navi: a token count that matches the model, a type for every file, and a socket that admits it is dead ...

Compression decided everything in chars // 3, and on this workload that sits
~1.8x below reality — 101k real prompt tokens against a ~56k estimate — so the
trigger, the target, the truncate budgets and the pre-call size check all ran
in a unit half the size of the real one. TokenCalibration now fits
overhead + chars / chars_per_token per model from the prompt_eval_count that
every call already reports, and a profile declares its own context_window
(sent to Ollama as num_ctx) instead of every model being held to OLLAMA_NUM_CTX.

Superseded summaries were never demoted in the database: save() only updates
flags for rows in session.messages, a summary is is_display=False, so it lived
in session.context alone and every reload resurrected it — prod sessions
carried up to 15 live summaries. PgSessionStore.set_context_flag() writes the
flip for those rows directly.

Five extension tables disagreed about what a file is. navi/content_types.py is
the one detector — signature, then extension, then a text probe — it decides
the MIME the download route serves, and the session file list now carries the
type the viewers branch on.

The idle receive loop answers client pings and sends its own heartbeat. A
half-open socket keeps readyState at OPEN and never fires close, so traffic
coming back is the only proof the connection still works.

compress: route every trigger path through compress_and_save_session ...

- CompressionWorker keeps the real-token gate (ctx.context_tokens) but now
  delegates to compress_and_save_session(reason="postturn") — it used to
  call compress_context directly with its own save logic and silently
  no-op'ed on any summarizer failure, leaving the session over the
  threshold until the next turn's gates
- pre-turn and /compact gates use real_baseline_estimate instead of the
  chars//3 heuristic (mid-turn already did), so code-heavy contexts
  compress in time instead of tripping ContextTooLargeError
- summarizer input keeps head + tail instead of head-only truncation,
  which silently dropped the newest summarized messages closest to the
  keep window
- critical tool results over the 4000-char budget keep head+tail halves
  instead of collapsing to the 800-char non-critical preview (a 3999-char
  read survived whole, a 4001-char one lost 98%)
- images count 500 tokens each, not 500 per message carrying them
- _plan_compression is the single partition decision shared by
  compress_context and would_compress, so the dry-run prediction cannot
  drift from the real path; the trigger reason is now logged
  (preturn/midturn/postturn/forced)

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>

Fix CompressionWorker: sync context compression with session messages ...

- Mark removed messages as is_context=False so DB reload doesn't resurrect them
- Persist summary_msg in messages (is_display=False) so summary survives reload
- Add is_compression marker with is_context=False
- Set context_token_count to real estimate instead of zero

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

Refine 3D modeler workflow

Architecture extensibility — event bus, middleware, auto-discovery, Pydantic profiles ...

- EventBus: async pub/sub for AgentEvents, WebSocket subscribes instead of direct yield
- Declarative serialization: AgentEvent.to_wire() on all event types
- Auto-discovery for LLM backends (_discover_backends) and workers (scan navi/workers/*.py)
- AgentProfile: Pydantic BaseModel with extra='allow', @field_validator for model coercion
- Tool middleware chain: pre/post execute hooks via ToolRegistry.add_middleware()
- LoggingMiddleware: built-in, logs every tool call
- Fix pg_trgm DDL: conditional GIN indexes via DO $$ block, no CREATE EXTENSION
- New files: event_bus.py, middleware.py, logging_middleware.py

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>

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>

Expose compression summary as collapsible debug card in chat UI ...

ContextCompressed event now carries the full summary text produced by the
LLM. Compression notice in chat becomes a <details> element showing
message count (before→after) with the summary expandable on click.
Rendered as markdown via marked.js.

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>

Review fixes: events module, circular imports, deps, vision-aware compression ...

- Extract all AgentEvent dataclasses to navi/core/events.py; import from
  there in agent.py and __init__.py — eliminates circular import between
  workers and core
- workers/compressor.py: remove runtime import hack, use navi.core.events
- workers/base.py: WorkerResult.events typed as list[AgentEvent] (was Any)
- api/deps.py: replace @lru_cache on mutable list with module-level
  singletons (_registries, _workers)
- core/compressor.py: _format_for_summary returns (text, images); images
  passed to summarization LLM so vision models describe them in summary;
  non-vision models silently ignore the images field; docstring updated
- client/js/app.js: add comment explaining is_summary backward compat branch

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

Separate display history from LLM context; formalize worker system ...

Architecture change:
- session.messages: full display history, never modified by compression
- session.context: what the LLM sees, may be compressed by workers
- System messages go only into context (not display history)
- Image injections (synthetic) go only into context
- User/assistant/tool messages go into both

SQLite: add context column with backward-compat migration
(empty context → initialized from messages on load)

Workers (navi/workers/):
- Worker ABC + WorkerContext + WorkerResult (base.py)
- CompressionWorker: compresses session.context when above threshold
- build_default_workers() returns [CompressionWorker()]
- Agent accepts workers list, runs them after StreamEnd
- Workers injected via deps.py get_workers() (lru_cached singleton)
- WebSocket agent construction also receives workers

Compressor: compress_context() now takes context[], not messages[]
Config: context_keep_recent 6 → 10
Agent: _run_workers() collects events from all workers and yields them

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