Commit Graph

24 Commits

Author SHA1 Message Date
tenglong
e544bfceae fix(codex): preserve Responses text format
Add "text" to Codex Responses API allowlist so text.format.json_schema
reaches upstream for structured outputs instead of being stripped.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-26 10:37:29 +07:00
Sutarto Jordan Chrisfivo
ed68bcedf8 fix(codex): preserve custom tools during request normalization
Add CODEX_PASSTHROUGH_TOOL_TYPES allowlist so Responses-native freeform
tools (e.g. grammar-backed apply_patch) survive normalizeCodexTools and
reach the upstream Codex Responses API intact.

Refs #1907

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-21 16:01:45 +07:00
decolua
b55cf36d2e feat(headroom): add proxy lifecycle management + dashboard UI
Build on the optional Headroom Token Saver from Carmelo Campos
(PR: feat: add optional Headroom token saver). Add managed start/stop
of the local headroom proxy from the dashboard, install detection,
status probing, and a simplified Token Saver UI.

- detect headroom CLI + python>=3.10, probe proxy /health
- spawn/stop proxy as a detached, pid-tracked process
- /api/headroom/{status,start,stop} routes, gated local-only in dashboardGuard
- one-click Start/Stop Headroom modal, no manual config needed
- claude<->openai shape conversion for /v1/compress via 9router translators

Thanks to Carmelo Campos (@carmelogunsroses) for the original Headroom integration.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-20 10:09:50 +07:00
decolua
aba4c45da6 fix(translator): ESM-safe registry + tool-id pairing + responses max_tokens; add real-creds tests
- translator/index.js: replace require() with static side-effect imports (ESM-safe),
  lazy-init registry maps to survive circular import order
- openai-responses->openai: map max_output_tokens -> max_tokens (avoid leaking field upstream)
- gemini/antigravity -> openai: derive deterministic tool_call id from name so
  functionCall/functionResponse pair correctly (fixes provider tool-pairing 400s)
- add offline unit tests (finish-reason, usage, session-manager, ollama malformed args, const guard)
- add real-creds integration tests (provider-cases + all-formats matrix: 6 inbound formats x 4 scenarios)

Includes co-located provider registry refactor (pricing/capabilities/media providers) and sessionManager updates.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-15 11:38:43 +07:00
decolua
d3f61aac2f refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup
- Bug B1-B7: media UI m.kind||m.type, serviceKinds, gemini mediaPriority, schema kind, models/info lookup by kind
- Dead code D1-D6: safeParseJSON, drop PROVIDER_ENDPOINTS, orphan fetcher, GITHUB_CONFIG derive, getProviderConfig internal, legacy kiro file
- Translator concerns: toOpenAIUsage, toOpenAIFinish (gemini/kiro/ollama + fix kiro tool finish), thinking effort maps
- Reorg helpers/ → concerns/ (logic) + formats/ (per-format) + schema/ (pure enums: roles/blocks/finishReasons/defaults)
- Wire ~280 hardcoded role/block/finish/default literals to schema enums across 20+ files
- collapseTextParts + extractTextContent dedup
- Normalize translator fn names to openaiToXRequest / xToOpenAIResponse
- Golden tests lock behavior; 0 regression (byte-for-byte providers/alias, 26=26 known fails)

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-14 18:49:38 +07:00
decolua
87fe069e9e refactor(open-sse): remove reverse coupling open-sse -> src (E2)
Move clineAuth into open-sse/shared (src re-exports back). Add standalone
open-sse/shared/machineId for codex session hashing (no @/lib/dataDir).
sttCore receives sttConfig via param instead of importing AI_PROVIDERS.
No behavior change; gate: no regression (26 known-fails unchanged).

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-13 16:35:07 +07:00
Kevin Le
c233c7c8fc fix(codex): durable OAuth refresh lifecycle
Add shared OAuth credential lifecycle manager with provider-aware refresh
decisions. Implement CodexExecutor.refreshCredentials so 401/403 retry
refresh works for Codex, track lastRefreshAt and refresh before the
upstream stale-token window, preserve omitted idToken, and add
per-connection single-flight refresh to avoid refresh-token rotation races.

Merged from PR #1664.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-06 11:04:36 +07:00
decolua
a648a42bdb Fix codex 2026-05-26 11:35:39 +07:00
Rezky Hamid
a463ee00ff feat(codex): add review model quota support (#836) 2026-05-03 14:57:33 +07:00
decolua
030fb34f88 - Updated markAccountUnavailable function to accept resetsAtMs for precise cooldown management.
- Added email backfill functionality for Codex OAuth connections to improve account information accuracy.
2026-04-24 11:36:16 +07:00
anuragg-saxenaa
d0ace2a3cf fix(codex): await image URL fetches before sending to upstream (closes #575)
Remote HTTP(S) image URLs are fetched and inlined as base64 data URIs
in a new prefetchImages() step run before super.execute(), so the body
sent to Codex contains resolved image bytes instead of URLs the backend
cannot access.

Scope is limited to the Codex executor — base executor and other
providers are untouched.

Co-authored-by: anuragg-saxenaa <anuragg.saxenaa@gmail.com>
Made-with: Cursor
2026-04-17 12:15:10 +07:00
decolua
04cdb75839 Add proactive token refresh lead times for providers and implement Codex proxy management 2026-04-14 11:41:06 +07:00
decolua
4bff21cb80 Enhance CodexExecutor with compact URL support 2026-04-14 10:18:27 +07:00
decolua
3b1a608e8d Fix codex cache session id 2026-04-13 15:52:01 +07:00
decolua
875a1282ea Fix bug 2026-04-11 11:36:33 +07:00
decolua
b0c6b61398 Refactor config 2026-03-12 16:20:46 +07:00
Rodrigo Rodrigues Costa
40a53fbd33 Fix: Codex image support - convert image_url to input_image format (#236)
Cursor sends images as Chat Completions format:
  { type: "image_url", image_url: { url: "data:...", detail: "auto" } }

But Codex Responses API requires:
  { type: "input_image", image_url: "data:..." }

- openai-responses.js: bidirectional conversion image_url <-> input_image
- responsesApiHelper.js: input_image -> image_url in Responses->Chat path
- codex.js: safety net conversion in executor before sending to Codex API

Note: Cursor has a known bug where images bypass the Override OpenAI Base URL
and are sent directly to api.openai.com. This fix is effective for other clients
(curl, Codex CLI, Claude Code) that route through the proxy correctly.

Made-with: Cursor
2026-03-05 10:31:50 +07:00
apeltekci
ac7cedd27e feat(responses): respect client streaming preference + string input support (#121)
- Remove forced stream=true from responsesHandler
- Add stream-to-JSON converter for non-streaming clients (Codex)
- Accept string input in Responses API (normalize to array)
- Codex SSE header fallback for missing Content-Type
- Refactor: extract shared normalizeResponsesInput()

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-15 11:47:55 +07:00
apple-techie
d7d5dc90bc fix: update Codex executor for gpt-5.3-codex support
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-12 18:12:38 +07:00
Hellodebasishsahu
127475df84 feat(codex): add GPT 5.3, fix API translation, add thinking levels
- Add GPT 5.3 Codex model with thinking level variants (none/low/medium/high/xhigh)
- Extract thinking level from model name suffix (e.g., gpt-5.3-codex-high)
- Fix Codex translation: preserve openai-responses format for Droid CLI
- Add effort level logging in request logs

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-06 09:46:11 +07:00
decolua
3c65e0c5f2 feat: Improve Antigravity quota monitoring and fix Droid CLI compatibility 2026-02-05 22:15:26 +07:00
decolua
7b864a9dcb feat(codex): Cursor compatibility + Next.js 16 proxy migration
- Force streaming for Codex/OpenAI models to fix non-streaming bug
- Strip unsupported params (user, metadata, stream_options, prompt_cache_retention)
- Force response translation from openai-responses to openai format
- Migrate middleware.js to proxy.js for Next.js 16
- Use webpack explicitly in dev/build scripts
- Updated Codex User-Agent
2026-02-02 09:17:15 +07:00
decolua
d9b8e48725 feat: OpenAI compatibility improvements & build fixes
- Fix hydration mismatches and initialization errors
- Add /v1/models endpoint for OpenAI clients
- Add Codex response translator (Responses → OpenAI)
- Fix circular dependencies and PropTypes
- Add Material Symbols font and CSS fixes
- Update README with deployment guide

Co-merged from PR #18 (14/15 commits, skipped debug)
2026-01-20 13:16:34 +07:00
decolua
26b61e5fbb Feat Kiro OAuth, Fix Codex 2026-01-15 18:29:47 +07:00