KRATOSandClaude Opus 4.8 2ee03ac854 audit2: cli + modelregistry + dead-code cleanup (2 med, rest low) ...

cli: --reasoning-effort notice evaluates the EFFECTIVE model (works without --model) (MED); unsafe warning fires for --auto high too (MED); --auto value validated even with --skip-permissions-unsafe (LOW); DefaultRegistry built once per exec, not 3x (LOW); --profile kept as intentional legacy-compat accept-and-ignore (contested finding resolved, doc-commented). modelregistry: removed dead FallbackFor. tools: removed dead TaskNonInteractiveMessage + dead OnSandboxDecision hook (no setter anywhere); fixed the now-stale loop.go comment. TDD where behavioral; build/vet/full-suite green.

Refs #102

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>

2026-06-07 10:21:36 +05:30

..

catalog_test.go

Slice 3: model registry depth — regex aliases, deprecation fallback, reasoning defaults

2026-06-06 22:16:33 +05:30

catalog.go

Slice 3: model registry depth — regex aliases, deprecation fallback, reasoning defaults

2026-06-06 22:16:33 +05:30

cost_test.go

Add Go model registry catalog and cost helpers

2026-06-04 19:49:03 +05:30

cost.go

Add Go model registry catalog and cost helpers

2026-06-04 19:49:03 +05:30

models_test.go

Add Go model registry catalog and cost helpers

2026-06-04 19:49:03 +05:30

models.go

address PR #101 review (CodeRabbit): registry validation + test error checks

2026-06-07 08:33:14 +05:30

modes_test.go

Slice 7: agent modes — --mode flag + /mode command presets

2026-06-06 23:03:43 +05:30

modes.go

Slice 7: agent modes — --mode flag + /mode command presets

2026-06-06 23:03:43 +05:30

resolve_test.go

audit2: cli + modelregistry + dead-code cleanup (2 med, rest low)

2026-06-07 10:21:36 +05:30

resolve.go

audit2: cli + modelregistry + dead-code cleanup (2 med, rest low)

2026-06-07 10:21:36 +05:30