Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
DeepSeek thinking-mode tool-call conversations may require the assistant
reasoning_content from previous turns to be sent back in later requests. Without
preserving it, those conversations can fail or lose reasoning context.
Changes:
- Preserve assistant reasoning_content when converting Chat Completions messages
to Responses input by wrapping it as a thinking block.
- Add regression coverage for non-streaming DeepSeek responses.
- Add regression coverage for streaming DeepSeek deltas.
- Add regression coverage that request-side messages[].reasoning_content is
passed through with tool calls.
Tests:
go test -tags=unit ./internal/pkg/apicompat ./internal/service -run
'TestChatCompletionsToResponses_AssistantReasoningContentPreserved|
TestChatCompletionsToResponses_AssistantThinkingTagPreserved|
TestForwardAsRawChatCompletions_PreservesDeepSeekReasoningContent|
TestForwardAsRawChatCompletions_ForcesStreamUsageUpstreamAndPassesUsageDownstream
When a chat-completions message has no usable content parts (empty array,
empty text part, or filtered-out image part), marshalChatInputContent
marshalled a nil slice to JSON null. The upstream Responses API rejects a
null content field with HTTP 400. Fall back to an empty string instead.
Fixes#2515
`corepack prepare pnpm@latest` now resolves to pnpm 11, which promotes
ERR_PNPM_IGNORED_BUILDS to a hard error and breaks the frontend stage of
`docker build`. Pin pnpm to v9 to match the CI workflow
(pnpm/action-setup version: 9) and keep image builds reproducible.
Fixes#2442
Vue's scoped-CSS compiler was dropping the `:global(.dark) .settings-tabs-shell`
rules in the production build, so the tab strip kept its light-mode white
background and the inactive tab labels (text-gray-300) showed at ~1.6:1
contrast — effectively unreadable.
Hoist the three dark-mode overrides into an unscoped `<style>` block so they
survive the scoped-CSS transform.
`fixCallIDPrefix` builds malformed ids when the input has the standard
OpenAI `call_<nanoid>` prefix:
input: call_YYen1qxDejd2myJwcTCf7Nyp
output: fcYYen1qxDejd2myJwcTCf7Nyp ← no underscore between 'fc' and the nanoid
ChatGPT's codex backend then rejects the replayed item with:
400 Invalid 'input[N].id': 'fcYYen1qxDejd2myJwcTCf7Nyp'.
Expected an ID that contains letters, numbers, underscores, or
dashes, but this value contained additional characters.
Sub2api wraps that into 502 to the client. Clients using the OpenAI SDK
on the OAuth/codex path see every multi-hop turn (after the first tool
call) fail because the item_reference rewritten this way gets sent on
every subsequent hop.
The other two branches of the same function correctly emit `fc_`
(line 1029: pass-through when already `fc*`; line 1035 fallback:
`fc_" + id`). Only the `call_` → `fc_` rewrite was missing the
underscore — looks like a copy-paste slip during the original commit.
Fix: change `"fc"` to `"fc_"` on the call_ branch. One character.
Repro:
client (OpenAI SDK) sends a function_call_output whose call_id is
`call_<nanoid>` (default OpenAI format). The sub2api request body
also contains an item_reference whose id mirrors the call_id (also
`call_<nanoid>`). On the codex OAuth path, this rewrite fires for
the item_reference's id, producing the malformed value.
Affects: `platform=openai type=oauth` accounts whose clients use the
official OpenAI SDK / Responses API conventions (id prefix `call_`).
API-key accounts and bridge-mode requests are untouched.
Image generation requests (forwardOpenAIImagesOAuth and
forwardOpenAIImagesAPIKey) were calling detachStreamUpstreamContext with
parsed.Stream, which for non-streaming requests (Stream=false) simply
returned the original client context unchanged. When the client
disconnected before the upstream completed (30-80s for image gen), the
context cancellation propagated to the upstream HTTP request, causing a
502 error despite the upstream having already started processing.
Switch to detachUpstreamContext (unconditional detach) so the upstream
image generation request is always bound to a background context and
completes regardless of client lifecycle.
Fixes#2310
