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>

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>

Review fixes: restore _build_sessions, fix flags, search filter, tests ...

- Restored _load_messages_map and _build_sessions helpers that were
  accidentally dropped in Phase 5 (list_all/list_page/search_list
  called them but they were missing, causing NameError at runtime)
- _build_sessions now filters messages by is_display so list methods
  return consistent display-only history like get()
- count_all/search_list EXISTS subquery now filters to is_display=true
  so search only matches visible chat messages
- Updated pg_session_store docstring to remove stale dual-write claim
- compressor summary_msg now defaults to is_display=False
- Added unit tests for message flags (agent, compressor, planning)

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>

Add subagent progress report on failure ...

When a subagent stops (timeout, max iterations, thinking stall, user stop),
it now returns a structured progress report built from its local message
context, so the parent agent knows what tools were called and what was
accomplished before the stop.

- Add _build_progress_report() to SubAgentRunner
- Report includes: turn number, assistant text, tool calls with results
- Prepended to result_text for every stop reason (completed also gets it)
- Updated test_run_ephemeral_complete to expect the report prefix

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

Fix MCP tool spinner bug: match tool_started → tool_call by tool_call_id ...

- Add tool_call_id field to ToolStarted and ToolEvent dataclasses
- Pass tc.id as tool_call_id from agent.py, subagent_runner.py, and tool_executor.py
- Update frontend chat.js onToolStarted/onToolCall to match cards by toolCallId
  with fallback to name-matching for backward compatibility

Closes spinner issue where LLM short name ("search_docs") didn't match
resolved MCP name ("mcp__gnexus_book__search_docs").

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

Add auth resilience: user cache, retry, and API token fallback ...

- 30-second in-memory _user_cache to avoid hammering gnexus-auth
- _fetch_user_with_retry: one retry after 1.5s sleep on transient failure
- API token fallback when OAuth cookie is present but refresh fails
- Clear cache/locks in test fixture to prevent cross-test pollution
- Fix registry timeout test after lowering default to 90s

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

Fix token counting: show only completion tokens, not cumulative prompt+completion ...

The token_count displayed next to assistant messages was summing
prompt_tokens + completion_tokens across ALL tool-calling iterations,
giving hundreds of thousands of tokens for multi-turn conversations.

Now:
- token_count (coins icon) = only completion tokens generated by the model
- context_tokens (ContextBar) = only prompt tokens (context size sent to LLM)

This gives users a realistic measure of how much the model actually generated.

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>

Make Settings immutable (frozen=True) and fix all test mutations ...

- Add frozen=True to SettingsConfigDict in navi/config.py
- Convert model_validator to mode="before" since mode="after" cannot mutate frozen instances
- Replace all field-level monkeypatches in tests with whole-Settings object replacement
- Ensure cross-module settings consistency (content_store, session_files, share_file, content_publish, filesystem)

392 passed, 1 skipped

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

Step 4: Extract SubAgentRunner from run_ephemeral() ...

- Create navi/core/subagent_runner.py with full sub-agent loop logic
- Move _iter_stream_guarded to navi/core/stream_guard.py
- Move _check_context_size to ContextCompressor.check_context_size()
- Extract build_tool_list() and load_user_enabled_tools() to tool_utils.py
- Agent.run_ephemeral() becomes a thin wrapper delegating to SubAgentRunner
- Remove ~310 lines from agent.py
- All existing run_ephemeral tests pass unchanged

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

Step 3: Extract AntiStallMonitor from run_stream() ...

- Create navi/core/anti_stall.py with AntiStallMonitor class
- Encapsulates stall detection (todo progress + repeated tool calls)
- Encapsulates adaptive re-plan (failed todo step detection)
- Provides init() / pre_turn() / post_turn() two-phase interface
- Remove ~50 lines of stall/replan logic from agent.py run_stream()
- Remove _todo_status_snapshot and _todo_failed_steps helpers from agent.py
- Update AgentTurnContext: remove stall fields (now live in AntiStallMonitor)
- Add 13 unit tests for pre_turn and post_turn behavior

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

Extract ContextCompressor, fix STL viewer, expand test suite, add architecture audit docs ...

- Extract ContextCompressor from agent.py (Step 1 of god-object refactor)
- Add retry + hard-truncate fallback logic to ContextCompressor
- Add unit tests: agent loop (14), compressor (18), KV store (8),
  auth encrypt (3), auth deps (13), todo/scratchpad/image_view/memory
- Fix WebGL STL viewer: allow-same-origin sandbox + graceful fallback
- Add CompressionStarted event and client-side compression notice
- Add docs/architecture_weak_spots.md and plan_01_god_object_agent.md
- Update test_events.py and test_agent_context_size.py for new logic

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

Enhance native toolset and add persistent KV store ...

- Add PostgreSQL-backed KvStore (navi/store/) for session-scoped data.
- Migrate todo and scratchpad from in-memory dicts to KvStore.
- Filesystem: add copy, grep, diff actions; compress description.
- CodeExec: remove language param, expose working_dir in schema.
- ImageView: resize to 1024px JPEG + Content-Type guard for URLs.
- Memory list: return distinct categories instead of all facts.
- SSH: add scp action with upload/download support.
- Update CLAUDE.md (Postgres-only), docs/tools.md, add docs/store.md.
- Fix agent/planning/context_builder async signatures for todo helpers.

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

Add self-recall (scheduled callback) system ...

Core features:
- schedule_recall tool: once/recurring/immediate callbacks
- manage_recall tool: cancel/skip/list scheduled recalls
- Natural-language time parser (ISO, relative, "tomorrow at 09:00")
- PostgreSQL-backed RecallScheduler with lazy pool init
- Background recall_scheduler_loop with asyncio.Semaphore(3)
- _busy_sessions guard prevents user messages during headless runs
- Agent.run() preserves thinking field for session history visibility
- API endpoints: GET/DELETE/POST for session recall, admin list
- Frontend: recall badge, filter, cancel/skip in sidebar and chat header
- Tests: parser, scheduler CRUD, tools, API, scheduler loop (53 tests)
- Manuals: schedule_recall.md and manage_recall.md

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

Fix gnexus-book MCP instructions and add old-format fallback in tool executor ...

- Updated mcp_servers.json gnexus-book instructions to use mcp:gnexus-book:
  prefix instead of the old mcp_gnexus-book_ format.
- Added fallback in tool_executor.py for old underscore format
  (mcp_server_tool → mcp:server:tool) so transitional models still work.
- Added unit test for the old-format fallback.

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>

Handle MCP tool aliases robustly

Clarify knowledge persistence prompts