The fetchCompatibleModelIds() function had no timeout on its fetch() call,
causing /v1/models to hang indefinitely when an openai-compatible provider
was unreachable or slow to respond.
Additionally, upstream/cross-instance connections (provider IDs containing
a UUID suffix like openai-compatible-chat-XXXXXXXX) would trigger recursive
/models fetches between instances, creating infinite loops.
Fixes:
- Add AbortController with 5-second timeout to the fetch() call
- Skip dynamic model fetching for upstream/cross-instance connections
(detected by UUID suffix pattern in provider ID)
- Existing try/catch already handles abort errors gracefully
Co-authored-by: Agent Zero <agent@agent-zero.local>
sseToJsonHandler.js unconditionally deleted reasoning_content from all
non-streaming responses (added for Firecrawl SDK compatibility). This
breaks thinking models (Qwen3.5, Claude extended thinking, etc.) where
the model may use all tokens for reasoning, leaving content empty.
When reasoning_content is stripped in that case, the response appears
completely empty to the client.
Fix: only strip reasoning_content when the response also has non-empty
content, so that reasoning output is preserved when it is the only
useful output.
Co-authored-by: Agent Zero <agent@agent-zero.local>
- Allow selecting multiple models for 9router provider
- Merge models instead of overwriting (backwards-compatible)
- Support setting active model via click or Apply
- Click active model to clear default (model = '')
- Remove individual models via X button (persists to config)
- Add PATCH endpoint for clearing active model
- Update GET to return normalized model list
- Preserve subagent model configuration for explorer subagent
Made-with: Cursor
The shutdown API calls `process.exit(0)` on POST without any authentication or authorization checks. Any party that can reach this endpoint can terminate the server process, causing immediate service disruption.
Affected files: route.js
Signed-off-by: tuanaiseo <221258316+tuanaiseo@users.noreply.github.com>
Cursor's API now rejects requests with outdated client versions,
returning [400]: Update Required for Composer 2. Bump
x-cursor-client-version from 2.3.41 to 3.1.0 across all three
locations where it is set.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sửa lỗi /v1/models chỉ biết lấy model từ danh sách tĩnh hoặc từ providerSpecificData.enabledModels. Với API Key Compatible Providers, endpoint test /api/providers/<id>/models vẫn lấy được model động từ upstream, nhưng /v1/models lại không fallback sang danh sách động đó. Ngoài ra alias trả ra cũng đang dùng providerId nội bộ thay vì prefix trong cấu hình.
Đã fix để OpenAI/Anthropic Compatible dùng đúng prefix làm alias public nếu chưa có enabledModels, /v1/models sẽ tự fetch động từ upstream /models
checkAndRefreshToken() updated providerSpecificData.copilotToken but
not the top-level creds.copilotToken. GithubExecutor.buildHeaders()
reads the top-level key, so every request after a proactive refresh
still sent the expired token, causing 401 "IDE token expired".
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add clientDetector utility to identify CLI tools (Claude Code, Gemini CLI,
Antigravity, Codex) from request headers. When the CLI tool and provider
are a native pair, skip all translation — only swap model and Bearer token.
Made-with: Cursor
- Add /api/providers/kilo/free-models endpoint with 1hr cache
- Fetch and merge Kilo free models with hardcoded models for kilocode provider
- Display 'Free' badge on models fetched from Kilo API
- Fix Windows build: add cross-env, remove --webpack flag, add turbopack config
- Add outputFileTracingExcludes for Windows system directories
Replace empty reasoning_content with explicit </think> closing tag when exiting thinking block to properly signal end of reasoning section in streaming responses.
- Encode thoughtSignature into tool_call.id using _TSIG_ delimiter and base64url
- Decode _TSIG_ on request to restore thoughtSignature for Gemini multi-turn thinking
- Track pendingThoughtSignature across parts for deferred signature attachment
- Add LocalMutex (2-layer locking) to prevent ELOCKED on concurrent DB access
- Increase lockfile retries from 5 to 15 for multi-process robustness
- Restore db.json seed on first run to prevent ENOENT on lockfile.lock
- Use process.env.BASE_URL fallback in models test route
- Remove gemini-3-flash-lite-preview from provider models
Co-authored-by: kwanLeeFrmVi <quanle96@outlook.com>
Closes#450
Made-with: Cursor
- Add claudeHeaderCache.js to intercept and cache live Claude Code client headers
- Forward cached headers dynamically to api.anthropic.com via default.js
- Strip first-party identity headers (x-app, claude-code-* beta) for non-Anthropic upstreams
- Validate and sanitize tool call IDs to match Anthropic pattern (^[a-zA-Z0-9_-]+$)
- Skip thinking blocks when applying cache_control; fix max_tokens buffer (+1024)
- Strip cache_control from thinking blocks in openai-to-claude translator
- Comment out thoughtSignature in Gemini translator (kept for reference)
- Expand .gitignore to match all deploy*.sh variants
Co-authored-by: kwanLeeFrmVi <quanle96@outlook.com>
Closes#433
Made-with: Cursor
The BaseExecutor's buildUrl() and buildHeaders() methods only handled
openai-compatible-* providers but not anthropic-compatible-* providers.
This caused Anthropic-compatible synthetic providers to fail API testing
by hitting the wrong endpoint (returning documentation instead of valid
API responses) and using incorrect auth headers.
Changes:
- Added buildUrl() handling for anthropic-compatible-* providers
to append /messages path
- Added buildHeaders() handling for x-api-key header and
anthropic-version for anthropic-compatible providers
Fixes #XXX
Co-authored-by: Bitgineer <bitgineer@bitgineer.shop>
The github provider in open-sse/config/providers.js was missing clientId,
causing refreshGitHubToken() to send client_id=undefined on 401 retry.
Also guard against undefined clientSecret in both refresh implementations.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Apply fix from PR #354 by @tannk4w to properly signal tool_calls finish_reason
when model emits tool calls, allowing OpenAI-compatible clients to continue with
tool result processing instead of stopping prematurely.
Refactored finish_reason logic into computeFinishReason() helper to eliminate
duplication and improve maintainability across flush and completion paths.
Co-authored-by: tannk4w <tannk@tmi-soft.vn>
Thanks to @tannk4w, @trungtq2799, @quanhavn, and @East-rayyy for the thorough
review and improvement suggestions on the original PR.
Made-with: Cursor
Adds OpenCode (https://github.com/opencode-ai/opencode) as a supported
provider. OpenCode is an open-source terminal AI coding assistant with
an OpenAI-compatible API running locally.
Changes:
- open-sse/config/providers.js: add opencode baseUrl (localhost:4096)
with openai format (fully compatible, no custom headers needed)
- open-sse/services/model.js: add 'oc' alias → opencode
- src/shared/constants/providers.js: add opencode to subscription
providers with alias 'oc', icon 'terminal', color #E87040
Usage after setup: use model prefix 'oc/<model>' to route through
a running OpenCode instance (e.g. oc/claude-sonnet-4-5).
Closes#378
