admin343/browser
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

功能修改

Browse Source
This commit is contained in:
npc0-hue
2026-07-20 16:42:33 +08:00
parent 48b8ad8d6c
commit a0e69417db
224 changed files with 22015 additions and 884 deletions
Download Patch File Download Diff File Expand all files Collapse all files
platform/protocol/ai-provider-contracts.md
+4 -2
View File
@@ -32,8 +32,10 @@ AI invocation responses must be bounded and must not include raw provider creden
- `AIProviderCreateRequest`: create provider metadata with `apiKeyRef`, never raw key material.
- `AIProviderUpdateRequest`: replace editable provider metadata while preserving status through the service layer.
- `AIProviderStatusRequest`: set provider status to `active` or `disabled`.
- `AIProviderResponse`: redacted provider response with `apiKeyConfigured` only; it does not expose the stored secret reference.
- `AIProviderResponse`: redacted provider response with `apiKeyConfigured` and `baseUrlConfigured` only; it does not expose the stored secret reference or provider endpoint.
- `AIProviderTestResponse`: local metadata validation result with `mode=metadata`; live external connectivity is deferred.
- `AIProviderModelsResponse`: configured model list and default model, without credentials.
Management endpoints must reject raw key-shaped values in `apiKeyRef`. Platform-mediated AI invocation is implemented through the platform service boundary; live external connectivity tests and remote model discovery are deferred to later changes.
Management endpoints reject raw key-shaped values in `apiKeyRef`. In `live` mode Platform resolves `env://NAME` or `secret://providers/<id>` inside the service boundary and invokes OpenAI-compatible, OpenAI, Claude, Gemini, Ollama, or custom HTTP providers with bounded requests. Local debug uses explicit `mock` mode.
Provider failures create redacted audit/alert evidence and return a stable safe error without URL, header, key, request-body secret, or stack details. Config suggestions persist `AIConfigDiffPreview` with actor/server/plugin/provider/model, config version/checksum, expiry, and proposed content. Only `POST /api/v1/ai/config-diffs/{id}/approve` may dispatch the matching `config.write` job, and stale/expired/mismatched approvals are rejected.