Commit Graph
722 Commits
Author SHA1 Message Date
Finessse 72be557be8 middleware: keep tools for droid/factory 2025-12-17 20:34:06 +07:00
Finessse d23af0518d middleware: model-aware prompt budget 2025-12-17 20:30:03 +07:00
Finessse 29bb32ccfd tray: GUI build, autostart toggle, packaging 2025-12-17 19:39:57 +07:00
Finessse 3bff4ed6f1 desktopctl: add process control + healthz 2025-12-17 19:11:18 +07:00
Finessse d8e55c7318 auth: allow probing unknown client model support 2025-12-17 18:02:15 +07:00
Finessse d4c3f6fcad codex: avoid role=system in input 2025-12-17 17:55:17 +07:00
Finessse 7649532c4a codex: always send official instructions; keep client as system 2025-12-17 17:53:55 +07:00
Finessse d3ca1218c5 codex: move instructions into system input 2025-12-17 17:52:13 +07:00
Finessse bc38faa2ad codex: prefix official instructions for non-codex clients 2025-12-17 17:47:27 +07:00
Finessse 755291cef8 middleware: preserve tool call/result pairs when trimming 2025-12-17 17:15:45 +07:00
Finessse b1b30d10ea codex: cap injected default instructions 2025-12-17 17:06:41 +07:00
Finessse ef732615a4 claude: do not auto-enable extended thinking 2025-12-17 17:06:33 +07:00
Finessse 2b53dbb09c middleware: harden agentic request trimming 2025-12-17 17:06:25 +07:00
Finessse 3167b12f0c api: trim oversized Codex CLI requests 2025-12-17 16:16:28 +07:00
Finessse ed30fd6f63 codex: avoid duplicating system instructions 2025-12-17 16:16:02 +07:00
Finessse 13d1ba7137 remove amp support 2025-12-17 16:15:10 +07:00
Finessse 5a576264dd feat(routing): gemini-3-pro fallback to gemini-cli 2025-12-17 14:20:33 +07:00
Finessse e7e1b26f11 fix(antigravity): keep scalar text parts 2025-12-17 14:19:45 +07:00
Finessse 7f260eb15e feat(openai): add embeddings + base-url aliases 2025-12-17 14:18:38 +07:00
Finessse 99e9ff1ad6 docs: Claude Code via local proxy
- Document Windows Claude Code settings for using CLIProxyAPI (base URL, auth token, default model mapping)
- Add Claude alias remapping for opus/sonnet/haiku to Gemini-backed models
- Improve auth unavailability reporting (429 cooldown vs 503 blocked) and fallback provider inference
2025-12-17 00:33:25 +07:00
Finessse e2950408bc fix(codex): emit fallback text when upstream returns none 2025-12-16 20:01:39 +07:00
Finessse d6aff12ace fix(responses): keep non-JSON tool output as string 2025-12-16 20:01:08 +07:00
Finessse 52f4d23c85 fix(antigravity): normalize tool call/response adjacency 2025-12-16 20:00:33 +07:00
Finessse d7eacf9524 Fix Codex 400 from empty streaming done text 2025-12-16 13:46:27 +07:00
Finessse 153d2bec96 Responses: ensure message output precedes reasoning 2025-12-16 13:00:12 +07:00
Finessse 2298be6958 Fix antigravity OpenAI chat streaming parsing 2025-12-16 13:00:04 +07:00
Finessse 6558cbbc0a Fix gemini-cli OpenAI chat streaming parsing 2025-12-16 12:59:56 +07:00
Finessse 4b4cd108ce Fix tool result ordering for Droid CLI 2025-12-14 23:34:54 +07:00
Luis Pater 660aabc437 fix(executor): add allowCompat support for reasoning effort normalization
Introduced `allowCompat` parameter to improve compatibility handling for reasoning effort in payloads across OpenAI and similar models.
2025-12-13 04:06:02 +08:00
Luis Pater f3f0f1717d Merge branch 'dev' into think 2025-12-12 22:16:44 +08:00
Luis Pater 7621ec609e Merge pull request #501 from huynguyen03dev/fix/openai-compat-model-alias-resolution
fix(openai-compat): prevent model alias from being overwritten
2025-12-12 21:58:15 +08:00
Luis Pater 9f511f0024 fix(executor): improve model compatibility handling for OpenAI-compatibility
Enhances payload handling by introducing OpenAI-compatibility checks and refining how reasoning metadata is resolved, ensuring broader model support.
2025-12-12 21:57:25 +08:00
hkfires 374faa2640 fix(thinking): map budgets to effort levels
Ensure thinking settings translate correctly across providers:
- Only apply reasoning_effort to level-based models and derive it from numeric
  budget suffixes when present
- Strip effort string fields for budget-based models and skip Claude/Gemini
  budget resolution for level-based or unsupported models
- Default Gemini include_thoughts when a nonzero budget override is set
- Add cross-protocol conversion and budget range tests
2025-12-12 21:33:20 +08:00
Luis Pater 1c52a89535 Merge pull request #502 from router-for-me/iflow
fix(auth): prevent duplicate iflow BXAuth tokens
2025-12-12 20:03:37 +08:00
hkfires e7cedbee6e fix(auth): prevent duplicate iflow BXAuth tokens 2025-12-12 19:57:19 +08:00
Luis Pater b8194e717c Merge pull request #500 from router-for-me/think
fix(codex): raise default reasoning effort to medium
2025-12-12 18:35:26 +08:00
huynguyen03.devandAmp 15c3cc3a50 fix(openai-compat): prevent model alias from being overwritten by ResolveOriginalModel
When using OpenAI-compatible providers with model aliases (e.g., glm-4.6-zai -> glm-4.6),
the alias resolution was correctly applied but then immediately overwritten by
ResolveOriginalModel, causing 'Unknown Model' errors from upstream APIs.

This fix skips the ResolveOriginalModel override when a model alias has already
been resolved, ensuring the correct model name is sent to the upstream provider.

Co-authored-by: Amp <amp@ampcode.com>
2025-12-12 17:20:24 +07:00
hkfires d131435e25 fix(codex): raise default reasoning effort to medium 2025-12-12 18:18:48 +08:00
Luis Pater 6e43669498 Fixed: #440
feat(watcher): normalize auth file paths and implement debounce for remove events
2025-12-12 16:50:56 +08:00
Ben Vargas b09e2115d1 fix(models): add "none" reasoning effort level to gpt-5.2
Per OpenAI API documentation, gpt-5.2 supports reasoning_effort values
of "none", "low", "medium", "high", and "xhigh". The "none" level was
missing from the model definition.

Reference: https://platform.openai.com/docs/api-reference/chat/create#chat_create-reasoning_effort
2025-12-11 15:26:23 -07:00
Luis Pater a68c97a40f Fixed: #492 2025-12-12 04:08:11 +08:00
Luis Pater cd2da152d4 feat(models): add GPT 5.2 model definition and prompts 2025-12-12 03:02:27 +08:00
hkfires 3c315551b0 refactor(executor): relocate gemini token counters 2025-12-11 21:56:44 +08:00
hkfires 27c9c5c4da refactor(executor): clarify executor comments and oauth names 2025-12-11 21:56:44 +08:00
hkfires fc9f6c974a refactor(executor): clarify providers and streams
Add package and constructor documentation for AI Studio, Antigravity,
Gemini CLI, Gemini API, and Vertex executors to describe their roles and
inputs.

Introduce a shared stream scanner buffer constant in the Gemini API
executor and reuse it in Gemini CLI and Vertex streaming code so stream
handling uses a consistent configuration.

Update Refresh implementations for AI Studio, Gemini CLI, Gemini API
(API key), and Vertex executors to short‑circuit and simply return the
incoming auth object, while keeping Antigravity token renewal as the
only executor that performs OAuth refresh.

Remove OAuth2-based token refresh logic and related dependencies from
the Gemini API executor, since it now operates strictly with API key
credentials.
2025-12-11 21:56:43 +08:00
Luis Pater a74ee3f319 Merge pull request #481 from sususu98/fix/increase-buffer-size
fix: increase buffer size for stream scanners to 50MB across multiple executors
2025-12-11 21:20:54 +08:00
hkfires e79f65fd8e refactor(thinking): use parentheses for metadata suffix 2025-12-11 18:39:07 +08:00
hkfires facfe7c518 refactor(thinking): use bracket tags for thinking meta
Align thinking suffix handling on a single bracket-style marker.

NormalizeThinkingModel strips a terminal `[value]` segment from
model identifiers and turns it into either a thinking budget (for
numeric values) or a reasoning effort hint (for strings). Emission
of `ThinkingIncludeThoughtsMetadataKey` is removed.

Executor helpers and the example config are updated so their
comments reference the new `[value]` suffix format instead of the
legacy dash variants.

BREAKING CHANGE: dash-based thinking suffixes (`-thinking`,
`-thinking-N`, `-reasoning`, `-nothinking`) are no longer parsed
for thinking metadata; only `[value]` annotations are recognized.
2025-12-11 18:17:28 +08:00
hkfires 6285459c08 fix(runtime): unify claude thinking config resolution 2025-12-11 17:20:44 +08:00
hkfires 21bbceca0c docs(runtime): document reasoning effort precedence 2025-12-11 16:35:36 +08:00