Commit Graph

17 Commits

Author SHA1 Message Date
vikingowl e38cce5f1f fix(tui): security hardening, race-safety, and event handling fixes
Bundles the pending TUI work into a coherent batch. Bug fixes from
external review:

* expandPlaceholders: single-pass alternation regex over the original
  input prevents `#p\d+` / `#img\d+` tokens inside pasted content from
  being re-expanded after the bracket form is inlined.
* /incognito: gate savePromptHistory and the Ctrl+V image-write branch
  on `!m.incognito` so the no-persistence contract holds.
* history.txt: write at mode 0600 (chmod existing 0644 files), create
  parent dir at 0700, truncate to 500 entries on every save, slog.Warn
  on errors instead of swallowing.
* triggerPickerAction: guard m.config.Engine before SetModel, matching
  the /model handler.
* Picker key handler: navigation/enter/q consume, escape/ctrl+c close
  the picker AND fall through to global handlers (so streaming cancel
  and double-tap quit work with an overlay open), default swallows
  stray input.
* Paste line count: report total non-empty lines instead of newline
  count, ignoring trailing newlines (no more "+0 lines" for "abc").
* Ctrl+O restored to expand-output; Ctrl+Y is the new copy-response
  bind. /keys help text updated; picker help entries reordered.
* Tighter perms on .gnoma/pasted_image_*.png (0600).

Race-safety refactor: ApplyTheme used to mutate ~25 package-level
lipgloss styles in place. Replaced with an immutable themeStyles
snapshot and atomic.Pointer[themeStyles] swap. Readers go through a
theme() helper (one atomic load) instead of touching package vars
directly. No locks, no nested-RLock risk if rendering ever moves
off-thread.

Includes pre-existing in-flight work: TUISection in config with
persistent theme/vim settings; /copy /theme /vim slash commands;
provider-name completion; session.SetProvider for the provider picker.

Tests: placeholder_test.go (6 regression + happy-path cases including
the pasted-content collision), history_test.go (5 cases covering perms
on new and existing files, on-disk truncation, blank-input, newline
flattening), provider_test.go (provider switching + picker transitions
+ SLM gating).
2026-05-22 11:50:12 +02:00
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 fb42202834 refactor(security): seal SecureProvider via unexported marker method
The router.SecureProvider interface previously required a public
IsSecure() bool method. Any test mock — or future production type —
could satisfy it by returning true, defeating the W1 "only wrapped
providers may flow past the boundary" contract through convention
rather than at the type level.

Replaces IsSecure() bool with an unexported security.Marker interface
that has a single secured() method. Go's method-set semantics key
unexported methods by their defining package, so only types declared in
internal/security can satisfy Marker. *SafeProvider gets the lone
secured() implementation; router.SecureProvider embeds Marker.

The seal forces every test mock that previously implemented IsSecure()
to either (a) be wrapped with security.WrapProvider(mp, nil) at the use
site, or (b) drop the method entirely if the mock never flows through
SecureProvider. 93 use sites across 11 test files were updated via a
per-package secureMock helper. WrapProvider with a nil firewall ref is
a no-op pass-through, so test behavior is unchanged.

Empirically: a type from outside internal/security can declare
`secured()` but the compiler will reject assigning it to
router.SecureProvider because the unexported method belongs to the
other package's namespace. Convention → compile-time guarantee.
2026-05-20 02:04:07 +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 635dad660c feat(config): per-profile config layering with --profile flag (Phase C-1)
Adds opt-in user profiles for swapping API keys, CLI binaries, and
permission modes between contexts (work/private/experiment/...).

Profile mode engages only when ~/.config/gnoma/profiles/ exists, so
existing single-config installations are untouched. Selection order:
--profile flag → default_profile in base config → fatal error.

Layering: defaults → ~/.config/gnoma/config.toml → profiles/<name>.toml
→ <projectRoot>/.gnoma/config.toml → env. Map sections merge per-key;
[[arms]] and [[mcp_servers]] merge by id/name; [[hooks]] appends.

Per-profile data: quality-<name>.json and sessions/<name>/ keep the
bandit and session list from cross-contaminating between profiles.

Profile names restricted to [A-Za-z0-9_-] to block --profile=../foo
path traversal into derived paths.
2026-05-19 21:35:33 +02:00
vikingowl ec9433d783 chore(lint): clear remaining errcheck and staticcheck findings
Brings the project to a clean `make lint` baseline (0 issues).

Mechanical:
- Wrap deferred resp.Body.Close() in closures (router/discovery.go,
  router/probe.go) so the unchecked return surfaces as `_ = ...`.
- Apply `_ = ...` (single or multi-return blank) to test-file calls
  that intentionally ignore errors: os.MkdirAll / os.WriteFile / os.Chdir
  in setup paths, Close / Shutdown in teardown, Submit / Spawn / Send /
  LoadDir in tests that assert on side effects.

Structural:
- engine.handleRequestTooLarge drops the unused req parameter and
  rebuilds the request from compacted history (SA4009 — argument was
  overwritten before first use).
- provider.ClassifyHTTPStatus and google.applyCapabilityOverrides switch
  to tagged switches over the discriminator (QF1002).
- tui.app.go MouseWheel + inputMode and cmd/gnoma main slm-status use
  tagged switches in place of equality chains (QF1003).
- cmd/gnoma main.go merges a var decl with its immediate assignment
  (S1021).
- Three empty-branch sites (dispatcher_test, loader_test,
  coordinator_test) become real assertions or get the dead `if` removed
  (SA9003).
2026-05-19 17:53:42 +02:00
vikingowl d71bd942c4 feat: local model reliability — SDK retries, capability probing, init skill, context compaction
Three compounding bugs prevented tool calling with llama.cpp:
- Stream parser set argsComplete on partial JSON (e.g. "{"), dropping
  subsequent argument deltas — fix: use json.Valid to detect completeness
- Missing tool_choice default — llama.cpp needs explicit "auto" to
  activate its GBNF grammar constraint; now set when tools are present
- Tool names in history used internal format (fs.ls) while definitions
  used API format (fs_ls) — now re-sanitized in translateMessage

Additional changes:
- Disable SDK retries for local providers (500s are deterministic)
- Dynamic capability probing via /props (llama.cpp) and /api/show
  (Ollama), replacing hardcoded model prefix list
- Engine respects forced arm ToolUse capability when router is active
- Bundled /init skill with Go template blocks, context-aware for local
  vs cloud models, deduplication rules against CLAUDE.md
- Tool result compaction for local models — previous round results
  replaced with size markers to stay within small context windows
- Text-only fallback when tool-parse errors occur on local models
- "text-only" TUI indicator when model lacks tool support
- Session ResetError for retry after stream failures
- AllowedTools per-turn filtering in engine buildRequest
2026-04-13 02:01:01 +02:00
vikingowl ce5f9d3dc9 feat(tui): Tier 3-4 UX improvements — split, routing, session naming, context bar
- Split app.go (2091→1378 lines) into rendering.go, events.go, init.go
- Add EventRouting stream event for router arm transparency
- Add session auto-naming from first user message
- Add context window progress bar in status bar
- Add /keys cheatsheet, /replay for resumed sessions
- Add inline cost-per-turn after assistant responses
- Add diff previews in fs.write/fs.edit permission prompts
- Collapse tool output to 3 lines by default (ctrl+o expands)
- Use AddPrefix for system context instead of InjectMessage
- Handle ContentThinking and ContentToolResult in session resume
- Show session title in resume picker
- Add /model numeric selection snapshot safety
2026-04-12 05:13:16 +02:00
vikingowl ae9683818b 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
vikingowl 2f60bd9f0a 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
vikingowl 0d08056f14 test: snapshot JSON round-trip with multi-turn conversation 2026-04-05 23:35:25 +02:00
vikingowl 9d18f1179a feat: SessionStore — save/load/list/prune session snapshots to .gnoma/sessions/ 2026-04-05 23:34:29 +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 e1a47a7620 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
vikingowl 704f3a7302 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
vikingowl 0f93ee18e4 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