|
|
509c897847
|
feat: M1-M7 gap audit phase 2 — security, TUI, context, router feedback
Gap 6 (M3): 7 new bash security checks (8-14)
- JQ injection, obfuscated flags (Unicode lookalike hyphens),
/proc/environ access, brace expansion, Unicode whitespace,
zsh dangerous constructs, comment-quote desync
- Total: 14 checks (was 7)
Gap 7 (M5): Model picker numbered selection
- /model shows numbered sorted list, /model 3 picks by number
Gap 8 (M5): /config set command
- /config set provider.default mistral writes to .gnoma/config.toml
- Whitelisted keys: provider.default, provider.model, permission.mode
- New config/write.go with TOML round-trip via BurntSushi/toml
Gap 9 (M6): Simple token estimator
- EstimateTokens (len/4 heuristic), EstimateMessages (content + overhead)
- PreEstimate on Tracker for proactive compaction triggering
Gap 10 (M7): Router quality feedback from elfs
- Router.Outcome + ReportOutcome (logs for now, M9 bandit uses later)
- Manager tracks armID/taskType per elf via elfMeta map
- Manager.ReportResult called after elf completion in both agent + batch tools
|
2026-04-04 11:07:08 +02:00 |
|
|
|
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 |
|
