aa95b0d465
Run Claude on OpenCode's Anthropic endpoint, and name the plan in the UI
...
Claude models are served on /messages, which the OpenAI SDK can't speak, so
those runs go through LiteLLM's Anthropic route instead. Prompt caching moves
with them, since LiteLLM consumes the injection points the raw SDK rejects.
Zen and Go now show up by name instead of both reading 'OpenCode
subscription', and Zen keeps its cost tracked: it bills prepaid credits per
request, so those runs were never actually free.
2026-08-31 21:07:10 +00:00
8ed2433574
Fix OpenCode routes: drop LiteLLM-only prompt-cache arg, persist subscription provider for viewer label
2026-08-31 21:06:48 +00:00
cf179d564e
fix(llm): bind dedupe credentials to a provider; send reasoning=max via extra_body ( #1187 )
...
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com >
2026-08-28 09:27:57 -07:00
583af23d9a
fix(llm): only attach prompt-cache points on routes LiteLLM serves ( #1186 )
...
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com >
2026-08-28 09:26:57 -07:00
391d81bea7
feat(agents): evidence discipline, and coverage as a first-class artifact ( #961 )
...
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com >
2026-08-24 03:34:09 -07:00
174c16fa26
fix(llm): send OpenRouter app attribution on the request itself ( #1045 )
2026-08-10 11:24:02 -07:00
649a2e2140
fix(llm): omit parallel_tool_calls on tool-less requests
2026-08-09 15:44:16 +03:00
5bb9fe896b
feat(tui): replace Textual with a Go/Bubble Tea interface ( #941 )
2026-08-03 19:23:07 -07:00
2e7040240d
feat(config): accept STRIX_REASONING_EFFORT=max for providers that support it ( #956 )
...
Co-authored-by: Ahmed Allam <allam@usestrix.com >
2026-08-01 17:10:01 -07:00
d4e58b2cd0
fix(llm): pass LLM_EXTRA_HEADERS through ModelSettings so they reach the agent loop ( #937 )
2026-07-29 19:38:06 -07:00
27f9750cdc
feat(llm): enable Bedrock/Anthropic prompt caching for Claude models ( #772 )
...
Co-authored-by: Sean Turner <sean.turner@zerohash.com >
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com >
2026-07-26 17:12:57 -07:00
7d5a67d234
chore(llm): shorten timeout helper docstring; update tests
2026-07-17 19:45:32 -07:00
cf7689e927
fix(llm): use httpx.Timeout read-inactivity for per-turn model timeout
2026-07-17 18:40:23 -07:00
3bb95ab43d
fix(llm): add per-turn model request timeout so stalled streams fail fast and retry
2026-07-17 18:40:23 -07:00
c13960ae01
Support routed OpenAI required tool choice ( #732 )
2026-07-10 18:43:07 -04:00
22d327d21f
feat(settings): add force_required_tool_choice to LlmSettings ( #730 )
...
feat(inputs): implement logic for required tool choice based on model
test(inputs): add tests for force_required_tool_choice behavior
test(runner): update tests to include force_required_tool_choice in settings
2026-07-10 18:36:33 -04:00
8cdf0683a3
fix(core): collapse child agent initial input into a single user message ( #589 )
2026-06-29 06:51:47 -07:00
Jonathan Singer