llm: routes that name a host, a backup and a window, and a profile that reads them ...

`llm.json` replaces `OLLAMA_BACKENDS_FILE`. It has targets (host and key
environment variable) and routes, where a route is an ordered chain of
`model @ target` entries, each with its own `context_window` and options. The
`default` route now starts on `glm-5.3-flash:cloud` and backs it with
`qwen3.6:35b-128k` on the home host, both at 131072 tokens, so a failover no
longer changes the budget the compressor and `num_ctx` are accounted against.
Embeddings get their own `embedding` route instead of a pinned host.

The engine classifies a failure (network, quota, auth, server, missing model),
cools that entry and moves the call down the chain; a background probe watches
only degraded targets and lets the next turn return to the primary once it is
healthy — it never interrupts a running turn. A profile joins a route with
`llm_route`, and the loader now actually reads it: `llm_route` and
`context_window` were declared on `AgentProfile` and written into every
`config.json` while the loader skipped both, the same silent no-op that
`is_admin_only` used to be, so every profile ran the legacy model list at the
global window. The writer emits them too, or an admin edit would erase the
route from disk.

The turn's resolved entry travels to the UI: the first chunk is stamped with
model and target, `model_info` carries `fallback` when a backup answered, and
the chat header shows a chip only then. `serving_primary` compares the target
as well as the model name, because a route may run one model on two hosts.
`/health` gains an `llm` block with the active entry, target states and missing
models.

`deploy/ollama/` keeps the local model's definition honest: MTP off (slower at
every context on this host), `presence_penalty 0` (the base model's 1.5 breaks
agentic tool calls), and `num_gpu 40` — Ollama's automatic fit claims a 128k
f16 slot fits and then dies mid-prefill with CUDA OOM; 40 of 42 layers leaves
~400 MiB and decodes at ~77 tok/s, 38 layers collapses to 48, and 39 OOMs.
q8_0 KV measured 37 tok/s against 70 on f16 here, so the cache stays f16.

tools: list_tools defaults to the profile the run executes as ...

Asking "what tools do I have?" required the agent to know its own profile id
— and to be right about it after a switch_profile had moved the session. The
run knows: run_stream now publishes the active profile id (re-published when
switch_profile reloads the run) alongside the model, SubAgentRunner publishes
its own rather than inheriting the parent's, and ToolContext carries it into
every execute() call.

list_tools reads that when profile_id is omitted, so the bare call answers the
question, and it says which profile it assumed ("current profile") so the
answer cannot be mistaken for another profile's.

scope='agent'|'subagent' selects which of the profile's two toolsets to list —
the set spawn_agent would hand a sub-agent running that profile, which is a
different list and until now had no way to be inspected.

Item D of the list_tools plan, kept separate from the accuracy/compactness work.

docs: sync with the plan rework and compression pipeline ...

- planning: plan tool flow (agent-invoked, no pre-turn gate), confirmation
  by COMPLEXITY, think=False + 20k-char Phase 1 window, retired flags
  removed from profiles/api docs
- compression: all four triggers through compress_and_save_session,
  real-baseline gates, head+tail summary input, _plan_compression shared
  decision, actual config defaults (0.90 threshold, 6000 summary tokens,
  32k input cap)

Fix settings route switching and document API token system ...

- App.vue: make route reactive via ref + getRouteFromHash() so
  #settings toggles work without page reload
- docs/api_tokens.md: new comprehensive API token auth doc
- docs/api.md: add /api-tokens REST endpoints
- docs/auth.md: add token flow architecture diagram and resolution order
- docs/websocket.md: add auth section with cookie vs query-param token
- docs/architecture.md: update to AgentSessionOrchestrator + ToolContext
- docs/tools.md: add gnexus-creds MCP tools
- docs/index.md: link to api_tokens.md
- Rebuild webclient dist

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

Docs audit: fix outdated references (PostgreSQL, Vue client, profiles, tools) ...

- architecture.md: SQLite → PostgreSQL + pgvector
- README.md: vanilla JS → Vue 3 + Pinia, remove smart_home, update temps
- profiles.md: remove smart_home, add discuss, update temperatures
- tools.md: add missing built-in tools, update user tools list
- sessions.md: fix outdated references
- NAVI.md: sync with current stack
- persona.txt: update self-extension and content_publish guidance
- content_publish.md manual: reflect session_dir-based no-copy design
- content_store.py & content_publish.py: inline with docs

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

WelcomeScreen polish, root-path fix, docs update ...

- Move mobile sidebar button to top-left corner (no header bar backdrop)
- Show WelcomeScreen on / with no hash instead of auto-loading first session
- Docs: document Ollama multi-server fallback, model priority lists, OLLAMA_BACKENDS_FILE

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Add backend documentation ...

10 markdown files covering all backend subsystems: architecture,
agent loop, tool system, sessions, WebSocket protocol, profiles,
memory, config, and API reference. Structured for AI readability
with a single entry point (docs/index.md) and cross-references.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>