5 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 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 43ea2e562d feat(engine): two-stage tool routing for small local arms
Plan A from docs/superpowers/plans/2026-05-19-post-slm-unlock.md.

Small local SLMs (<=16k context) waste ~1500 tokens per turn on the
full tool catalogue. Two-stage routing replaces round-1 tools with a
single synthetic select_category schema; round-2+ sends only the
selected category's real tool schemas plus select_category for
re-selection.

- internal/tool/category.go: Category type, optional Categorized
  interface, CategoryOf() with meta fallback. fs.read/fs.ls -> read,
  fs.write/fs.edit -> write, fs.glob/fs.grep -> search, bash -> exec.
- internal/engine/twostage.go: synthetic select_category tool,
  intercept helper, per-turn selectedCategory state under e.mu.
- Engine round 1 forces ToolChoiceRequired so SLMs don't fall back to
  prose. State resets at the top and end of every runLoop.
- Activates automatically on a forced local arm with ContextWindow
  <=16384, or via [router].force_two_stage TOML key.
- Integration test drives a 3-round trip and asserts: round 1 emits
  exactly one schema (synthetic) with ToolChoiceRequired, round 2
  contains only write-category schemas + select_category, real
  fs.write executes. Invalid-category fallback round-trips back to
  round-1 mode.
2026-05-19 20:53:21 +02:00
vikingowl 9fb520fba6 feat(engine): M8 cleanup — Wave A wiring gaps
- Remove stale TODO(P0c) comment from main.go (resolved by P0c tier routing)
- Wire config.Provider.Temperature → engine.Config.Temperature → provider.Request
- Add WithMaxFileSize option to fs.write; wire cfg.Tools.MaxFileSize in main.go
- Wire router.ReportOutcome after each runLoop return (success = err == nil)
- Fix nil-callback guard on EventRouting dispatch (pre-existing bug exposed by new test)
2026-05-07 15:22:22 +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