_file/web_get/search_memory/run_command) and Anthropic's
native web_search are unchanged.
Client contract:
- Soul returns (HTTP 200) on an unknown tool:
{ "tool_pending": true, "session_id": "br-...", "call_id": "<tool_use_id>",
"tool_name": "...", "tool_input": { ... }, "model": "...",
"agentic": true, "tools_used": [...] }
- Client runs the MCP tool, then POSTs to
/api/sessions/{session_id}/tool_result
with body:
{ "call_id": "<the call_id from the envelope>",
"content": "<MCP tool output as a string>" }
- Soul resumes the loop and returns the same envelope shape: either a final
{ "reply": ..., "tools_used": [...] }
or another tool_pending if the continuation needs a further MCP tool
(fully chainable). Saved continuation is one-shot (cleared on resume).
elc-verified (--target=c, exit 0, no stderr) on chat.el, routes.el, and the
full soul.el import graph. Needs Will's build to ship.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
handle_chat_agentic now always attaches Anthropic's native web_search_20250305
tool instead of gating it behind a per-request web_search flag. Web search is a
built-in capability: the model invokes it only when a query needs fresh info
(max_uses:5 caps it), so there is no user-facing toggle. The body's web_search
field is now ignored (back-compat — old UI clients sending it cause no harm).
Pairs with neuron-ui removing the chat-input web search toggle.
Note: .el change only — no elc on the authoring machine; reviewer builds/verifies.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
When a chat request carries web_search=true, handle_chat_agentic now attaches Anthropic's
NATIVE server-side web_search tool (web_search_20250305) to the request. The native tool is
executed by Anthropic (not by the soul), so it returns real results with citations and needs
no local runtime — it sidesteps the soul's lack of executable tools entirely.
- new agentic_tools_with_web(web_search) helper (appends the native tool to the standard set)
- handle_chat_agentic reads json_get_bool(body,"web_search") and uses it
Pairs with neuron-ui: ChatRequest.web_search + the chat-input Web search toggle.
Note: built/verified by reviewer — no elc on the authoring machine.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
chat.el recorded the soul's utterance via engram_node(content, "episodic", ...),
putting a TIER into the node_type slot (nodes showed node_type="episodic"). Now uses
engram_node_full(..., "Conversation", "soul:utterance", ..., "Episodic", tags).
The core wrapper fix is in the el repo (PR #52). HANDOFF-engram-write-corruption.md
has the full root-cause analysis, coercion mechanism, caller audit, validation,
deploy runbook (elc build + restart), and the data-prune proposal (~107 corrupt
nodes, all unrecoverable genesis/binary detritus → prune; backup taken).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Adds handle_dharma_room_turn_agentic to chat.el — same full tool loop
as handle_chat_agentic but reads transcript directly (not message), and
returns {response, cgi_id, tools_used} to match the dharma room shape.
Registers dharma_room_turn_agentic as a new event type in routes.el so
the studio can dispatch @neuron turns through this dedicated path.
- soul.el: SOUL_CGI_ID, SOUL_ENGRAM_PATH, SOUL_IDENTITY env vars;
state_set("soul_snapshot_path") so callers can find it; only call
init_soul_edges() when cgi_id == "ntn-genesis"
- chat.el: handle_dharma_room_turn — soul builds its own context from its
own engram, assembles system prompt, calls LLM, persists episodic memory;
also fix is_new_tool scoping bug in handle_chat_agentic (use has_tool)
- routes.el: wire dharma_room_turn event type before chat_as_soul branch
- rebuild dist/neuron: handle_dharma_room_turn now compiled in
elp-input.el: walk frame_nodes to pick the first node whose content
contains the query topic (case-insensitive) rather than always taking
index 0 — prevents the always-high-salience CGI architecture memory
from hijacking every ELP response.
chat.el: rewrite handle_chat_agentic to run the tool loop natively in
El using http_post_with_headers + Map headers, bypassing the broken
llm_call_agentic(model, system, message, tools) C binding that cast a
JSON String as an ElList and never serialized tools. New impl supports
up to 8 tool-use iterations with read_file, write_file, web_get,
search_memory, and run_command dispatch.
Replace scan-by-offset fallback with engram_get_node_json calls for the
known high-salience identity nodes (family, origin). Offset-based scanning
is order-dependent and unreliable; direct ID fetch is stable regardless of
snapshot position. Ensures biographical context (Fox, Bobby, etc.) is
always in the system prompt when vector search returns nothing.
Routes a new event_type "chat_as_soul" through dharma/recv. The Studio
preassembles the system_prompt + transcript and dispatches per-speaker;
the soul-binary just performs the LLM call as the requested speaker_slug.
No engram_compile here — each soul has its own engram (88xx) and the
Studio queries it before composing the prompt.
Also: track the previously-untracked split source modules (chat, routes,
memory, awareness, studio) and add build.sh so the binary can be rebuilt
without the studio’s concat trick. elb resolves the import graph and
emits one .c per .el; we link them together with cc. dist/soul-el now
points at dist/neuron via symlink (matching the launchctl plist).
will.anderson
Tim Lingo