mirror of
https://github.com/rcourtman/Pulse.git
synced 2026-05-19 16:27:37 +00:00
9329258f8b
The previous comment claimed DeepSeek's API aliases v4-flash/v4-pro to
deepseek-reasoner, justifying the auto coercion via the legacy
reasoner's known 400 behavior. That had the alias direction inverted:
per DeepSeek's pricing page, deepseek-chat and deepseek-reasoner are
deprecated aliases for v4-flash's non-thinking and thinking modes
respectively, not the other way around.
The coercion itself is empirically correct, though. Live preflight
against deepseek-v4-flash with tool_choice=required produces a
deterministic HTTP 400 ("provider rejected forced tool selection") in
275ms. The behavior is consistent across the DeepSeek user community
- multiple downstream projects (pydantic-ai #5193, claude-code-router
#1378, opencode #24190, others) confirm V4 models reject forced tool
selection despite DeepSeek's chat-completion docs listing required as
a supported value. Server reality disagrees with documentation.
This commit updates only the comments in openai.go and openai_test.go
to point at the empirical evidence and the community confirmation.
The coercion behavior is unchanged.
|
||
|---|---|---|
| .. | ||
| actionplanner | ||
| agentexec | ||
| agenttls | ||
| agentupdate | ||
| ai | ||
| alerts | ||
| api | ||
| bootstrap | ||
| cloudcp | ||
| config | ||
| crypto | ||
| deploy | ||
| discovery | ||
| dockeragent | ||
| hostagent | ||
| hosted | ||
| hostmetrics | ||
| kubernetesagent | ||
| license | ||
| logging | ||
| metrics | ||
| mock | ||
| mockmode | ||
| mockmodel | ||
| mockruntime | ||
| models | ||
| monitoring | ||
| notifications | ||
| platformsupport | ||
| recovery | ||
| relay | ||
| remoteconfig | ||
| repoctl | ||
| securityutil | ||
| sensors | ||
| servicediscovery | ||
| ssh/knownhosts | ||
| storagehealth | ||
| system | ||
| telemetry | ||
| testutil | ||
| truenas | ||
| unifiedresources | ||
| updates | ||
| updatesignature | ||
| utils | ||
| vmware | ||
| websocket | ||