memory+llm: three failures the prod logs gave up ...

All three came out of a survey of the last days of journalctl on prod,
and each one silently destroyed something the user had already paid for.

memory_facts: the no-embedding INSERT bound $13 while its column list
had 12 entries, so every fact written while the embedding backend was
down died on PostgresSyntaxError and the extraction was lost — 47
embed failures in three days, most of them landing in this branch.

Embedding input now gets clipped instead of 400'd away. A 400 takes the
whole embedding with it and recall drops to ILIKE over everything; a
reaction-session prompt (a full event envelope inlined) did that 41
times. settings.embedding_max_chars (6000, 0 disables) caps the input
at the model's window, so recall still works on the head of the text.

Message strips NUL bytes at the model boundary. PostgreSQL text cannot
hold one, and a NUL arriving in a tool result (reading a binary file)
made the whole session_messages INSERT fail with
CharacterNotInRepertoireError — the turn died and the user lost it.
Three times on 2026-10-07. As a Message validator it covers every
writer downstream: session store, kv store, memory extraction.

Each new test was checked to fail with its fix reverted.

tui: show the currently-served model in the status panel ...

The status panel's Model line was fed the global ollama_default_model, not the
session/profile model, and the server never told the client which model
actually served a call. Now:

- Backends stamp the resolved model onto LLMChunk (first chunk) / LLMResponse.
  The fallback backend reports the model that survived its server+model
  priority list (may differ from the profile's first choice).
- New ModelInfo event ({"type":"model_info","model":...}) emitted once per
  turn from agent._consume_stream, re-emitted only when the model changes
  across iterations. Additive WS event — old clients ignore it.
- TUI: attach_session/switch fetch the profile's configured model (first of
  profile.model) via api.get_profile_model so the panel shows a value before
  the first request; model_info then refines it to the actually-served model.
  Not forwarded to the chat panel. raw CLI prints "[model] ...".

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

compressor: structured summaries, profile-aware compression, adaptive keep_recent ...

- Replace free-form summary with strict Markdown template (Goal, Active Files,
  Decisions, Completed Work, Pending Work/Todo, Errors, Key Values).
- Keep filesystem/code_exec/terminal tool results and messages with
  is_compression_critical=True verbatim during compression instead of 300-char truncation.
- Make compression profile-aware: AgentProfile gains compression_keep_recent,
  compression_max_tokens, compression_prompt_file. navi_code uses dedicated
  compression prompt and larger keep_recent/max_tokens.
- Adaptive partition_messages(): important turns (user corrections, errors,
  critical tools) survive longer; filler/social turns compress sooner.
- Increase default context_summary_max_tokens from 3000 to 4000.
- Propagate active profile changes to ContextCompressor and SubAgentRunner.

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

Add session message archive table + global sequence_number tracking ...

Schema:
- session_messages_archive — identical structure, stores old messages.
- sessions.next_sequence    — monotonic seq counter per session.
- sessions.archive_threshold — split point between hot and archive.

Behaviour:
- get() / _build_sessions() load only seq >= archive_threshold (hot).
- save() UPDATEs existing rows (seq >= 0) and INSERTs new ones (seq = -1)
  with auto-assigned sequence_number = next_sequence, next_sequence+1, ...
- archive_old_messages() moves a batch to archive and bumps the threshold.

This keeps the hot table bounded so list/get RAM stays flat regardless
of total session history size.

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

Phase 2: Dual-write with is_context/is_display flags on Message ...

- Message model gets is_context and is_display bools
- PgSessionStore.save() writes flags directly to session_messages
- Agent sets is_context=False on display-only messages, is_display=False on context-only
- Planning: plan context msg is_display=False, plan marker is_context=False
- Compression: summarized messages get is_context=False, summary added to messages with is_display=False
- Tests updated for extra user display+context messages per turn

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

fix(recall): stabilize scheduled callback system and improve UX ...

Backend fixes:
- stop_session now stops headless recall runs via _busy_sessions dict
- _fire_recall sets user ContextVars so tools work correctly
- MaxIterationsReached treated as success, not failure
- skip_next_recall uses GREATEST(trigger_at, now) for overdue recalls
- schedule_recall rejects past trigger times
- timezone offset double-adjustment fixed for aware datetimes
- _fire_recall registers _AgentRun for reconnect/replay support
- session_sync race with stream_start fixed

Frontend improvements:
- Recall banner moved to ChatHeader with live Cancel/Skip buttons
- Recall messages styled with is_recall flag and badge
- Real-time recall updates via WebSocket (recall_update events)
- Recall filter moved to sessions-header as toggle button
- Session list shows clock icon for sessions with pending recall
- Empty state messages for empty/filtered session lists
- Fixed missing api import in ChatHeader.vue

Tests:
- Updated scheduler_loop tests for _busy_sessions dict change

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

Persist uploaded files in messages, live file tree updates, and UI polish ...

Backend:
- Add `files` field to `Message` model so uploaded file metadata survives page refresh
- Pass `files` through websocket handler → `agent.run_stream` / `agent.run`
- `list_tools`: make `profile_id` required; return error instead of all-tools fallback

Webclient:
- Call `fetchFiles()` after successful file upload for immediate Files tab update
- Live refresh file tree on filesystem (write/edit/append/mkdir/rm/cp/mv), terminal, and code_exec tool calls
- Add manual refresh button (desktop) and pull-to-refresh (mobile) to Files tab
- Fix live link updates: move regex creation inside per-message loop to avoid lastIndex state leak
- Restore full profile name text next to avatar in ChatHeader; hide avatar in header
- Fix mobile ArtifactsPanel: collapse tab text labels so close button fits with 3 tabs

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

Remove dead LLMBackend.stream() method ...

The method was defined on all backends (Ollama, FallbackOllama, OpenAI)
and in the base LLMBackend interface, but was never called by agent.py
or messages.py. stream_complete() covers all streaming use cases.

- navi/llm/base.py: remove abstract stream() method
- navi/llm/ollama.py: remove OllamaBackend.stream()
- navi/llm/fallback.py: remove FallbackOllamaBackend.stream()
- navi/llm/openai_backend.py: remove OpenAIBackend.stream()
- docs/tech_debt_review: mark item 54 as fixed

236 tests passing.

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

Stability fixes batch — tech debt review 2026-04-29 ...

Critical:
- Concurrent WS run race guard (#1)
- Tool task cancellation on generator teardown (#2)
- StopAsyncIteration kills fallback chain (#3)
- Session loading race with _lastLoadId guard (#4)
- ContentCard .match() crash on non-string result (#5)
- Image data type guard in buildMessageList (#6)

High:
- Cap WS replay buffer at 500 events (#7)
- Deduplicate memory extraction task with asyncio.Lock (#9)
- TTL-based fallback blacklisting (5 min) (#10)
- Subagent tool exception isolation (#11)
- Inline image size/count validation on WS (#12)
- Clean up orphaned file on DB insert failure (#13)
- Deep watch streamingMsg for auto-scroll (#14)
- WS_SCHEME wss:// support for HTTPS (#15)
- Sending guard against duplicate message sends (#16)
- Global unhandledrejection listener in API layer (#17)

Medium:
- Cap planning_logs at 20 entries (#22)
- Store cleanup_loop task reference (#23)
- BaseException → Exception in _run_with_sentinel (#24)
- Propagate SystemExit in agent loop (#25)
- Configurable output_reserve_tokens (#26)
- Always reloadSession on session_sync (#30)
- FIFO queue for confirm dialogs (#31)
- Reset body.overflow on ImageLightbox unmount (#32)
- try/finally in fallback copy (#33)
- _isConnecting guard in WS send() (#34)

Low:
- Lazy-init deps.py singletons (#36)
- Replace __import__ with direct imports (#38)
- Preserve token count 0 in ollama.py (#39)
- Clear orphaned streamingMsg on reconnect reload (#43)
- Escape single quote in UserMessage (#44)
- Polyfill-free findLast replacement (#48)
- Match <table> tags with attributes in markdown (#49)
- Attach copy buttons only when msg.done (#50)
- Fix hasMeta falsy-0 bug (#53)

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

Wire pgvector semantic search into memory system ...

- Add vector(768) column + HNSW index to memory_facts

- Add LLMBackend.embed() with Ollama + fallback implementation

- MemoryStore: cosine-distance search with ILIKE fallback

- New memory tool params: source, confidence, expires_days, source_context

- Update extractor, sqlite_store, deps wiring

- Add pgvector to requirements

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

Autonomous reasoning improvements: budget, anchoring, anti-stall, validation ...

- AgentProfile: per-profile thinking mechanics flags (think_enabled,
  iteration_budget_enabled, goal_anchoring, anti_stall, step_validation,
  planning_reflect, adaptive_replan) — all profiles updated in config.json
- Iteration budget: inject remaining iterations into context so model knows
  when to wrap up; urgency levels at ≤7 and ≤3 remaining
- Goal anchoring: inject original goal + todo state every N iterations to
  prevent drift on long tasks
- Anti-stall: two signals — no todo progress for N iterations, or identical
  tool calls repeated N times; warning injected into context
- Todo step validation: marking done requires a validation field describing
  how result was verified; failed gets a soft nudge with tip for re-planning
- stream_complete: add think param to base class, ollama and openai backends
- Summarizer: raise max_tokens 1024→3000, expand system prompt with
  user-preferences section and verbatim-value instructions
- Compression card: persist to session.messages (is_compression flag on
  Message), show expandable summary in webclient with markdown body
- ToolResult.to_message_content: always include output on failure so
  tracebacks and error details reach the model (fixes silent Error: None)
- Developer profile: fix subagent profile secretary→developer, add write_tool
  to subagent_tools, clarify write_tool vs filesystem in system prompt

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

Count AIHelper tokens in session metrics ...

Adds prompt/completion token fields to LLMResponse, populated by
OllamaBackend.complete(). AIHelper emits AIHelperTokensUsed into the
current event sink after each LLM call; run_stream drains it into
_subagent_tokens so AIHelper usage is reflected in the turn token delta.

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

Add response metrics: elapsed time, tool calls, token count ...

Server:
- Message model: elapsed_seconds, tool_call_count, token_count fields
  (display-only, excluded from LLM context via exclude_none)
- StreamEnd event: carries same three fields
- agent.run_stream: tracks turn start time, counts ToolEvent completions,
  writes metrics onto the final assistant Message before saving to DB
- WebSocket: forwards metrics in stream_end payload

Client:
- chat.onStreamEnd: attaches elapsed_seconds, tool_call_count, token_count
  to the streaming message on completion
- buildMessageList: scans each assistant group for metrics from history
- AssistantMessage: renders .msg-meta-row below the response —
  timer icon + Xs · wrench icon + N tools · coins icon + Nk tokens · time
  (each item only shown if present; time pushed right via margin-left: auto)

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

Persist thinking and plan cards across session reloads ...

- Message: add thinking and is_plan fields (display-only, not sent to LLM)
- Agent main loop: accumulate thinking per iteration, save with assistant message
- _run_planning: also append plan to session.messages with is_plan=True so UI
  can render plan cards after page reload (context already had the plan)

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

Add explicit output token budget for summarizer (context_summary_max_tokens) ...

Previously there was no num_predict set for the summarization LLM call,
so Ollama used its server default (often 128 tokens — very short summaries).

- Add max_tokens param to LLMBackend.complete() and OllamaBackend (→ num_predict)
- Add context_summary_max_tokens: int = 1024 to config
- Thread it through compress_context() and CompressionWorker

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

Add stop button and fix context compression hang ...

Stop generation:
- Client: send button toggles to red ■ during streaming; sends {type:stop} via WS
- Server: _stream_recv concurrently reads incoming messages during streaming using
  asyncio.wait — stop signal is handled immediately without polling
- Cooperative stop via asyncio.Event (current_stop_event ContextVar): agent breaks
  out of LLM async-for cleanly so aclose() fires → Ollama stream closes gracefully,
  model stays in VRAM. No task.cancel() which would eject the model.
- StreamStopped event propagates through run_stream/run_ephemeral; sub-agents stop
  via the same shared stop_event inherited through task context

Context compression fix:
- compress_context passes think=False to llm.complete() — no extended reasoning
  during summarization which caused GPU hang
- Input truncated to 12k chars before sending to summarizer
- LLMBackend.complete() / OllamaBackend.complete() accept think: bool | None override

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

Major feature batch: visibility, planning, file uploads, streaming ...

- stream_complete(): streaming with tools for all LLM turns — thinking
  now streams as ThinkingDelta/ThinkingEnd in real-time during tool-
  selection turns, not just on the final response
- todo built-in tool: session-scoped plan manager (set/view/update/clear);
  persona + all profiles updated with mandatory planning instructions
- TurnThinking event: sub-agent thinking forwarded to parent sink as a
  collapsible block in the spawn_agent card
- File uploads: non-image files uploaded via XHR, shown as badges in
  message bubble; SVG treated as regular file (not base64 image)
- session_files: POST /sessions/{id}/files, TTL cleanup, forbidden exts
- WebSocket reconnect: _AgentRun broadcast pattern, re-attach mid-stream
- UI: favicon, sidebar logo, turn-thinking cards, subagent thinking blocks,
  token counter, draft persistence, file progress bar
- Removed AgentNote (content is always None alongside tool_calls)
- Ollama stream_complete: tool_calls captured from non-final chunk (done=False)

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

Add context compression: rolling summarization when context fills up ...

Mechanism:
- After streaming ends, if context_tokens >= threshold (80% of num_ctx),
  compress old turns into a summary message using the same LLM
- Partition: keep system msg + last N turns verbatim (default 6);
  everything older goes to the summarizer
- Tool call groups (assistant + tool results) never split across boundary
- Existing summary messages folded into new compression pass — no stack growth
- Summary stored as Message(role=user, is_summary=True) after system msg
- On failure: logged, session left unchanged (non-fatal)

New files:
- navi/core/compressor.py: should_compress, partition_messages,
  compress_session (pure logic, testable without agent)

New config (navi/config.py):
- context_compression_enabled: bool = True
- context_compression_threshold: float = 0.80
- context_keep_recent: int = 6
- context_summary_temperature: float = 0.3

New agent event: ContextCompressed(messages_before, messages_after)
Message.is_summary: bool field marks compressed history blocks

Client:
- context_compressed WS event → subtle inline notice in message list
- loadHistory: is_summary messages rendered as collapsible summary cards
- style.css: .summary-card, .compression-notice

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

Add context token counter: 64k default, live UI display ...

- config: ollama_num_ctx default 8192 → 65536
- LLMChunk: add prompt_tokens / completion_tokens fields
- OllamaBackend.stream: populate token counts from final chunk
  (prompt_eval_count + eval_count when chunk.done)
- StreamEnd: add context_tokens and max_context_tokens
- Agent.run_stream: capture token counts, pass to StreamEnd
- websocket: include context_tokens / max_context_tokens in stream_end
- index.html: split chat-header into title span + token-counter span
- sidebar.js: updateChatHeader targets #chat-header-title, not innerHTML
- app.js: updateTokenCounter() shows "X/Y (Z%) tokens", colors:
  gray <50%, amber 50–79%, red ≥80%
- style.css: .token-counter, .warn, .danger styles

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

Server review fixes: profile model routing, sorting, datetime, cleanup ...

- LLMBackend.complete/stream: add model param; OllamaBackend uses it
  over self.model, enabling per-profile model selection
- BackendRegistry.get(): remove unused model param
- Agent: pass profile.model to complete() and stream()
- Profiles: correct model to gemma4:e2b-it-q8_0 (was leftover e4b)
- InMemorySessionStore.list_all(): fix sort (pinned+newest first,
  was pinned+oldest) — now consistent with SQLite ORDER BY
- session.py, sqlite_session_store.py: datetime.utcnow() →
  datetime.now(timezone.utc) (deprecated since Python 3.12)
- _base_options(): accept temperature param, remove dead default
- deps.py: rename _registries → get_registries (public API)
- websocket.py: update import accordingly

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

Add thinking/reasoning streaming support ...

Enable Ollama think param and stream reasoning chunks to client.
New agent events: ThinkingDelta, ThinkingEnd. Config gains ollama_think
and ollama_num_ctx settings. WebSocket protocol updated accordingly.

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

Add multimodal image support and client UX improvements ...

Server:
- Add ImageViewTool (load image from file/URL, returns base64)
- Add images field to Message model with created_at timestamp
- Agent run/run_stream accept images param; inject image messages after image_view tool calls
- WebSocket handler accepts images array from client, strips data URI prefix
- All profiles include image_view tool
- Fix tool call serialization (model_dump mode=json for datetime)
- Add no-store cache headers for static files

Client:
- Image attachment: file picker button + clipboard paste + preview strip with remove
- Images rendered in chat bubbles; loaded from history
- Tool cards rebuilt as div+CSS toggle (fixes details/overflow-hidden collapse bug)
- Tool cards appear before response bubble (lazy bubble creation on first stream_delta)
- Typing indicator persists through tool calls, removed only when text starts streaming
- Tool cards restored from history on page reload
- Message timestamps stored via created_at field, shown correctly in history
- Session ID reflected in URL hash for bookmarking; restored on page load
- Remove localStorage session tracking (server last_active used instead)

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

Initial implementation of the agent system core ...

- FastAPI server with REST API and WebSocket streaming
- Modular LLM backend abstraction (Ollama implemented, OpenAI stub)
- Tool system: web_search (ddgs), filesystem, http_request, code_exec, terminal
- Agent profiles: smart_home, server_admin, secretary
- Tool-calling loop with concurrent tool execution
- In-memory session store with SessionStore ABC for future persistence
- Registry pattern for tools, profiles, and backends
- Orchestrator stub as foundation for multi-agent scenarios