Game_Time
3a16fb8179
possible fix for refresh token
2025-09-25 20:05:54 +05:00
Game_Time
6c0d63869e
add limits to info
2025-09-25 16:43:55 +05:00
Paweł Hawrylak
fe5796abeb
Fix tool call argument serialization issue ( #39 )
...
* Tool calling arguments JSON fix
* Extracted duplicated code to helper function
* Update utils.py
---------
Co-authored-by: Game_Time <108236317+RayBytes@users.noreply.github.com >
2025-09-20 18:42:00 +05:00
Game_Time
bf16fbe3e1
add codex-mini to model list
2025-09-18 11:41:22 +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
8d92a63626
allow for diff machine logins
2025-09-12 21:53:59 +05:00
Game_Time
7d944548cd
reasoning effort as models support
2025-08-24 23:53:37 +05:00
Game_Time
ffcb12e76c
Merge pull request #16 from FammasMaz/FammasMaz-patch-1
...
fix: stream(legacy): include delta.reasoning alongside reasoning_summary
2025-08-22 13:53:05 +05:00
Game_Time
48780c9e83
finally make token counting work in apps
2025-08-22 02:09:31 +05:00
Game_Time
f05dc62eaa
Delete chatmock/__pycache__ directory
2025-08-22 02:02:11 +05:00
Game_Time
cadd959778
hopefully patch token counting?
2025-08-22 02:01:15 +05:00
Moeeze Hassan
b0de3a2e6f
fix: stream(legacy): include delta.reasoning alongside reasoning_summary
...
In legacy/current compatibility mode, stream both `delta.reasoning_summary` and
`delta.reasoning` (string) for reasoning deltas. This ensures clients that
expect `choices[0].delta.reasoning` as a string (e.g., OpenCode) render
reasoning without schema errors.
Change made only to legacy to avoid breakage with other software
2025-08-21 22:36:37 +02:00
Game_Time
c8c6540d23
intitial docker impl
2025-08-20 15:26:14 +05:00
Game_Time
fc9727cb73
added "minimal" reasoning option (better for coding)
2025-08-20 11:41:10 +05:00
Game_Time
8129b62083
implemented caching! should increase the usage available
2025-08-19 22:43:40 +05:00
Game_Time
2ed6dbe2d4
fix ollama regression
2025-08-19 21:26:47 +05:00
Game_Time
554ec53a25
refactor to reorganise codebase
2025-08-19 17:21:00 +05:00
