sync update from LAN repo (source dhk-1 @ 3b1ec5b4)

This commit is contained in:
gozeros committed 2026-11-05 10:56:34 +08:00
1 parent da6521b6cb
commit 264e2200d6
995 files changed
+148105 -13399

No files matched your search

@@ -49,7 +49,6 @@ models:
use: deerflow.models.openai_codex_provider:CodexChatModel
model: gpt-5.4
supports_thinking: true
supports_reasoning_effort: true
- name: claude-sonnet-4.6
display_name: Claude Sonnet 4.6 (Claude Code OAuth)
@@ -59,6 +58,15 @@ models:
supports_thinking: true
```
Whether a model exposes the per-chat reasoning-effort selector is managed by
an administrator in **Model Management** and persisted in the
`model_capabilities` database table. For upgrade compatibility, a legacy
`supports_reasoning_effort: true` value is imported once at startup only when
that model has no database row. Existing database values (including `false`)
are never overwritten; after that first import the database is authoritative.
Remove the legacy YAML field when convenient. Model Management also removes it
the next time the model list is saved, and new configurations should not add it.
**Auth behavior for CLI-backed providers**:
- `CodexChatModel` loads Codex CLI auth from `~/.codex/auth.json`
- The Codex Responses endpoint currently rejects `max_tokens` and `max_output_tokens`, so `CodexChatModel` does not expose a request-level token cap