8 Commits

Author SHA1 Message Date
2d41c2d46c fix: session security and correctness — path traversal, turn count restore, incognito quality leak
- store: validate session ID against store root to block path traversal in Load/Save
- local: seed turnCount from LocalConfig.TurnCount so resumed sessions keep correct turn count
- main: pass TurnCount from snapshot to LocalConfig on resume
- main: suppress quality.json save when --incognito is active
- main: handle UserConfigDir error in quality save defer instead of silently using wrong path
- test: add TestSessionStore_Load/Save_RejectsPathTraversal
2026-04-06 00:04:09 +02:00
16193de4fc feat: LocalConfig + auto-save hook in session.Local
Refactor NewLocal to accept LocalConfig (matching engine/router patterns),
add persistence fields (SessionID, Store, Incognito, Logger), capture
finalState before releasing the lock to avoid data races, and auto-save
a Snapshot after each successful turn when a store is configured.
Add SessionID() to the Session interface and three new tests covering
auto-save, no-store no-panic, and SessionID accessors.
2026-04-05 23:46:48 +02:00
8b489d429a test: snapshot JSON round-trip with multi-turn conversation 2026-04-05 23:35:25 +02:00
3cf5cdeeb6 feat: SessionStore — save/load/list/prune session snapshots to .gnoma/sessions/ 2026-04-05 23:34:29 +02:00
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
706363f94b feat: rate limit pools, elf tree view, permission prompts, dep updates
Rate limits:
- Add PoolRPS/PoolTPM/PoolTokensMonth/PoolCostMonth pool kinds
- Provider defaults for Mistral/Anthropic/OpenAI/Google (tier-aware)
- Config override via [rate_limits.<provider>] TOML section
- Pools auto-attached to arms on registration

Elf tree view (CC-style):
- Structured elf.Progress type replaces flat string channel
- Tree with ├─/└─ branches, per-elf stats (tool uses, tokens)
- Live activity updates: tool calls, "generating… (N chars)"
- Completed elfs stay in tree with "Done (duration)" until turn ends
- Suppress raw elf output from chat (tree + LLM summary instead)
- Remove background elf mode (wait: false) — always wait
- Truncate elf results to 2000 chars for parent context
- Parallel hint in system prompt and tool description

Permission prompts:
- Show actual command in prompt: "bash wants to execute: find . -name '*.go'"
- Compact hint in separator bar: "⚠ bash: find . | wc -l [y/n]"
- PermReqMsg carries tool name + args

Other:
- Fix /model not updating status bar (session.Local.SetModel)
- Add make targets: run, check, install
- Update deps: BurntSushi/toml v1.6.0, chroma v2.23.1, x/text v0.35.0, cloud.google.com/go v0.123.0
2026-04-03 20:54:48 +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
c6b13f7cc8 feat: add session interface with channel-based local implementation
Session interface decouples UI from engine via channels:
- Send(input) starts agentic turn in background goroutine
- Events() returns channel for streaming events
- TurnResult() returns completed Turn after drain
- Cancel() propagates context cancellation
- Status() reports state, provider, model, token usage, turn count

Local implementation: engine runs on dedicated goroutine per turn,
events pushed to buffered channel (64), context cancellation
propagated. 5 tests.
2026-04-03 15:12:12 +02:00