Finessse
c5d64d807a
memory: normalize escaped todo/pinned text
2025-12-17 21:31:40 +07:00
Finessse
34082f2eef
middleware: pack state into last user message
2025-12-17 21:15:58 +07:00
Finessse
1d000affec
memory: add pinned+summary readers
2025-12-17 21:15:49 +07:00
Finessse
0a74cf7efb
middleware: inject persistent todo
2025-12-17 21:01:14 +07:00
Finessse
e1b9fa0a36
memory: add session todo file
2025-12-17 21:01:05 +07:00
Finessse
11b994cd14
memory: anchored summary + pinned context
2025-12-17 20:53:54 +07:00
Finessse
80e383098f
middleware: persist + retrieve trimmed history
2025-12-17 20:45:47 +07:00
Finessse
ce03ba863b
memory: add file-backed store
2025-12-17 20:45:13 +07:00
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.dev and Amp
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