Автономность мелких моделей: OUTPUT DISCIPLINE, milestone-todo, перехват финала хода ...

Два последовательных захода над одной проблемой — мелкие модели (12–30B) в navi_code
теряют автономность на трудных шагах: «остановился поболтать» вместо действия и
слишком большое расстояние между пунктами плана.

Заход 1 (З1–З3):
- З1: OUTPUT DISCIPLINE в системном промпте navi_code — «act, don't announce»,
  без few-shot антипримеров. Контракт хода: ответ без tool_calls = конец хода, поэтому
  объявление намерения текстом убивает автономность; правила заставляют вызывать
  инструмент в том же ходе.
- З2: плоский todo + метка группы milestone + декомпозиция. _parse_plan_steps
  возвращает list[tuple[milestone, text]]; milestone — метка группировки (не сущность,
  без статуса), «done» вычисляется при рендеринге; подшаги = больше плоских шагов
  (без вложенности). TUI side-panel группирует по milestone (плоский фолбэк при пустом
  milestone). Plan depth: max 15→20 + правило декомпозиции.
- З3: adaptive re-plan «длинный шаг» — nudge «разбей шаг» при in_progress ≥ порога
  итераций без смены todo (порог 4, раньше общего anti-stall warning на 8).

Заход 2 (шаги 1–3, после cloud-теста 31b vs 12b):
Корневая структурная причина: весь спасательный механизм (anti-stall warning с явным
предложением reflect, adaptive re-plan) живёт только внутри tool-цикла — nudge
инжектируется в pre_turn *следующей* итерации, которой при «остановился поболтать»
нет (ход закрылся по return до post_turn). 31b застревала через «продолжаю
tool-итерации» → дожала до warning → спаслась; 12b — через «замолчала текстом» → мимо
всех nudge.

- Шаг 1: перехват финала хода. Если модель выдала bare-text, но в todo есть открытые
  шаги (pending/in_progress) и лимит не исчерпан — НЕ эмитить StreamEnd, а сохранить
  ассистентский текст в session.context, поставить системный nudge и continue
  (без StreamEnd, без workers — консистентно с multi-iteration tool-турами). Счётчик
  final_interceptions на AgentTurnContext, лимит final_intercept_limit (default 2),
  эскалация жёсткости (мягкий → «second stop»). has_open_steps в todo.py: пустой
  todo → False (защита casual-сообщений), failed/skipped терминальны. Профильные
  флаги final_intercept_enabled/limit в base.py + loader + admin.
- Шаг 2: жёсткий reflect-триггер в промпте — «~3 tool attempts on the same step
  without progress → call reflect IN THIS TURN (tool call, not reasoning aloud)».
- Шаг 3: открыть replan для застревания — «call replan when reflect showed the whole
  approach is dead (not one failed step, but the approach itself)».

Тесты: 874 passed, 1 skipped. Новые — has_open_steps (5), final intercept (5),
milestone-группировка, adaptive long-step nudge, парсер шагов с milestone-маркером.

cloud: navi_code model → gemma4:31b-cloud для тестирования догадки (31b признала
застревание, 12b — нет); .env cloud-host уже gitignored.

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

config: raise context compression threshold 0.70 -> 0.90 ...

Midturn compression now splits the in-flight turn correctly, so it's safe to
let the context grow closer to the limit before compressing. 0.90 gives the
model more raw context per turn and trips the compressor less often.

Worker test context_tokens bumped 50_000 -> 60_000 (76% -> 91.5%) to stay
above the new threshold; other compression tests pass the threshold as an
explicit argument and are unaffected.

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

filesystem: show real file line numbers in unified diffs ...

_number_diff parses @@ hunk headers and prefixes each content line with its
real file line number: removed/context lines use the old (from) number,
added lines use the new (to) number, in `{marker} {num}│ {content}` form
(marker first so existing startswith highlighting stays valid; column
right-aligned to the largest line number). Hunk/file headers and the
`\ No newline` marker are left unchanged.

Applied in _unified_diff (covers edit / edit_lines / smart_edit) and the
`diff` action — a single server-side change, so both the TUI and the web
client receive numbered diffs in the tool result text.

TUI highlight_unified_diff renders the `{marker} {num}│` column dim and the
content in the marker color, so the number reads as meta, not as part of the
added/removed text. Lines without the prefix (standalone `diff` event, older
callers) are still colored whole.

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

compressor: split in-flight turn in midturn mode + flush incrementally ...

Two related fixes for long autonomous turns in planning profiles (navi_code):

A1 — partition_messages turn-based branch held the in-flight (current) turn
verbatim when turns > keep_recent, so midturn compression was shallow
(e.g. 150 -> 141 messages). Now, when keep_recent_messages is set, the
in-flight turn is split like partition_current_turn_messages: head (user
request) + tail (recent tool steps) kept, middle summarized. The adaptive
swap is disabled in midturn mode (it could move the in-flight turn into
old_turns and summarize the current request whole). First branch
(len(turns) <= keep_recent) is untouched, so locked-in midturn tests hold.

B1 — agent.run_stream had no try/finally around the for-loop, so an
asyncio.CancelledError (server restart/shutdown) unwound the stack with no
flush: all in-memory turn messages (sequence_number < 0) were lost, only the
user message survived. Add incremental save() after planning, after the
assistant tool-call decision, and after each tool result, so a crash loses at
most the single in-flight tool call, not the whole turn. B2 (try/except
safety-net) was dropped: B1 leaves no window where an append is unsaved.

Tests: midturn split with many turns (partition + compress_session), and
crash/cancel persistence via a snapshot session store that mirrors the DB
boundary.

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

replan: integrated mid-task re-planning tool ...

Add a replan tool that re-runs the planner over the live session context
+ todo + scratchpad when the plan's structure is stale due to discoveries
(NOT failed steps -- that stays [Adaptive re-plan]). Integrated approach:
PlanningEngine.run gains is_replan/replan_context (suppresses DIRECT
shortcut and observe-skip, frames Phase 1 as a revision); ReplanRunner
packs reason/goal/todo/findings/errors and captures PlanReady; the tool
is exposed to navi_code/developer/tool_developer via a
current_replan_runner ContextVar set per-iteration in run_stream (correct
after switch_profile). New plan replaces the todo. Lazy events import
breaks the navi.tools -> navi.core -> navi.tools cycle.

recall: carry self-instruction (message) on the recall_update wire ...

The recall card could show call_type/trigger_at but not the self-instruction
(additional_context_message) — it was absent from RecallUpdate.to_wire, so
the user couldn't see what future-self was about to do at the scheduled or
fired moment. Extend the wire payload.

- events.RecallUpdate: add `message` field; to_wire emits "message".
- scheduler._publish_recall_update: accept and forward `message`.
- Publish sites carry message=recall.additional_context_message:
  schedule_recall (scheduled) and orchestrator._finalize_recall
  (rescheduled / fired / cancelled). manage_recall cancel/skip omit it
  (no recall object handy; already visible in the prior scheduled card).
- TUI RecallRenderer: preview the message (first line + "(+N lines)",
  capped at 80) on a `msg:` body line when present.
- Tests: RecallUpdate.to_wire carries message (defaults None); renderer
  preview (single/multiline/truncate/empty) and scheduled-card renders it.

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

filesystem edit: render red/green diff in TUI without changing model context ...

edit is now the primary editing method, yet its output was a dry one-line
status ("Edited …: replaced X B with Y B") while edit_lines/smart_edit showed a
highlighted unified diff. Carry the unified diff in ToolResult.metadata["diff"]
(kept out of the model-facing output, so the agent's context is unchanged) and
render it in the TUI: dim summary line plus highlighted diff (green +, red -,
dim @@). Falls back to plain text when no diff metadata is present.

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

filesystem: make edit/edit_lines the default, smart_edit a last-resort fallback ...

Agent overused smart_edit (whole-file LLM call, weak context). Rewrite the
FilesystemTool description decision tree so edit (exact text) is the default and
edit_lines (by line numbers) is the deterministic option; smart_edit is reserved
for genuinely semantic changes that cannot be expressed as exact text or line
numbers. Strengthen the old_not_unique hint to steer back to edit/edit_lines
before smart_edit. Add an "Editing policy" section to the navi_code and
developer profile prompts reinforcing the same priority.

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

compression: profile-aware worker + real-token baseline estimator ...

Item 2 — thread the active profile into CompressionWorker so
compress_context applies per-profile overrides (compression_keep_recent,
compression_max_tokens, compression_prompt_file). navi_code now compresses
with keep_recent=12 instead of the global 8.

Item 1 — estimate the next LLM call's context from the *real* prompt_tokens
of the previous call (bulk) plus a heuristic delta for messages appended
since, replacing the chars//3 estimate that undercounts code-heavy tool
output and fired midturn compression too late (Navi kept working until the
window was exhausted). Baseline is recorded after each stream and cleared
after compression; check_context_size and the midturn gate use it, with a
heuristic fallback when no baseline exists or the context shrank.

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

compression: fix auto-compress no-op on few-huge-messages + honest status ...

Root cause: the compression gate (should_compress) measures tokens, but the
partition measures message/turn count, and CompressionStarted was emitted
before the attempt. For navi_code's "few very large messages" shape (one big
file read = 1 user + assistant + 1 huge tool result, 66k tokens in 3 messages)
the gate fired, the UI showed "compression", but partition returned
to_summarize=[] -> compress_context None -> nothing shrank. The agent kept
going until the window overflowed. It wasn't running "during" compression —
there was no compression, just a no-op the user mistook for one.

A. Per-message head/tail truncation in context_builder.build(): oversized
   tool/assistant messages (over context_message_token_budget, 0=num_ctx//6)
   are capped head+marker+tail in the LLM view only (model_copy — stored
   history and reloads are never affected). A single huge tool result can no
   longer alone blow the window; user/system messages are never truncated.

B. Token-budget hard-truncate fallback in compress_session: when partition
   no-ops but tokens exceed the threshold, drop oldest turns to num_ctx*0.5.
   _hard_truncate is now token-aware (was a fixed message-count floor that
   no-oped on <=6 messages even when huge). New would_compress() predicts
   compress_session's real outcome with no LLM call.

C. Honest CompressionStarted: _compression_events_midturn/_preturn emit it
   only after would_compress() confirms the partition (or token-budget
   fallback) can actually shrink the stored context — no more "compression"
   status with no ContextCompressed to follow.

Bonus: post-turn CompressionWorker now passes keep_recent_messages=
max(12, context_keep_recent*2), matching the midturn path, so a single long
autonomous turn compresses post-turn too (was always a no-op).

Tests (+14): would_compress agreement, token-budget fallback, token-aware
hard_truncate, build() truncation (preserves user, no mutation, head+tail),
agent no-CompressionStarted-when-nothing-to-compress, worker single-long-turn.

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

Navi Code: force context compression via typed /compact control message ...

Forced /compact previously sent a chat message, which ran a full agent turn
that only produced summary text instead of running the real context compressor.
Worse, even when wired correctly, forced compact always reported "Nothing to
compact yet — the context is still small" regardless of context size: the typical
navi_code shape is a single long autonomous turn (1 user message + many tool
iterations = one turn), and partition_messages finds nothing to summarize when
turns <= keep_recent. The midturn auto-compress path already bypassed this via
keep_recent_messages (intra-turn split), but compact_stream passed
keep_recent_messages=None, so the fallback was disabled.

Changes:
- WS protocol: {"type":"compact"} control message (distinct from {"type":
  "message"}); rejected while an agent turn is active to avoid racing the agent.
- Agent.compact_stream: forced compression that bypasses the token threshold
  but still runs the real compressor; passes keep_recent_messages=max(12,
  context_keep_recent*2) so a single long turn compresses via intra-turn split
  (mirrors midturn auto-compress). Raises NothingToCompactError when context is
  genuinely too small.
- Orchestrator.run_compact + clear_run: broadcast agent events to subscribers,
  end with done marker, surface NothingToCompactError as an error event.
- Terminal client: ws_client.send accepts str|dict; CompactCommand enqueues
  {"type":"compact"}; TUI distinguishes forced compact (no stream_start) from
  in-turn auto-compress via the _streaming flag.
- Tests: compact_stream (incl. single-long-turn regression), WS handler
  dispatch/rejection, run_compact event/error broadcasting, ws_client send,
  compact command.

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

tui: show the changed step's text in the todo update call card ...

The todo update call card (→ todo · #3 → done) now shows the text of the
step being changed, plus the validation when present. The LLM's update args
carry only the index, not the task text, so the text is read from the
current plan row before the tool runs and attached to ToolStarted.metadata
(client-rendering only, backward-compatible).

Backend:
- events.ToolStarted gains a metadata dict (mirrors ToolEvent) → to_wire.
- navi/tools/todo: step_text_for_update(index, ctx) resolves the step text
  via _sid/_uid (so sub-agent isolation holds), started_metadata_for_call
  wraps it for both emit sites.
- agent.py (parent) and subagent_runner.py (sub-agent) enrich ToolStarted
  via the shared helper before emitting.

Renderer:
- TodoStartedRenderer update card reads msg.metadata.step_text → shows the
  step text + validation; falls back to 'no validation' on history replay.
- Removed the step-text line from the result card (it now lives in the call
  card) — result card is back to the compact 'plan · X/N done' summary.

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

Isolate sub-agent todo + render live todo in TUI side panel ...

Phase 1 — sub-agent todo isolation (backend):
- Add current_todo_session_id ContextVar; subagent_runner scopes it to the
  sub-agent's ephemeral run id so its auto-populated plan and todo updates
  land in an isolated KV row instead of clobbering the parent session's todo
  (which the parent's goal-anchoring reads every iteration).
- todo._sid() and planning.set_tasks prefer current_todo_session_id; the
  parent run leaves it unset, so all existing todo consumers (anti-stall,
  goal anchor, get_progress_message) behave exactly as before.

Phase 2 — live todo in the TUI right column:
- TodoUpdated event + emit it from the agent loop after planning auto-populate
  and after each tool-execution turn.
- GET /sessions/{id}/todos reads the parent session's todo KV row (explicit
  user_id/session_id, optional injected kv).
- api.get_todos + TodoList/TodoPanel widgets: status-coloured markers
  (pending dim, in_progress accent+bold, done success, failed error, skipped
  dim), progress header, scrollable panel below the auto-height info block.
- Hybrid delivery: REST seeds the panel on attach/switch, todo_updated WS
  events update it live.

Sub-agent todos as nested sub-lists is deferred to a later phase.

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

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>

agent: cwd-aware memory fact filter for bounded autonomy ...

Long-term memory stored context-dependent path facts (e.g. "project_root
→ /home/.../navi-1") as global user facts. search_facts injected them into
any session, so when working in another project the agent was told "the
project root is navi-1" and drifted there.

When scope_boundary_enabled and a session cwd is set, _memory_facts_msg now
drops facts whose value is an absolute path outside the session cwd tree.
Facts are kept when working inside that path (then they are correct), and
non-path/relative facts always pass. Free flight stays reproducible by
toggling the flag off. No facts deleted, extractor untouched.

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

agent: bounded autonomy — scope boundary + observe-vs-act ...

navi_code had unwanted "free flight": an observe request ("look at a
directory") triggered the full Phase 3 plan with milestones + auto-todo,
and goal_anchoring then drove the agent to finish those steps, climbing
into sibling projects and executing milestone docs it found.

Two toggleable, default-off profile flags (on for navi_code):

- scope_boundary_enabled: injects a standing system message keeping the
  agent within the literally requested scope; forbids acting on
  discovered TODO/roadmap/milestone docs (report only).
- observe_skips_plan_enabled: Phase 1 classifies MODE: observe|act; an
  observe request skips Phase 2/3 — no multi-step plan, no auto-todo, no
  "execute step by step" prompt. The agent just gathers info and answers.
  Independent of force_plan (observe on the first message still skips).

Free flight stays reproducible by flipping both flags off.

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

session store: lazy persistence — no empty sessions in DB ...

POST /sessions no longer inserts a DB row. The Session is registered in an
in-memory _pending registry on PgSessionStore and only upserted on the first
save() (first user message / meaningful state change). Empty sessions that
never receive a message never reach the DB and vanish on server restart or
via the hourly pending sweep.

- pg_session_store: _pending dict + lock; create() registers, get() checks
  _pending first, save() upserts the sessions row (INSERT ... ON CONFLICT)
  and pops _pending so the session_messages FK is satisfied; sweep_pending()
  drops abandoned entries; pending_sweep_loop() background task.
- main.py: start/cancel pending_sweep_loop in lifespan.
- tests: 7 new tests for create/get/save/list/sweep semantics; updated
  existing save() test comments for the upsert.

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>

agent: skip planning for casual greetings + strengthen DIRECT shortcut in Phase 1 ...

- Add fast _is_casual_message heuristic in navi/core/agent.py. Greetings and
  social chat (e.g. 'привет', 'как дела', 'hi', 'thanks') bypass planning even
  on the first session message, unless planning_mandatory is enabled.
- Strengthen Phase 1 planning prompt in navi/core/planning.py: explicitly
  require DIRECT output for greetings, simple questions, and one-step
  instructions.
- Fix broken ContextCompressed import in navi/core/compressor.py.
- Add unit tests covering the new heuristic and DIRECT prompt.

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

Navi Code TUI: fix Phase 4 review critical/medium issues ...

- PermissionEngine: always-deny returns None via check(); is_always_deny() exposed for explicit rejection; default rules for code_exec/ssh_exec/shell; extract_target() made public.
- ShellRunner: set ShellResult.truncated when output is actually truncated.
- File refs: restrict paths to base_dir/home, block sensitive files/dirs, skip binary, support glob brackets, shared guess_language.
- Permission dialog: deny now renders synthetic tool_call before stopping; shell ! commands require permission with always-allow/deny persistence.
- Tests: add permission tests, fix file_refs/shell tests, add __init__.py to fix pytest name collisions, update websocket integration for AgentSessionOrchestrator.

504 passed, 1 skipped. Ruff clean.

Signed-off-by: Eugene Sukhodolskiy <eugene.sukhodolskiy@gmail.com>

Fix review issues for NAVI_AUTH_ENABLED feature ...

- Return 503 from /auth/login and /auth/callback when NAVI_AUTH_ENABLED=false
- Return model_copy() of _ANONYMOUS_USER to prevent accidental mutation
- Clean up __import__(datetime) in auth DDL
- Reorder FakeChatSession definition before use in tests
- Remove dead monkeypatch code in no-auth integration fixture
- Add unit test for get_current_user_ws in no-auth mode
- Add integration tests rejecting OAuth endpoints in no-auth mode

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

Add NAVI_AUTH_ENABLED switch for optional auth ...

- Add navi_auth_enabled setting (default true) to navi/config.py and .env.example
- When disabled, treat every request as anonymous admin user (id='anonymous')
- Create/update fixed anonymous navi_users row on startup
- Bypass OAuth/cookie/API-token resolution in navi/auth/deps.py
- Update /auth/status to return {enabled, configured}
- Log security warning on startup when auth is disabled
- Update webclient: skip fetchMe/login screen, show Local mode footer,
  expose /admin link, warn in API keys panel
- Rebuild webclient production bundle
- Add unit and integration tests for no-auth mode
- Update docs: auth.md, config.md, api.md, api_tokens.md, sessions.md,
  websocket.md, mechanics.md, index.md

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

Fix scratchpad tool: rename op→action, add examples, improve error messages ...

- Rename primary parameter from 'op' to 'action' for consistency with
  all other tools (terminal, filesystem, todo, etc.). Legacy 'op' still
  works as a fallback to avoid breaking old calls in compressed context.
- Add JSON examples directly in the tool description so the model sees
  the exact structure to produce.
- Improve all error messages to include the correct JSON example,
  making it obvious what the model did wrong.
- Add manuals/scratchpad.md for tool_manual support.
- Update and expand tests for new syntax and error cases.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Make shared files and published content publicly accessible ...

Remove auth requirements from:
- GET /sessions/{id}/files/{filename} — direct download links (session ID
  acts as unguessable capability token)
- GET /sessions/{id}/content — published inline content list

Both endpoints still verify session exists and protect against path
traversal. File upload and file listing remain auth-gated.

Update tests to match new signatures.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Move terminal_manager to _internal subpackage ...

- terminal_manager is an internal helper, not a tool
- Update imports in terminal.py, container.py, test_terminal.py

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

Fix terminal review issues: security, lifecycle, reactivity ...

- TerminalManager.open now accepts exec_tokens to use create_subprocess_exec
  for restricted commands instead of always using shell
- Fix kill/terminate order: SIGTERM first, SIGKILL fallback
- Pop closed sessions from _sessions dict to prevent memory leak
- Add terminal_manager.shutdown() to AppContainer.shutdown()
- Wait for reader tasks in foreground open before returning output
- Add _MAX_TERMINALS_PER_SESSION limit (10)
- Wrap cleanup_idle tasks in _close_one_safe with error logging
- send_input catches BrokenPipeError/ConnectionResetError specifically
- Foreground terminals auto-close after gathering output
- Vue reactivity: replace terminals object immutably instead of mutating
- onTerminalClosed marks matching tool card as no longer pending
- Update tests for new behavior (foreground auto-close, max limit)

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

Add persistent multi-session terminal tool with background support ...

- New TerminalManager module: named subprocess sessions per Navi session,
  background readers, event-sink streaming, idle auto-cleanup
- Refactor terminal tool to multi-action: run, open, close, list,
  status, send_input
- Add TerminalOutputDelta and TerminalClosed events for streaming
- Wire TerminalManager into AppContainer, orchestrator, and registry
- Persist session_metadata in Session model and pg_session_store
- Close all session terminals on session delete
- Webclient: handle terminal_output/terminal_closed WS events,
  display live terminal output in tool cards
- Update unit tests for new terminal actions

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

Fix 19 issues found in full codebase review ...

Backend:
- Stop session auth bypass: require auth for owned sessions, reject anonymous with 401
- upload_file: stream chunks directly to disk instead of buffering in RAM
- MCP config: validate name against path traversal regex
- auth deps: cleanup stale refresh locks periodically
- auth routes: expire mobile auth states after 10 min to prevent unbounded growth
- compressor: meta-summarize existing summaries before compression; preserve assistant content when tool_calls present; rewrite hard_truncate to keep whole turns
- orchestrator: configurable WS replay buffer size; async cleanup/remove_websocket/clear_busy; fix run_recall ContextVar order to avoid deadlock on _build_agent failure; await cleanup in finally
- agent: persist image_msg in session.messages; remove archived messages from session after archive; remove duplicate StreamStopped yield on tool stop
- websocket: try/except around create_task with cleanup on failure; await remove_websocket

Frontend:
- App.vue: hashchange listener lifecycle in onMounted/onUnmounted
- MessageList.vue: passive scroll, flash timeout cleanup, archive scroll snapshot
- InputBar.vue: 300 ms debounce on draft save to localStorage
- SessionList.vue: remove :key from DynamicScroller to avoid remount jitter

Tests: 422 passed, 1 skipped

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

Add meta-summary for multi-level compression ...

When to_summarize contains multiple existing summary messages whose
combined length exceeds 8000 chars (~1/3 of max summarizer input),
run a quick meta-summary pass first to consolidate them into a single
compact summary before the main compression. This prevents information
loss when repeated compressions stack up long summary chains.

- _meta_summarize(): fast LLM pass (think=False, max_tokens=1500)
- compress_context(): detects >1 long summaries and triggers meta pass
- Graceful fallback: if meta-summary fails, continue with raw summaries
- 3 new unit tests: consolidation, skipped for short summaries, failure fallback

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

Wire archive trigger into agent after compression ...

After _do_compress_and_save finishes, if the total persisted message count
(db_next_sequence) exceeds session_messages_window (default 1000), the agent
now calls archive_old_messages() to move older rows into
session_messages_archive.

Adds session_messages_window config and unit tests for archive SQL.

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