navi-web: make the batch shape the schema, drop Brave ...

Every recorded web_search and web_view call in production carried a scalar
(20 of 20, 8 of 8), including sessions where three searches on one topic went
out one after another. The recommendation was already written in three
places — the parameter description, the tool docstring and the server's
summary line — so prose was not the problem: `str | list[str]` renders as
`anyOf: [string, array]`, and the model took the first branch.

The parameter is now a pure array with minItems/maxItems and an examples
entry. A BeforeValidator folds a bare "query": "…" into a one-item list, so a
laxer caller still works; the cap rides in json_schema_extra rather than
pydantic's max_length, so four queries reach the code that runs three and
names the rest instead of failing validation.

Brave is gone on both paths: the keyed Search API (signup answers 403, so a
third backend that can never be enabled) and the ddgs engine of the same name,
which answers nothing from this host. The chain is SearXNG -> ddgs.

The persona's parallelism rule now separates "several items in one call" from
"several calls in one message" — it used to read "when the profile allows
parallel tool calls", which the model could only read as "not here".

navi-web: pin the ddgs engines, drop bing, and give the fallback room ...

SearXNG answered the session's searches with noise. Bing, asked explicitly,
returns trending/homepage blocks for queries it cannot match (Block Blast for
a motherboard query); because the list is non-empty the chain accepted it as an
answer and never reached the working fallback. The request now pins
google,duckduckgo and asks for language=all — the pinned uk-UA was what made the
instance's DDG engine return CAPTCHA (kl=ua-uk) on every request.

The ddgs leg had a quieter bug. ddgs v9 has no "html" backend, and an unknown
name does not fail: it silently means "auto" — all engines shuffled together,
yandex and grokipedia included. That is where the slow, flaky, mixed-provenance
results came from. The engine set is now explicit and yandex-free. The 4s client
timeout and 12s chain budget also could not fit a real 1-13s multi-engine scrape,
so they become 10s and 20s.

Wire the Brave key placeholder the docs already described: optional, mapped
with a ":-" fallback so an empty value means off.

navi-web: search backends, three-at-a-time batches, and pages read as markdown ...

web_search runs SearXNG first, DuckDuckGo with one retry after a real failure,
and Brave last; measured 0.2-1.4s through SearXNG against 1.7-11.8s on
scraping. Both tools take one item or up to three and run them concurrently —
three pages went from 17.3s to 1.9s, three searches from 3.5s to 0.6s — each
under its own deadline, so one hung backend or page is named in the output
instead of erasing what the others already returned. Text is capped at 20k for
one page and 40k for a batch. A call that opened nothing now raises: a green
journal line carrying "success": false is how a server whose browser could not
launch at all looked like a working one, and how 604 search calls in two weeks
reported no errors.

web_view returns the main content as markdown, not innerText after a tag
kill-list. The old path could not tell navigation from prose (462 of the asyncio
page's 1018 lines were shorter than 40 characters), collapsed tables into one
line per thousand characters — news.ycombinator.com came back as four lines —
marked no headings and dropped every link. trafilatura now picks the content by
density, and its html output keeps the whitespace inside <pre> that its markdown
output throws away, so the fragment is rendered here: # headings, fenced code
with its indentation, table rows joined by |, and up to 40 links lifted into a
"Links on this page" appendix rather than sprinkled through the sentences.
Threads are read again with comments when the extractor keeps less than a
quarter of the visible text; if it still finds nothing, the old visible-text
read answers and metadata.extractor says which one did.

trafilatura goes into the server's own venv, which deploy/install.sh does not
build — docs/mcp.md and deploy/UPDATE.md carry the install line. The tests load
the server by path, so it also joins Navi's dev extra.

mcp: credentials leave the tree, and sub-agents lose the task board ...

Five tracked configs (gnexus-creds, gntodo, hard-panel, synapse, tgclient)
carried live bearer tokens — in git, in every clone, and handed to the admin
client by GET /admin/mcp/config. They now name a variable, and the value lives
in the service .env (chmod 600, untracked).

Substitution happens once, at transport open, next to the project-relative
path resolution: that is the single place a transport is built, so every
stored and serialised config stays placeholder-only and save_mcp_servers —
reached by create_mcp_server and PUT /admin/mcp/config — cannot write a secret
back into a tracked file. A variable that is not set refuses the connection
instead of dropping the header, which would fail open: a server may answer an
unauthenticated request as an anonymous user rather than returning 401.

Sub-agents also drop gntodo, gnexus-creds, tgclient and synapse from their
scopes, and the runner injects a scope anchor unconditionally — a sub-agent
asked to echo one word had picked a project off the task board and researched
it for forty iterations.

Docs: docs/mcp.md#secrets, a migration recipe in deploy/UPDATE.md, the variable
names in .env.example and deploy/env.template, and a regression guard over the
tracked configs.

The old values stay in git history; rotating all five at their sources is the
remediation, not a follow-up.

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.

mcp: point navi_ui at the port its server actually binds ...

navi_ui is navi's own MCP server (navi/mcp/ui_server), started in-process on
NAVI_UI_MCP_PORT — 8098. The config still carried the pre-8099/8098 default,
localhost:8001, where nothing has listened for a long time: on prod the connect
fails on every start and render_component only ever appeared as an unregistered
phantom in list_tools.

The URL now names the loopback literal rather than "localhost", which can
resolve to ::1 while the server binds IPv4 only.

Three tests assert the file against the live FastMCP object (host, port, path,
transport) instead of a second copy of the setting — with the old URL two of
them fail, so the drift that produced this cannot come back unnoticed.

config: give tgclient the shared key it needs to handshake ...

The server declares a user_key slot and no shared credential, so the
startup handshake went out unauthenticated, got a 401, and the client
was marked disconnected — which kept its tools out of the registry
entirely, groups or no groups. The shared key now backs the handshake
and stays the fallback: a personal key from /mcp-keys still wins.

config: tool groups for tgclient and synapse ...

Both servers declare no groups, so every profile asking for "tgclient":
["read", "write"] resolved to nothing: resolve_group reads the static
config, returned [], and no mcp__tgclient__* name ever reached the agent.
Worse, the server's own instructions did reach it — they are selected by
server name, not by group — so the model was told about tools it did not
have. synapse is not exposed by any profile, so its groups change nothing
today; without them, exposing it would repeat the same failure.

read  — observe only.
write — changes to sources, types, targets and routing rules.
admin — hub-wide knobs, not routing: issuing and revoking a source's API
        key, and settings overrides on top of .env. The same fence
        gnexus-book puts around its service-operator tools.

config: point the tgclient MCP server at the live host ...

The committed value was the local dev address (localhost:8710, where
~/Projects/tgclient-mcp serves it) and the server ran with the wrong public
host, so the tools never connected. Both clones now use
https://tgclientmcp.gnexus.space/mcp.

No default headers: the key is per-user by design (BYOD settings field), and
until one is entered the server answers 401.

config: add the gntodo MCP server

config: capture the live server configuration ...

Profiles gain the gntodo / gnexus-book / gnexus-creds scopes for agent and
subagent runs, refreshed model lists, and write access where the live setup
has it. MCP server configs pick up their user_key slots, gnexus-book learns
delete_pending_change, and the hard-panel / synapse / tgclient servers join
the tree.

Merge origin/master (b7743f8): PWA icons, MCP settings tab, android push, runbook

MCP settings tab: list every connected server, slot only where declared ...

The tab was empty on every install: it listed only servers whose config
declares a `user_key` slot, and no config declared one — which read as
"no MCP servers connected" even though five are wired to profiles.

- GET /mcp-keys now returns every server referenced by at least one
  profile, keyed ones first, with `accepts_user_key`, the slot location
  (null when there is none) and the profile ids that connect it. The
  per-user key store is skipped entirely when nothing has a slot.
- gnexus-creds declares `user_key: {header: Authorization, prefix:
  "Bearer "}` — it is the one server carrying a shared credential, so its
  personal-key field is now real: users with a key run under their own,
  users without one fall back to the shared default.
- The panel lists all servers (transport + profiles), dims the keyless
  rows, and shows a key input only for slotted ones, spelling out the
  shared-key fallback.

docs/api.md and docs/mcp.md updated; backend 1367 passed, webclient 148.

.

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>

Merge branch 'master' of https://git.gnexus.space/git/root/navi-1

Update gnexus-creds MCP instructions: require tags, category, and allow_mcp ...

- Add rule to always include `tags` and `category` when creating secrets
- Add rule to always set `allow_mcp=true` so secrets remain visible through MCP

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

Merge branch 'master' of https://git.gnexus.space/git/root/navi-1

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>

merge

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>

chore: remove test MCP servers from repo ...

project_health and time_toolkit were created for development testing
and should not be part of the committed codebase.

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>