xiaoen b84adacc2f fix(routing): address review feedback on CJK estimation and observability ...

1. CJK token estimation: replace flat rune_count/3 with script-aware
   counting — CJK runes (U+2E80–U+9FFF, U+F900–U+FAFF, U+AC00–U+D7AF)
   count as 1 token each, non-CJK runes at /4. This fixes a 3x
   underestimate for Chinese/Japanese/Korean text that could incorrectly
   route complex CJK messages to the light model.

2. Routing observability: SelectModel now returns the computed score as
   a third value. selectCandidates logs the score on both paths — Info
   level for light model selection, Debug level for primary model
   selection.

3. Added tests: TestExtractFeatures_TokenEstimate_Mixed (CJK+ASCII mix),
   TestRouter_SelectModel_ReturnsScore.

Addresses review feedback from @mingmxren.

2026-03-06 13:10:20 +08:00

..

context_cache_test.go

…

context_test.go

…

context.go

feat: honor PICOCLAW_HOME env var for config, auth, and workspace paths

2026-03-05 22:08:37 +00:00

instance_test.go

…

instance.go

merge: resolve conflicts with upstream/main

2026-03-06 11:27:48 +08:00

loop_media.go

…

loop_test.go

Feat/add tool enable or disable configuration (#1071)

2026-03-05 14:53:26 +08:00

loop.go

fix(routing): address review feedback on CJK estimation and observability

2026-03-06 13:10:20 +08:00

memory.go

…

mock_provider_test.go

…

registry_test.go

…

registry.go

…

thinking_test.go

feat: add extended thinking support for Anthropic models (#1076)

2026-03-05 09:51:18 +08:00

thinking.go

feat: add extended thinking support for Anthropic models (#1076)

2026-03-05 09:51:18 +08:00