9 Commits

Author SHA1 Message Date
vikingowl c4fde583f5 chore(lint): gofmt sweep + errcheck cleanups in router discovery
Apply gofmt -w across the codebase (struct field comment realignment
only — no semantic changes) and silence two errcheck warnings on
fmt.Sscanf / fmt.Fprintf return values in internal/router/discovery
with explicit `_, _ =` discards. Required so `make check` is green
before tagging v0.1.0.
2026-05-20 03:13:05 +02:00
vikingowl 3c875276c9 feat(security): implement multi-wave audit remediation and agy provider support
Implemented full security remediation following Universal Security Pilot protocol:
- W1: Enforced SecureProvider at router and engine boundaries to prevent bypasses.
- W1: Implemented path-sensitive policy for MCP tools.
- W2: Added SHA256 hash verification for SLM downloads (llamafile).
- W3: Enhanced secret redaction for private keys (full body) and high-entropy strings.
- W4: Fixed symlink-based filesystem sandbox escapes in paths and grep.
- W4: Documented CLI agent trust boundaries.

Also added 'agy' (Antigravity) as a subprocess CLI provider with plain-text JSON schema support.
2026-05-20 01:13:13 +02:00
vikingowl 34f6f1c786 feat(security): incognito coherence across firewall/router/persist (Wave 2)
Closes the cluster of audit findings where gnoma's incognito promise
('no persistence, no learning, local-only routing') silently broke
because state was duplicated across the CLI flag, the firewall's
IncognitoMode, the router's localOnly flag, and the TUI's local
m.incognito field. Wave 2 makes security.IncognitoMode the canonical
source of truth.

W2-1 Router.Select rejects forced non-local arms when localOnly is on
  rather than short-circuiting and silently routing to cloud. Main
  fails fast when --incognito + --provider <cloud> are combined; the
  TUI toggle (Ctrl+X, /incognito, config panel) refuses with an
  actionable message when a non-local arm is pinned. Factored the
  three duplicated toggle sites into Model.attemptIncognitoToggle.

W2-2 persist.Store.Save consults an IncognitoGate (local interface,
  *security.IncognitoMode satisfies it). nil gate = always persist
  (legacy behaviour for tests); non-nil gate is consulted on every
  Save so TUI runtime toggles take effect without reconstructing the
  store. File mode 0o600, dir mode 0o700.

W2-3 tui.New seeds m.incognito from cfg.Firewall.Incognito().Active().
  Fixes the Ctrl+X-on-launch-with-incognito case where the first
  toggle silently turned the firewall OFF because the local flag
  started false out of sync with the firewall.

W2-4 saveQuality gates on both *incognito (defensive, covers the
  window before fwRef.Set fires) and fw.Incognito().ShouldLearn() (so
  TUI Ctrl+X suppresses the snapshot on exit). Quality restore skipped
  under --incognito. Quality file written 0o600 in dir 0o700.
  engine.reportOutcome and elf.Manager.ReportResult both gate on
  fw.Incognito().ShouldLearn() — bandit signal no longer leaks out of
  incognito sessions.

W2-5 session files written 0o600 in dirs 0o700 (was 0o644 / 0o755).

W2-6 IncognitoMode.LocalOnly dropped — dead field with no readers;
  routing local-only state lives on the router, not the firewall.

Also wires rtr.SetLocalOnly(true) when --incognito at launch — main
previously activated the firewall's flag but never told the router to
filter, so even without the forced-arm bug, launching with
--incognito alone gave you 'incognito badge but full arm pool'.
2026-05-19 22:57:36 +02:00
vikingowl 64ee385039 feat: QualityTracker — EMA router feedback from elf outcomes, ResultFilePaths tracking 2026-04-05 22:08:08 +02:00
vikingowl dae2c488e5 feat: wire persist.Store into engine, elf manager, and agent tools 2026-04-05 21:59:55 +02:00
vikingowl 4f1e0cf567 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 11363f3b97 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
vikingowl ebfbefc73d feat: configurable max_turns for elfs — LLM sets via agent tool param 2026-04-03 19:37:17 +02:00
vikingowl 13db7521b1 feat: M7 Elfs — sub-agents with router-integrated spawning
internal/elf/:
- BackgroundElf: runs on own goroutine with independent engine,
  history, and provider. No shared mutable state.
- Manager: spawns elfs via router.Select() (picks best arm per
  task type), tracks lifecycle, WaitAll(), CancelAll(), Cleanup().

internal/tool/agent/:
- Agent tool: LLM can call 'agent' to spawn sub-agents.
  Supports task_type hint for routing, wait/background mode.
  5-minute timeout, context cancellation propagated.

Concurrent tool execution:
- Read-only tools (fs.read, fs.grep, fs.glob, etc.) execute in
  parallel via goroutines.
- Write tools (bash, fs.write, fs.edit) execute sequentially.
- Partition by tool.IsReadOnly().

TUI: /elf command explains how to use sub-agents.
5 elf tests. Exit criteria: parent spawns 3 background elfs on
different providers, collects and synthesizes results.
2026-04-03 19:16:46 +02:00