subagents, secrets: an honest result contract, and two leaks closed ...

A pass over the sub-agent system, plus the two findings from the previous one.

Leaks:

- `redact_args` / `is_sensitive_key` (navi/tools/_internal/redact.py) mask
  credential-shaped keys at every log site that prints tool arguments — by key
  name, for all tools, so a future MCP tool is covered without declaring
  anything. ssh_exec passwords were sitting in the prod journal in plaintext.
- `mcp_servers.d/*.json` are tracked in git and carried the scaffolding
  machine's absolute paths, so navi-3d/navi-web silently vanished from the
  toolset off that machine. They now hold project-relative paths, resolved in
  `McpClient.open_transport` — not at load time, because create_mcp_server
  round-trips every config file through save_mcp_servers.

Sub-agent result contract:

- `run_ephemeral` returns a `SubAgentOutcome` (text + status: ok, timeout,
  max_iterations, thinking_stall, user_stop, context_overflow) instead of
  `(text, bool)`. Every exit routes through `SubAgentRunner._finish`, so token
  accounting is never dropped and a partial run always carries a progress
  report — the stop-after-stream path used to return a bare string.
- `spawn_agent` renders its header from the status. Before this, every short
  run reached the parent as "hit iteration limit", and the parent repeats that
  diagnosis to the user — a timeout was reported as an iteration limit.
- `ContextTooLargeError` no longer kills a sub-agent: the parent compresses its
  own context, a sub-agent has no session to compress into, so it stops with
  `context_overflow` and hands back what it did rather than surfacing as
  "Sub-agent failed: …" with the whole run discarded.
- The result is capped at 8000 chars (head and tail kept) so a long run cannot
  flood the parent's context, and tool arguments in the progress report go
  through `redact_args`.
- The navi-3d calling convention left the runner for the server's own tool
  schemas — a generic runner should not know one MCP server's path shapes.
- Validation moved inside spawn_agent's try: a bad argument is a clean
  ToolResult the model can read, not an exception in the parent's loop.

Tests: 1636 passed, 1 skipped. New: SubAgentOutcome paths and headers, result
truncation, context overflow, clean argument failures.

tools, mcp: a description is a hook, not a manual ...

With 24 tools in a profile the schemas are the largest fixed block of every
request, and they are paid for whether or not the tool is called. Eleven of
them carried a manual's worth of prose in their `description` — examples,
error tables, "common mistakes", the mechanics of the file areas. Reading
them against the manuals first, the manuals already held all of it, and
richer: this was duplication sitting in the one place the model cannot avoid
reading, not knowledge that had nowhere else to live. So the descriptions
became selection hooks — what the tool is for, when to pick it over its
neighbour, and the one rule that cannot wait — and the detail moved to
tool_manual("<tool>"), which costs nothing until the tool is actually in
play.

filesystem, spawn_agent, schedule_recall, manage_recall, scratchpad, plan,
share_file, content_publish, reflect, todo and peer. Descriptions drop from
18.4 KB to 11.5 KB, those tools' schemas from 25.5 KB to 16.8 KB, and a
profile's whole native toolset from 38.3 KB to 29.6 KB (server_admin,
developer; secretary 33.7 → 25.0, navi_code 32.9 → 25.9, tool_developer
37.9 → 29.2, modeler_3d 33.4 → 24.8). Stated as a budget rather than a byte
count: roughly 4k tokens of the model's window per request, back.

Two things were deliberately not shortened. The filesystem edit ladder
(`edit` → `edit_lines` → `smart_edit`, last resort, costs an LLM call) and
todo's mandatory `validation` on `done` both exist to prevent an extra
round trip; a shorter description there would trade tokens for turns. What
todo lost is the prose around the rule, not the rule. `enabled.json` was
left alone too: weather, gmail and get_current_datetime are opt-in and the
DB shows 12, 16 and 40 calls, so they are opt-in tools that are actually
used.

peer had no manual at all, which is how this surfaced: its description was
the only documentation the tool had. manuals/peer.md is now written from
the tool and its /peer route — the ask/status/list actions, the fact that
the hive is only a phone book and the question travels peer-to-peer, the
one-concurrent-answer semaphore, the two independent recursion guards, and
the six error codes.

The MCP server instructions leave the system prompt the same way. They were
8 KB of always-present prose per request, most of it workflow detail the
model only needs when it is about to use that server. Each server now
contributes one line — a new optional `summary` field in mcp_servers.d/*.json,
defaulting to the first sentence of its `instructions` — and
tool_manual("<server>") returns the full text plus the tool names the server
declares. server_admin's MCP block goes from 8.3 KB to 1.3 KB, secretary's
from 8.1 to 1.2. tool_manual learned to answer for a server (a tool name
still wins over a server of the same name, and dash/underscore spelling is
tolerated), and the index names the servers alongside the tools.

One judgement call worth recording: gnexus-book's and navi-web's
instructions end in an absolute "NEVER bypass these tools with filesystem,
terminal or code_exec" rule. Moving that on demand would have been a
behavioural regression dressed as a token saving, so those two `summary`
fields carry the prohibition verbatim alongside the hook, and it stays
always visible.

docs/tools.md gains a section on the split (a description is paid for every
request, a manual only when the tool is used), which is where the next
person will look before trimming a description back into a manual.

Full suite green (1577 passed, 1 skipped). No frontend change and no new
dependency, so the deploy is a pull and a restart.

Await the session pool in notify and three neighbours ...

PgSessionStore._get_pool() is async, and four call sites passed its coroutine
straight into a store constructor, so the first query inside died with
"'coroutine' object has no attribute 'fetchrow'": notify always failed, the
reaction runner never got past reading its settings, synapse_instructions was
unusable, and the BYOK resolver caught the AttributeError and silently fell
back to the default credential.

The tests missed it because each one mocked the store or the pool provider
away; the new ones run on a fake asyncpg pool with nothing faked below the tool.

mcp keys W2: per-user client clones, KeyResolver wiring, user_id in call path

mcp keys W1: user_key config slot, encrypted keystore, /mcp-keys REST

port: 8000/8001 -> 8099/8098 everywhere ...

navi runs on shared servers where 8000/8001 are usually taken. New
defaults: API 8099, navi_ui MCP 8098. Touched: config defaults
(navi_port, navi_ui_mcp_port, public_url, gnauth_redirect_uri),
navi-server launcher docs, env.template/.env.example, install.sh
health-check fallback, terminal client base_url, webclient dev configs
(useWebSocket, contentLinks, vite proxy), android url hint, docs.
Also made the navi_ui FastMCP constructor port settings-driven instead
of a hardcoded 8001 (it was overridden at start anyway).

mcp: a dead MCP endpoint no longer kills server startup ...

A failed transport connect inside the MCP SDK's anyio cancel scopes
surfaces as CancelledError without any task.cancel(). The runner mistook
that for a real teardown, cancelled the in-flight caller's future, and
McpManager.load_all (which only catches Exception) let it blow up the
whole lifespan startup — one unreachable server in mcp_servers.d/ meant
a dead Navi.

The runner now distinguishes real task cancellation
(asyncio.current_task().cancelling()) from the anyio artifact: the
latter is surfaced to the caller as a normal connect failure, the
server pool marks it disconnected and the health-check loop retries.
Also, when the runner dies for any reason, pending queue commands are
failed instead of leaving _send callers hanging forever.

Merge branch 'master' into feature/navi-code ...

# Conflicts:
#	navi/api/websocket.py
#	navi/config.py
#	navi/core/agent.py
#	navi/core/orchestrator.py
#	navi/main.py

mcp: dedicated runner task per client (fix cross-task cancel-scope on shutdown) ...

MCP client SDK transports (stdio/sse/streamable_http) + ClientSession are
anyio task groups whose cancel scopes require __aenter__/__aexit__ in the
SAME asyncio task. McpClient entered the transport in one task (lifespan
connect / health-check reconnect / request retry) and exited it in another
(lifespan teardown) -> RuntimeError: Attempted to exit cancel scope in a
different task than it was entered in.

Refactor McpClient to own a single long-running runner task that holds the
AsyncExitStack and performs ALL transport enter/exit + list_tools/call_tool.
The public async API (connect/disconnect/list_tools/call_tool/mark_disconnected)
just enqueues a _Cmd and awaits a Future, so callers from any task no longer
cross cancel-scope boundaries. connected/instructions mirror from the runner
onto the instance to stay sync-readable. disconnect() enqueues a stop command
and awaits shield(runner) so teardown isn't interrupted by lifespan cancel.

Also call mcp_manager.stop_health_check() BEFORE disconnect_all() in
AppContainer.shutdown() so the health-check task cannot enqueue onto a
client whose runner is being torn down. mark_disconnected() is now async
(queued) and its manager caller updated.

Regression test: connect in one task, list_tools in a second, disconnect in
a third — the exact scenario that raised the RuntimeError before.

feat: integrate navi_ui MCP server (card_grid + form) into master ...

Port the internal navi_ui MCP server from the vmkdemo branch (it never
landed on master). The server exposes render_component, which returns a
structured JSON envelope; navi/mcp/tools.py extracts metadata.ui_component
onto the role="tool" message, and the webclient renders the component
(card_grid, form) inline inside the assistant turn.

Backend
- navi/mcp/ui_server/: FastMCP server + component registry with card_grid
  and form components (pydantic-validated payloads, LLM-friendly schema docs)
- mcp_servers.d/navi_ui.json: streamable_http config, group "ui"
- config.py: navi_ui_mcp_enabled/host/port flags
- main.py: start UI server in lifespan (task + wait-for-ready + cancel)
- mcp/tools.py: navi_ui envelope parsing; "Error:" results surface as
  failed tool calls so the UI card is not green
- orchestrator.py + agent.py: run_stream(hidden=) for form submissions
  (single is_display=False, is_context=True user message)
- api/websocket.py: extract _start_agent_run helper, add form_submit
  branch that delivers submitted form values as a hidden user message
- profiles/secretary: enable navi_ui "ui" group (agent + subagent)
- .env.example: NAVI_UI_MCP_* flags
- tests/unit/mcp/test_ui_server.py

Webclient
- components/ui/{registry.js,CardGrid.vue,Form.vue}: auto-discovered
  renderers (snake_case <-> PascalCase aliasing)
- components/messages/UiComponentCard.vue: wrapper rendered in
  AssistantMessage when entry.kind === 'ui_component'
- stores/chat.js: extract ui_component from tool_call metadata in both
  live stream and history-replay paths
- composables/useWebSocket.js: note that ui_component rides tool_call
- tests/unit/components/ui/* (17 tests)
- dist rebuilt

Excluded from the vmkdemo port: the stale single-file navi/mcp/ui_server.py
duplicate, the realtor profile, and the vmk_data server (unrelated real
estate work that was interleaved with navi_ui on vmkdemo).

Co-Authored-By: Claude <noreply@anthropic.com>

Fix MCP tool registration at startup ...

Root cause: _on_mcp_server_connected was defined and registered AFTER
mcp_manager.load_all(), so startup connections never registered their
tools into the ToolRegistry.

Fix: explicitly iterate connected clients after build_default_registries()
creates tool_registry, and register their MCP tools before starting the
health-check loop. The callback stays for future reconnects.

Also adds diagnostic warning in build_tool_list when tools are missing.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Fix MCP tool availability after health-check disconnect/reconnect ...

- connect() now calls _cleanup() first to avoid stale transport leaks.
- mark_disconnected() clears _session so _ensure_connected() knows
  the client truly needs a fresh session.
- register_mcp_tools() is no longer a no-op; it re-registers all
  connected MCP tools so reload_tools correctly restores them.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Fix MCP health-check spamming "connected" toasts every 30s ...

Only publish McpStatusUpdate "connected" when a server transitions
from disconnected -> connected, not on every routine poll.
Track last-known state in _connected_status dict.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Add MCP health check loop, auto-reconnect, and system toast notifications ...

Backend:
- McpManager: keep all configured servers in the pool even if connect()
  fails at startup; health-check loop (30s) tries to reconnect dead servers
  and verifies live ones with list_tools()
- McpManager: set_on_server_connected callback re-registers tools when a
  dead server comes back online
- McpClient: add mark_disconnected() for silent drop detection
- McpStatusTool: skip list_tools() for disconnected servers
- Orchestrator: broadcast mcp_status_update to all WebSocket sessions
- New event type McpStatusUpdate with server_name, status, tool_count

Webclient:
- useWebSocket: handle mcp_status_update → toast.success/toast.error

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Fix MCP transport teardown race with anyio task groups

Add MCP streamable_http transport, integrate gnexus-creds, and document headless nodes ...

- navi/mcp/client.py: add streamable_http transport via httpx + mcp.client.streamable_http
- navi/mcp/config.py: add "streamable_http" to transport literal and is_streamable_http property
- mcp_servers.d/gnexus-creds.json: new MCP server config with overlay instructions for secret workflow
- docs/future_headless_nodes.md: architecture exploration for headless Navi node swarm

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Pass explicit ToolContext to tools instead of hidden ContextVars ...

Add ToolContext dataclass (session_id, event_sink, stop_event, model,
user_id, user_role, user_info) and thread it through the execution chain:
Agent._execute_tools_with_sink → ToolExecutor → tool.execute().

All ~25 tools updated to accept ctx parameter. Tools that previously
read ContextVar now prefer ctx when provided, falling back to
ContextVar for backward compatibility.

Tests updated to pass ToolContext explicitly — no more test fixtures
that set current_session_id / current_user_id ContextVars.

ContextVar setters remain as fallback for non-tool consumers
(ai_helper, context_builder, planning) and will be removed in a
follow-up refactor.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Fix stop button responsiveness and shutdown CancelledError ...

Agent loop (_execute_tools_with_sink):
- Poll stop_event every 1s while draining the event sink via asyncio.wait_for
- When stopped, cancel the tool task, yield a synthetic ToolEvent failure,
  append a cancellation message to session, yield StreamStopped, and return
- Pass stop_event into _execute_tools_with_sink call site

Subagent runner:
- Check stop_event at the start of each tool in turn_tool_calls loop
- Returns early with ("", False) when stopped mid-batch

McpManager.disconnect_all():
- Disconnect clients sequentially instead of asyncio.gather
- Handle asyncio.CancelledError per-client to avoid shutdown traceback

AppContainer.shutdown():
- Catch BaseException instead of Exception for MCP and DB cleanup

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Migrate MCP tool naming from mcp:server:tool to mcp__server__tool ...

The colon separator (mcp:server:tool) confuses many LLMs during
tool-calling because colons appear in schemas and URLs. Switch to
double-underscore separator (mcp__server__tool) for robust parsing.

Key changes:
- navi/mcp/tools.py: add build_mcp_name(), parse_mcp_name(), is_mcp_tool()
- navi/core/tool_executor.py: update _resolve_tool() with new helpers
  and legacy colon fallback for old sessions
- navi/core/tool_utils.py, subagent_runner.py: use build_mcp_name()
- navi/api/routes/{admin,agents}.py: prefix via build_mcp_name()
- navi/tools/{list_tools,reload_tools}.py: migrated
- All profile configs + system_prompt.txt: replace mcp: with mcp__
- manuals/{model_3d,lint_scad,render_3d,spawn_agent}.md: updated
- mcp_servers.d/gnexus-book.json: instructions updated
- docs/{api,profiles,tools,mechanics,visual.html}: updated
- tests: test_tool_executor.py and test_mcp.py aligned

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

McpTool: auto-inject session_id + normalize navi-3d paths ...

- McpTool.execute() now forces the real session_id from current_session_id
  ContextVar, preventing LLM hallucinations of wrong UUIDs (ghost-session bug).
- For navi-3d MCP server, source_path/output_path are normalized to basename
  to prevent double path nesting when the LLM passes full relative paths.
- Updated MCP tool descriptions to ask for filenames only.
- Added system prompt instructions in context_builder and subagent_runner
  reminding the model to pass bare filenames to navi-3d tools.

396 passed, 1 skipped

MCP: cache config in McpManager, add exponential backoff to McpClient reconnect ...

McpManager:
- Cache loaded configs in self._configs (loaded once at load_all)
- resolve_group() and get_instructions() read from cache instead of disk
- reload_all() busts the cache before re-reading
- Fallback to disk when cache is empty (tests / first call without load_all)

McpClient:
- Exponential backoff on reconnect: base 1s, max 30s, ±20% jitter
- Backoff resets on successful connect, doubles on failure
- _ensure_connected() blocks reconnect if within backoff window
- Prevents thundering herd against a flapping MCP server

392 passed, 1 skipped

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Refactor: move tool helper modules into _internal subpackage ...

Moves non-tool infrastructure out of navi/tools/ root so that only
actual tool classes live there:

  base.py           → _internal/base.py
  loader.py         → _internal/loader.py
  middleware.py     → _internal/middleware.py
  logging_middleware.py → _internal/logging_middleware.py
  _time_parser.py   → _internal/time_parser.py

All imports updated across core/, api/, mcp/, tools/, and tests/.
No proxy files remain in navi/tools/ root.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

fix: wire test_mcp_tool into MCP manager startup injection ...

The startup loop in main.py assigns _mcp_manager only to tools that
have the attribute, but test_mcp_tool never declared it and mcp_status
used _manager instead of _mcp_manager — so both received None forever.

Changes:
- test_mcp_tool: add __init__(mcp_manager) with _mcp_manager, fallback
  to module-level import if startup wiring skipped
- mcp_status: rename _manager → _mcp_manager, same fallback
- registry.py: register create_mcp_server and test_mcp_tool builtins
- main.py: include test_mcp_tool in startup wiring loop
- client.py: add 5s timeout to disconnect cleanup

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

refactor: migrate MCP config to directory-based mcp_servers.d ...

Replaces monolithic mcp_servers.json with per-server files in
mcp_servers.d/<name>.json. Filename stem becomes the server name.

- load_mcp_servers() reads directory globs, auto-migrates legacy file
- save_mcp_servers() writes per-server files, cleans up stale ones
- Update docstrings in manager.py and context_builder.py

Auto-migration: existing servers (gnexus-book, navi-3d, navi-web) plus
new ones (project_health, time_toolkit) now live in mcp_servers.d/.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Add MCP admin endpoints for config, reconnect, status, test, and profile group management ...

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Fix agent.py _tool_list to use colon-delimited MCP names ...

The main registry and API routes were migrated, but Agent._tool_list
still built names with the old underscore format. This meant MCP tools
were silently dropped from the tool list passed to the LLM, causing
"tool not found" when the model correctly called mcp:server:tool names.

Also updates stale docstring in McpTools.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Rename MCP tools to mcp:server:tool format and restore human-readable names ...

- Core naming: mcp_server_tool → mcp:server:tool (colon-delimited)
- navi-web tools: search/view/request → web_search/web_view/http_request
- navi-3d tools: compile_scad/render_stl/lint_scad (unchanged names)
- Updated all profile configs, system prompts, docs, manuals, tests
- Added new lint_scad.md manual
- Fixed modeler_3d prompt stale references (scad_lint, model_3d, render_3d)
- All 240 tests pass

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Migrate 3D modeling tools to standalone MCP server navi-3d ...

Phase 0 — Fix MCP error propagation:
- McpClient.call_tool now returns (output, is_error) tuple
- McpTool.execute sets success=False when MCP reports isError=True
- Fixes silent failures where MCP errors looked like success

Phase 1 — Create mcp-server-navi-3d:
- New standalone MCP server in mcp-servers/navi-3d/
- Tools: compile_scad, render_stl, lint_scad
- Session-scoped path resolution via SESSION_FILES_DIR env
- Anti-escape validation for security
- Includes tests/unit/test_scad_analyze.py

Phase 2 — Remove from Navi core:
- Deleted navi/tools/{model_3d,render_3d,scad_lint}.py
- Removed from registry.py builtins and navi/tools/__init__.py
- Updated pyproject.toml testpaths to exclude mcp-servers/

Phase 3 — Wire into Navi config:
- Added navi-3d block to mcp_servers.json (SSE on :8002)
- Updated modeler_3d profile: mcp_servers + updated system_prompt
- All old tool names replaced with mcp_navi-3d_* equivalents

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Add auto-reconnect to MCP client on call_tool/list_tools ...

- McpClient._ensure_connected() reconnects if session is dead
- list_tools() and call_tool() try reconnect + one retry on failure
- Fixes crash when MCP server restarts between calls

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Clarify knowledge persistence prompts