Commit Graph

5 Commits

Author SHA1 Message Date
vikingowl 27ca12f863 feat: tokenizer-aware Tracker.CountTokens/CountMessages replaces EstimateMessages in compaction 2026-04-05 22:21:12 +02:00
vikingowl cb2d63d06f feat: Ollama/gemma4 compat — /init flow, stream filter, safety fixes
provider/openai:
- Fix doubled tool call args (argsComplete flag): Ollama sends complete
  args in the first streaming chunk then repeats them as delta, causing
  doubled JSON and 400 errors in elfs
- Handle fs: prefix (gemma4 uses fs:grep instead of fs.grep)
- Add Reasoning field support for Ollama thinking output

cmd/gnoma:
- Early TTY detection so logger is created with correct destination
  before any component gets a reference to it (fixes slog WARN bleed
  into TUI textarea)

permission:
- Exempt spawn_elfs and agent tools from safety scanner: elf prompt
  text may legitimately mention .env/.ssh/credentials patterns and
  should not be blocked

tui/app:
- /init retry chain: no-tool-calls → spawn_elfs nudge → write nudge
  (ask for plain text output) → TUI fallback write from streamBuf
- looksLikeAgentsMD + extractMarkdownDoc: validate and clean fallback
  content before writing (reject refusals, strip narrative preambles)
- Collapse thinking output to 3 lines; ctrl+o to expand (live stream
  and committed messages)
- Stream-level filter for model pseudo-tool-call blocks: suppresses
  <<tool_code>>...</tool_code>> and <<function_call>>...<tool_call|>
  from entering streamBuf across chunk boundaries
- sanitizeAssistantText regex covers both block formats
- Reset streamFilterClose at every turn start
2026-04-05 19:24:51 +02:00
vikingowl 14b88cadcc feat: M1-M7 gap audit phase 3 — context prefix, deferred tools, compact hooks
Gap 11 (M6): Fixed context prefix
- Window.PrefixMessages stores immutable docs (CLAUDE.md, .gnoma/GNOMA.md)
- Prefix stripped before compaction, prepended after — survives all compaction
- AllMessages() returns prefix + history for provider requests
- main.go loads CLAUDE.md and .gnoma/GNOMA.md at startup as prefix

Gap 12 (M6): Deferred tool loading
- DeferrableTool optional interface: ShouldDefer() bool
- buildRequest() skips deferred tools until activated
- Tools auto-activate on first model request (activatedTools map)
- agent + spawn_elfs marked as deferrable (large schemas, rarely needed early)
- Saves ~800 tokens per deferred tool per request

Gap 13 (M6): Pre/post compact hooks
- OnPreCompact/OnPostCompact callbacks in WindowConfig
- Called in doCompact() (shared by CompactIfNeeded + ForceCompact)
- M8 hooks system will extend these to full protocol
2026-04-04 20:46:50 +02:00
vikingowl 31cba286ac fix: M1-M7 gap audit phase 1 — bug fix + 5 quick wins
Bug fix:
- window.go: token ratio after compaction used len(w.messages) after
  reassignment, always producing ratio ~1.0. Fixed by saving original
  length before assignment.

Gap 1 (M3): Scanner patterns 13 → 47
- Added 34 new patterns: Azure, DigitalOcean, HuggingFace, Grafana,
  GitHub extended (app/oauth/refresh), Shopify, Twilio, SendGrid,
  NPM, PyPI, Databricks, Pulumi, Postman, Sentry, Anthropic admin,
  OpenAI extended, Vault, Supabase, Telegram, Discord, JWT, Heroku,
  Mailgun, Figma

Gap 2 (M3): Config security section
- SecuritySection with EntropyThreshold + custom PatternConfig
- Wire custom patterns from TOML into scanner at startup

Gap 3 (M4): Polling discovery loop
- StartDiscoveryLoop with 30s ticker, reconciles arms vs discovered
- Router.RemoveArm for disappeared local models

Gap 4 (M5): Incognito LocalOnly enforcement
- Router.SetLocalOnly filters non-local arms in Select()
- TUI incognito toggle (Ctrl+X, /incognito) sets local-only routing

Gap 5 (M6): Reactive 413 compaction
- Window.ForceCompact() bypasses ShouldCompact threshold
- Engine handles 413 with emergency compact + retry
2026-04-03 23:11:08 +02:00
vikingowl b0b393517e feat: M6 context intelligence — token tracker + truncation compaction
internal/context/:
- Tracker: monitors token usage with OK/Warning/Critical states
  (thresholds from CC: 20K warning buffer, 13K autocompact buffer)
- TruncateStrategy: drops oldest messages, preserves system prompt +
  recent N turns, adds compaction boundary marker
- Window: manages message history with auto-compaction trigger,
  circuit breaker after 3 consecutive failures

Engine integration:
- Context window tracks usage per turn
- Auto-compacts when critical threshold reached
- History syncs with context window after compaction

TUI status bar:
- Token count with percentage (tokens: 1234 (5%))
- Color-coded: green=ok, yellow=warning, red=critical

Session Status extended: TokensMax, TokenPercent, TokenState.
7 context tests.
2026-04-03 18:46:03 +02:00