cbd4da272b
Add GPT-5.5 Pro preset
ci / test (push) Has been cancelled
2026-05-21 20:18:30 +01:00
Haoyu Tang
85bdb27a08
feat: add gpt-5.5 support ( #106 )
...
* feat: add gpt-5.5 support
* tests for gpt-5.5 support
2026-05-18 01:04:19 +05:00
Game_Time
8754203ec6
feat: add responses api, websocket support, and fast mode
2026-03-23 15:41:42 +05:00
Ra's al Ghul
e96db19538
feat: Add GPT-5.4 mini. ( #101 )
...
* feat: Add gpt-5.4-mini.
This just adds gpt-5.4-mini at (low/med/high/xhigh) reasoning levels.
* Fix formatting in README for reasoning effort section
---------
Co-authored-by: Ra's al Ghul <ras@alghul.com >
Co-authored-by: Game_Time <108236317+RayBytes@users.noreply.github.com >
2026-03-22 21:32:32 +05:00
Game_Time
e6eeae8fa6
publishing pipeline update + model spec
2026-03-16 16:56:23 +05:00
Ra's al Ghul
baf312a02e
Add support for GPT-5.4 ( #93 )
...
Co-authored-by: Nigel Norris <ras@alghul.com >
2026-03-08 16:08:14 +05:00
Game_Time
5b51b53a20
GPT-5.3-Codex
2026-02-28 00:23:42 +05:00
Game_Time
f15c880fc3
GPT-5.2-Codex added
2025-12-26 16:45:05 +05:00
Game_Time
c6eec41d25
Add support for GPT-5.2
2025-12-12 01:39:56 +05:00
Game_Time
8db91eb8c8
GPT-5.1 models "minimal" removed, add gpt-5.1-codex-max ( #80 )
2025-11-22 12:16:18 +05:00
Game_Time
e56416d653
Update README.md
2025-09-21 21:53:18 +05:00
Game_Time
499fa5ce0b
Update README.md
2025-09-21 21:51:54 +05:00
Game_Time
bc02c33eed
slight formatting changes
2025-09-21 21:50:44 +05:00
Game_Time
2857a5b601
Update README.md
2025-09-18 12:06:58 +05:00
Game_Time
cb9fccc6c6
Update README.md
2025-09-16 19:32:21 +05:00
Game_Time
74b400c62c
Update README.md
2025-09-16 19:15:07 +05:00
Game_Time
a7d5f3c292
Update README.md
2025-09-16 19:13:21 +05:00
Maciej Wilczyński
77d60fe321
Add GPT-5-Codex support ( #37 )
2025-09-16 17:58:41 +05:00
alexx-ftw
2f23cd5a89
native openai web search ability!
...
* feat: local passthrough for Responses tools via responses_tools + responses_tool_choice (behind CHATMOCK_ALLOW_RESPONSES_TOOLS)
* feat: gate Responses tools passthrough behind CHATMOCK_ALLOW_RESPONSES_TOOLS (default OFF)
* test(docs): add pytest for Responses tools passthrough (default off), and README usage section
* feat: responses tools hardening (fallback on 400, host allowlist, size guard, tool_choice strings only); tests updated
* feat: enable Responses tools passthrough by default; remove env gate
- Tools forwarded whenever is present
- Keep size guard and optional MCP host allowlist
- Accept strings unconditionally
Tests:
- Update to cover default passthrough and baseline (no responses_tools)
Docs:
- README: update instructions; move Star History to bottom
* chore: clean imports/comments; use gpt-5 in examples and tests
* docs: tighten Responses tools README; fix gpt-5 example\nchore: remove feature-specific test per review; trim comments/imports
* chore: remove __pycache__/ and bytecode; add .gitignore
* chore: add .gitignore for caches and bytecode
* Update README.md
* fix: remove MCP passthrough; allow only web_search in responses_tools
- Reject non-`web_search` types with 400 (`RESPONSES_TOOL_UNSUPPORTED`).
- Drop MCP host allowlist logic and related import.
- Keep size guard via `RESPONSES_TOOLS_MAX_BYTES` and fallback retry without extras.
- Docs: update README to state web_search-only passthrough.
Runtime verified locally with a stubbed upstream:
- OK: `responses_tools: [{"type": "web_search"}]` -> 200.
- BAD: `responses_tools: [{"type": "mcp"}]` -> 400 `RESPONSES_TOOL_UNSUPPORTED`.
* feat: forward Responses web_search tool via Chat Completions; fallback on rejection
- Accept `responses_tools` array and filter to `type: web_search` only.
- Enforce size guard `RESPONSES_TOOLS_MAX_BYTES` (default 32768).
- Fallback: if upstream rejects tools, retry without extras; otherwise return `RESPONSES_TOOLS_REJECTED`.
- README: document web_search-only passthrough and example.
- Headers: hint experimental features in OpenAI-Beta (responses; web-search).
* chore: remove local test-only forcing flag (CHATMOCK_FORCE_WEB_SEARCH)
* fix: restore full routes_openai (web_search-only passthrough + endpoints)
- Undo accidental large deletion from prior cleanup.
- Keep `web_search` passthrough, size guard, and fallback.
- Preserve `/v1/completions` and `/v1/models` endpoints and SSE handling.
* Update upstream.py
* Update upstream.py
* Update README.md
* Update README.md
* Update routes_openai.py
* feat(openai): default-enable web_search; accept preview; quiet retry; rm env knob
- Injects responses_tools=[{"type":"web_search"}] when client omits tools; explicit opt-out via responses_tool_choice:"none".
- Allowlist accepts "web_search" and "web_search_preview"; others rejected with RESPONSES_TOOL_UNSUPPORTED.
- Replaces env max-bytes knob with MAX_TOOLS_BYTES=32768.
- Retry on upstream rejection is silent; logs only under verbose.
* feat(stream): surface web_search_call as tool_calls; aggregate args; verbose-only logs
- Translates Responses web_search_call.* and output_item.done into OpenAI-style delta.tool_calls.
- Aggregates parameters by call_id (query/q, recency/time_range/days, domains/include/include_domains/include, max_results/topn/limit).
- No inference; arguments remain "{}" if upstream provides none. Logs only when verbose.
* feat(responses-tools): web_search passthrough; flag; fallback; Ollama parity; stable indexes
- Add --enable-web-search (default OFF) to inject web_search when requests omit responses_tools
- Allow tool types: web_search and web_search_preview; 32,768-byte cap on serialized responses_tools
- OpenAI /v1/chat/completions: passthrough + retry without extras on upstream rejection; return retry status
- Streaming: function.arguments always JSON; stable tool_calls index per call_id
- Ollama /api/chat: same passthrough + fallback behavior
- README updated to match behavior and limits
* Update README.md
* Update README.md
* Update routes_ollama.py
* Update routes_openai.py
* Update utils.py
---------
Co-authored-by: alexx-ftw <alexx-ftw@users.noreply.github.com >
Co-authored-by: Game_Time <108236317+RayBytes@users.noreply.github.com >
2025-09-16 17:06:00 +05:00
Game_Time
d235032368
Update README.md
2025-08-25 12:30:23 +05:00
Game_Time
630fccc0a7
Update README.md
2025-08-22 16:30:55 +05:00
Test User
75bb1ea4c6
homebrew tap
2025-08-22 15:39:31 +05:00
Game_Time
fc9727cb73
added "minimal" reasoning option (better for coding)
2025-08-20 11:41:10 +05:00
Game_Time
584574360f
Update README.md
2025-08-18 18:44:11 +05:00
Game_Time
bcbad51493
Update README.md
2025-08-18 18:43:16 +05:00
Game_Time
24f5dda1fd
Update README.md
2025-08-18 00:40:24 +05:00
Game_Time
b40c0a111a
Update README.md
2025-08-17 22:55:21 +05:00
Game_Time
e95f2efaca
Update README.md
2025-08-17 22:26:26 +05:00
Game_Time
3a4e0fe7f2
Update README.md
2025-08-17 21:51:25 +05:00
Game_Time
70da6b9c6d
Update README.md
2025-08-17 21:51:05 +05:00
Game_Time
046e13fa38
Update README.md
2025-08-17 12:56:11 +05:00
Game_Time
33cfd4573f
Update README.md
2025-08-16 17:22:47 +05:00
Game_Time
9d4da4c9f5
Update README.md
2025-08-16 17:22:34 +05:00
Game_Time
09cb98d185
Update README.md
2025-08-16 17:22:12 +05:00
Game_Time
2522062620
Update README.md
2025-08-16 17:21:02 +05:00
Game_Time
08c90be5b7
Update README.md
2025-08-16 17:18:44 +05:00
Game_Time
98e95be301
Update README.md
2025-08-16 17:18:06 +05:00
Game_Time
5e9fbf79f6
Update README.md
2025-08-16 17:17:42 +05:00
Game_Time
54aa6d7a18
Update README.md
2025-08-16 11:57:52 +05:00
Game_Time
11dfec16aa
Update README.md
2025-08-16 11:57:31 +05:00
Game_Time
749b239c4f
Update README.md
2025-08-16 10:55:38 +05:00
Game_Time
9ce5379cdb
Update README.md
2025-08-16 09:30:15 +05:00
Game_Time
39536725a7
Update README.md
2025-08-16 01:03:45 +05:00
Game_Time
50eccac1e2
Update README.md
2025-08-16 00:46:27 +05:00
Game_Time
b3c993aecd
Update README.md
2025-08-16 00:43:48 +05:00
Game_Time
2d3d654072
Update README.md
2025-08-16 00:42:38 +05:00
Game_Time
20cb42616b
Update README.md
2025-08-16 00:42:13 +05:00
Game_Time
aebe879619
Update README.md
2025-08-16 00:41:42 +05:00
Game_Time
43da12410b
Update README.md
2025-08-16 00:39:41 +05:00
Game_Time
c25906e606
Initial commit
2025-08-15 15:28:50 +05:00