decolua
b282f05549
Refactor
2026-06-15 18:18:04 +07:00
decolua and Cursor
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
b309261166
enhance Kiro profile ARN resolution
2026-06-13 09:28:55 +07:00
lukmanfauzie
c43f8c54d4
fix: Antigravity INVALID_ARGUMENT errors and Copilot agent mode parity
2026-04-26 19:53:08 +08:00
decolua
1973fe5a83
fix(translator): correct thought signatures for AG, Gemini CLI, Vertex; fix missing Vertex response translator
...
- Add DEFAULT_THINKING_AG_SIGNATURE, DEFAULT_THINKING_GEMINI_CLI_SIGNATURE, DEFAULT_THINKING_VERTEX_SIGNATURE
- Rename DEFAULT_THINKING_GEMINI_SIGNATURE → DEFAULT_THINKING_AG_SIGNATURE for clarity
- Pass provider-specific signature into openaiToGeminiBase (AG vs Gemini CLI)
- Replace synthetic thoughtSignatures with Vertex-native signature in postProcessForVertex
- Register Vertex → OpenAI response translator (fixes empty Vertex streaming responses)
Made-with: Cursor
2026-04-05 00:38:36 +07:00
decolua
333e704b2a
MODEL_CAPS
2026-04-04 23:24:24 +07:00
decolua
93b8668e9e
Fix AG
2026-04-01 11:48:38 +07:00
kwanLeeFrmVi
054facb08b
fix(gemini): preserve thoughtSignature via tool_call ID smuggling + fix ELOCKED mutex
...
- 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
2026-03-30 16:57:28 +07:00
kwanLeeFrmVi
1c160cc8d9
feat(claude-code): spoof TLS fingerprint and stabilize headers for Anthropic
...
- 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
2026-03-30 16:27:28 +07:00
Anurag Saxena
ade3f57d4c
fix: sanitize Gemini function names to meet API requirements ( closes #369 ) ( #403 )
2026-03-27 10:40:29 +07:00
Kwan96
1154244f1d
refactor: clean JSON schemas for Gemini function declarations ( #371 )
...
Apply cleanJSONSchemaForAntigravity to both Anthropic and OpenAI format tool schemas before converting to Gemini function declarations
2026-03-23 09:18:22 +07:00
decolua
b0c6b61398
Refactor config
2026-03-12 16:20:46 +07:00
decolua
985985e454
refactor: update Antigravity model configurations and pricing
2026-02-20 17:52:15 +07:00
zx and Cursor
a229d79158
feat(antigravity): initial steps for Antigravity anti-ban alignment
...
Cherry-picked from decolua/9router#141 (author: LinearSakana / zx <me@char.moe >)
- Implement client identity spoofing with numeric enums (ideType: 9, pluginType: 2)
- Add runtime platform detection for User-Agent and metadata
- Implement per-connection session ID caching (binary-compatible format)
- Add ANTIGRAVITY_HEADERS (X-Client-Name, X-Client-Version, x-goog-api-client)
- Add X-Machine-Session-Id header injection
- Align metadata/mode parameters across all Antigravity API calls
- Implement double injection for system prompt (raw + [ignore] wrapped)
- Rename internal anti-loop header to x-request-source for anonymity
Skipped: commit 6 (signature side-channel caching) — kept DEFAULT_THINKING_GEMINI_SIGNATURE
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-02-20 14:44:29 +07:00
decolua
2e854bd4c9
feat(antigravity): integrate Antigravity tool with MITM support and update CLI tools
2026-02-08 16:28:13 +07:00
decolua
3c65e0c5f2
feat: Improve Antigravity quota monitoring and fix Droid CLI compatibility
2026-02-05 22:15:26 +07:00
decolua
c7219d0ac9
Fix cloud
2026-01-29 18:07:28 +07:00
decolua
fb5be37e14
Fix Antigravity
2026-01-12 16:53:27 +07:00
decolua
af5edfd00e
Fix bug antigravity
2026-01-12 15:08:31 +07:00
decolua
f46ff42cb3
refactor: streamline provider interactions and enhance error handling
2026-01-11 21:45:01 +07:00
decolua
18533505ef
refactor: restructure translator from from-openai/to-openai to request/response folders
2026-01-09 17:14:51 +07:00
decolua