Closed
Conversation
Custom headers configured under openai-compatibility (and any other provider passing through applyCustomHeaders) were silently dropped for the Host key, because Go's net/http reads the wire Host from req.Host, not req.Header["Host"]. As a result, virtual-host routed upstreams (e.g. LiteLLM behind an ingress) saw the base-url's host instead of the user-configured override and returned 404. Detect the Host key with http.CanonicalHeaderKey and assign it to req.Host so it is actually written on the wire. Other headers continue to use Header.Set as before. Fixes #2833
Addressing the P1 note from the Codex reviewer: applyCustomHeaders is
also called with a synthetic &http.Request{Header: ...} from the
websockets executors (aistudio_executor.go, codex_websockets_executor.go),
which forward only the header map. The previous continue meant a custom
Host was dropped from that map, regressing virtual-host overrides on
those flows. Mirror the value to both r.Host (for real net/http) and
r.Header (for header-map-only consumers).
…ni, Claude, Codex, OpenAI, and Vertex
feat(api): integrate auth index into key retrieval endpoints for Gemi…
…dex-GPT and Codex-Gemini flows - Introduced `LastImageHashByItemID` in Codex-GPT and `LastImageHashByID` in Codex-Gemini for deduplication of generated images. - Added support for handling `partial_image` and `image_generation_call` types, with inline data embedding for Gemini and URL payload conversion for GPT. - Extended unit tests to verify image handling in both streaming and non-streaming modes.
…2866) Anthropic has moved the 1M-context-window feature to General Availability, so the context-1m-2025-08-07 beta flag is no longer accepted and now causes 400 Bad Request errors when forwarded upstream. Remove the X-CPA-CLAUDE-1M detection and the corresponding injection of the now-invalid beta header. Also drop the unused net/textproto import that was only needed for the header-key lookup.
…te-1m-beta-header fix(executor): drop obsolete context-1m-2025-08-07 beta header
… links - Added VisionCoder sponsorship information to `README.md`, `README_CN.md`, and `README_JA.md`. - Updated external links to include `target="_blank"` for improved user experience. - Added new logo asset `visioncoder.png` for README use.
- Introduced `refreshIneffectiveBackoff` to prevent tight-looping in auto-refresh when token refresh fails to update expiry. - Adjusted refresh logic to apply backoff when `shouldRefresh` evaluates true. Closes: #2830
- Refactored `/healthz` handler to support `HEAD` requests alongside `GET`. - Updated tests to include validation for `HEAD` requests with expected status and empty body. Closes: #2929
…fill fix(codex): backfill streaming response output
fix(util): forward custom Host header to upstream
- Added `GPT-Image-2` as a built-in model to avoid dependency on remote updates for Codex. - Updated model tier functions (`CodexFree`, `CodexTeam`, etc.) to include built-in models via `WithCodexBuiltins`. - Introduced new handlers for image generation and edit operations under `OpenAIAPIHandler`. - Extended tests to validate 503 response for unsupported image model requests.
…AI image handlers
Codex CLI gates the built-in image_generation tool behind
AuthMode::Chatgpt (OAuth only). When clients connect via API key
auth through CPA, the tool is absent from requests, making image
generation unavailable through the reverse proxy.
Changes:
1. Inject image_generation tool (codex_executor.go):
Add ensureImageGenerationTool() that appends
{"type":"image_generation","output_format":"png"} to the tools
array if not already present. Applied to all three execution
paths: Execute, executeCompact, and ExecuteStream.
2. Route aliases for Codex CLI direct access (server.go):
Add /backend-api/codex/responses routes that map to the same
OpenAI Responses API handlers as /v1/responses. This allows
Codex CLI to connect via chatgpt_base_url config while keeping
AuthMode::Chatgpt, which enables the built-in image_generation
tool on the client side.
3. Unit tests (codex_executor_imagegen_test.go):
Cover no-tools, existing tools, already-present, empty array,
and mixed built-in tool scenarios.
Move credits handling from executor-level retry to conductor-level orchestration. When all free-tier auths are exhausted (429/503), the conductor discovers auths with available Google One AI credits and retries with enabledCreditTypes injected via context flag. Key changes: - Add AntigravityCreditsHint system for tracking per-auth credits state - Conductor tries credits fallback after all auths fail (Execute/Stream/Count) - Executor injects enabledCreditTypes only when conductor sets context flag - Credits fallback respects provider scope (requires antigravity in providers) - Add context cancellation check in credits fallback to avoid wasted requests - Remove executor-level attemptCreditsFallback and preferCredits machinery - Restructure 429 decision logic (parse details first, keyword fallback) - Expand shouldAbort to cover INVALID_ARGUMENT/FAILED_PRECONDITION/500+UNKNOWN - Support human-readable retry delay parsing (e.g. "1h43m56s")
CountTokens upstream API does not support enabledCreditTypes, so remove the dead credits fallback path from ExecuteCount and delete the unused tryAntigravityCreditsExecuteCount method. Fix gofmt on credits test file.
|
This pull request targeted The base branch has been automatically changed to |
…ferred body on success - findAllAntigravityCreditsCandidateAuths now filters by PinnedAuthMetadataKey to prevent credential isolation violations during credits fallback - Release deferredBody reference on success path to avoid holding large payloads in memory for the lifetime of the gin context
…s-only logging Remove deferred body optimization and maxErrorLog constants that were unrelated to credits fallback. Keep only MarkCreditsUsed/CreditsUsed helpers for flagging requests that consumed AI credits.
…auths as fallback candidates Replace antigravityCreditsAvailableForModel with inline known/unknown split. Auths whose credit hints are not yet populated are kept as lower-priority candidates instead of being rejected, breaking the chicken-and-egg deadlock at cold start.
…ion-tool-injection feat(codex): inject image_generation tool + route aliases for Codex CLI image generation
- Included `/v1/images` in AI API path prefixes. - Introduced tests to validate `/v1/images/generations` and `/v1/images/edits` as AI API paths.
feat(antigravity): conductor-level credits fallback for Claude models
Align GPT-5.5 Codex metadata with runtime cache
…ool injection - Modified `ensureImageGenerationTool` to accept `baseModel` for conditional logic. - Ensured `gpt-5.3-codex-spark` models bypass image_generation tool injection. - Updated relevant tests and executor logic to reflect changes.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
12 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.