fix(config): correct fallback model from kimi-for-coding to kimi-k2.5 #222

Closed

Timmy wants to merge 3 commits from fix/kimi-fallback-model into main

Author	SHA1	Message	Date
Bezalel	3433b8514a	fix(kimi): purge kimi-for-coding from model lists, tests, docs (#lazzyPit) Some checks failed Forge CI / smoke-and-build (pull_request) Failing after 45s Details kimi-for-coding triggers 401/403 access-terminated errors. Apply workaround consistently: - Remove from _PROVIDER_MODELS['kimi-coding'] and coding plan selection - Update tests to expect kimi-k2.5 instead - Update docs and reports - Live config on Beta VPS also corrected	2026-04-07 16:13:12 +00:00
Bezalel	a8eb7dfbad	feat(provider): first-class Ollama support + Gemma 4 defaults (#169 ) Some checks failed Forge CI / smoke-and-build (pull_request) Failing after 32s Details - Add 'ollama' to CLI provider choices and auth aliases - Wire Ollama through resolve_provider_client with auto-detection - Add _try_ollama to auxiliary fallback chain (before local/custom) - Add ollama to vision provider order - Update model_metadata.py: ollama prefix + gemma-4-* context lengths (256K) - Default model: gemma4:12b when provider=ollama	2026-04-07 15:55:50 +00:00
Bezalel	dd0fa2d1a1	fix(config): correct fallback model from kimi-for-coding to kimi-k2.5 All checks were successful Forge CI / smoke-and-build (pull_request) Successful in 47s Details The kimi-for-coding model triggers 403 access-terminated errors. Switch fallback config to use kimi-k2.5 which is valid for Hermes gateways. Refs: #lazzyPit	2026-04-07 15:40:00 +00:00

Author

SHA1

Message

Date

Bezalel

3433b8514a

fix(kimi): purge kimi-for-coding from model lists, tests, docs (#lazzyPit)

Forge CI / smoke-and-build (pull_request) Failing after 45s

Details

kimi-for-coding triggers 401/403 access-terminated errors.
Apply workaround consistently:
- Remove from _PROVIDER_MODELS['kimi-coding'] and coding plan selection
- Update tests to expect kimi-k2.5 instead
- Update docs and reports
- Live config on Beta VPS also corrected

2026-04-07 16:13:12 +00:00

Bezalel

a8eb7dfbad

feat(provider): first-class Ollama support + Gemma 4 defaults (#169 )

Forge CI / smoke-and-build (pull_request) Failing after 32s

Details

- Add 'ollama' to CLI provider choices and auth aliases
- Wire Ollama through resolve_provider_client with auto-detection
- Add _try_ollama to auxiliary fallback chain (before local/custom)
- Add ollama to vision provider order
- Update model_metadata.py: ollama prefix + gemma-4-* context lengths (256K)
- Default model: gemma4:12b when provider=ollama

2026-04-07 15:55:50 +00:00

Bezalel

dd0fa2d1a1

fix(config): correct fallback model from kimi-for-coding to kimi-k2.5

Forge CI / smoke-and-build (pull_request) Successful in 47s

Details

The kimi-for-coding model triggers 403 access-terminated errors.
Switch fallback config to use kimi-k2.5 which is valid for Hermes gateways.

Refs: #lazzyPit

2026-04-07 15:40:00 +00:00

fix(config): correct fallback model from kimi-for-coding to kimi-k2.5 #222

3 Commits