chore(llm): trim retry default refactor

docs/subsystems/llm-streaming.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/subsystems/llm-streaming.md
-llm-streaming.md: c1d40bf3111bb534a5401506016256264b3767bf
-llm-streaming.zh.md: 04e753d486f667eb4a63ef33d41e7103c03f4914
+llm-streaming.md: c1b2ab5f1e0926864f25409c021691d078df9e0f
+llm-streaming.zh.md: 7bf04bf7a4a7de63d20eb67461842ff49f3b189d

docs/subsystems/llm-streaming.md

@@ -655,7 +655,7 @@ interface LlmCallConfigAdapterDefaults {
 
 ## Service and provider contracts
 
-`LlmAdapter` is the provider contract: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerRetryPolicy()` supplies a resolved provider policy; omission uses the shared normal defaults. `providerInfo()` and asynchronous `listModels()` feed `LlmRuntime.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. One asynchronous `resolveModel()` query returns exact model identity plus optional correctness-sensitive context capacity, an adapter-configured `defaultMaxTokens`, and ordered model-owned reasoning ids with an optional deployment default; absent fields mean unavailable metadata or provider-owned behavior, not invalid catalog membership. The resolver receives optional cancellation and must settle promptly after abort. `LlmRuntime.resolveModelInfo()` validates and detaches the aggregate. At the final adapter boundary, `resolveCallConfig()` materializes the output default only when `maxTokens` is absent and validates and materializes reasoning, so direct calls cannot bypass either configured behavior; direct dispatch captures one registration before awaiting that resolution. The agent loop instead uses `prepareCall()` to keep the same registration across model resolution, durable header logging, and dispatch, retain detached context metadata from that exact lookup, and report which config fields the adapter defaulted. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. AgentLoop observes a request attempt once the outer waterfall returns a stream handle; that limited boundary does not prove a lazy terminal adapter was constructed or began provider I/O. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. [architecture.md](../architecture.md#turn-flow) shows where `ctx.llm.stream()` and the `llm/stream` waterfall sit in one turn.
+`LlmAdapter` is the provider contract: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerRetryPolicy()` is captured per route with normal defaults, while `providerInfo()` and asynchronous `listModels()` feed `LlmRuntime.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. One asynchronous `resolveModel()` query returns exact model identity plus optional correctness-sensitive context capacity, an adapter-configured `defaultMaxTokens`, and ordered model-owned reasoning ids with an optional deployment default; absent fields mean unavailable metadata or provider-owned behavior, not invalid catalog membership. The resolver receives optional cancellation and must settle promptly after abort. `LlmRuntime.resolveModelInfo()` validates and detaches the aggregate. At the final adapter boundary, `resolveCallConfig()` materializes the output default only when `maxTokens` is absent and validates and materializes reasoning, so direct calls cannot bypass either configured behavior; direct dispatch captures one registration before awaiting that resolution. The agent loop instead uses `prepareCall()` to keep the same registration across model resolution, durable header logging, and dispatch, retain detached context metadata from that exact lookup, and report which config fields the adapter defaulted. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. AgentLoop observes a request attempt once the outer waterfall returns a stream handle; that limited boundary does not prove a lazy terminal adapter was constructed or began provider I/O. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. [architecture.md](../architecture.md#turn-flow) shows where `ctx.llm.stream()` and the `llm/stream` waterfall sit in one turn.
 
 ```ts type-equiv
 /** One model call whose config and adapter registration were resolved together. */
@@ -803,7 +803,7 @@ registerModelDiscovery( settingsNs: string, discover: (request: LlmModelDiscover
 async discoverModels( settingsNs: string, request: LlmModelDiscoveryRequest, ): Promise<LlmDiscoveredModel[]>
 
 /**
- * Read the retry policy captured when one provider route was registered.
+ * Resolve the retry policy captured when one provider route was registered.
  * @param provider - registered provider route to inspect.
  * @returns the provider-owned policy, with normal defaults already resolved.
  */

docs/subsystems/llm-streaming.zh.md

@@ -661,7 +661,7 @@ interface LlmCallConfigAdapterDefaults {
 
 ## 服务与提供方约定
 
-`LlmAdapter` 是提供方约定：创建子类、实现 `stream()`，再用 `ctx.llm.registerAdapter(providers, adapter)` 注册一个适配器实例。`GenerateOptions.provider` 选择已注册适配器；`GenerateOptions.model` 会传给该适配器，无需在生命周期启动时注册。重复提供方路由会原子失败。可选的 `providerRetryPolicy()` 提供解析后的提供方策略；省略时使用共享的 normal 默认值。`providerInfo()` 与异步 `listModels()` 方法则为 `LlmRuntime.listProviders()` / `listModels()` 提供分离的 selector 元数据。该目录仅供参考，不是请求白名单：适配器仍是权威，并可接受未列出的模型 id。单次异步 `resolveModel()` 查询返回确切模型身份，以及可选的对正确性敏感的上下文容量、适配器配置的 `defaultMaxTokens`、由模型持有的有序推理强度 ID 和可选的部署默认值；字段缺失表示元数据不可用或保留提供方持有的行为，而不表示目录成员关系无效。解析器会接收可选的取消信号，并且必须在信号中止后迅速完成结算。`LlmRuntime.resolveModelInfo()` 会校验聚合结果并返回分离值。在最终适配器边界，`resolveCallConfig()` 仅在 `maxTokens` 缺失时填入输出默认值，并校验和填入推理强度，因此直接调用也无法绕过任何一项已配置行为；直接分派会在等待解析前捕获一项适配器注册。agent loop 则使用 `prepareCall()`，使模型解析、请求头持久记录和分派全程使用同一项注册，保留来自同一次查询的分离上下文元数据，并报告适配器填入的配置字段。适配器查找发生在 `llm/stream` waterfall 的终端 continuation，因此 listener 可以在查找前短路调用，或路由一个可变的一次性请求。AgentLoop 在外层 waterfall 返回流句柄时观察到一次请求尝试；这个有限边界不能证明惰性终端适配器已构造完成或开始提供方 I/O。`block-start` / `block-end` 的 `index` 关联与 assembler 共同意味着适配器只需 emit 格式正确的分片——块重组不是每个适配器各自的问题。`ctx.llm.stream()` 与 `llm/stream` waterfall 在一个轮次中的位置见 [architecture.md](../architecture.md#turn-flow)。
+`LlmAdapter` 是提供方约定：创建子类、实现 `stream()`，再用 `ctx.llm.registerAdapter(providers, adapter)` 注册一个适配器实例。`GenerateOptions.provider` 选择已注册适配器；`GenerateOptions.model` 会传给该适配器，无需在生命周期启动时注册。重复提供方路由会原子失败。可选的 `providerRetryPolicy()` 会按路由捕获并填入 normal 默认值，`providerInfo()` 与异步 `listModels()` 方法则为 `LlmRuntime.listProviders()` / `listModels()` 提供分离的 selector 元数据。该目录仅供参考，不是请求白名单：适配器仍是权威，并可接受未列出的模型 id。单次异步 `resolveModel()` 查询返回确切模型身份，以及可选的对正确性敏感的上下文容量、适配器配置的 `defaultMaxTokens`、由模型持有的有序推理强度 ID 和可选的部署默认值；字段缺失表示元数据不可用或保留提供方持有的行为，而不表示目录成员关系无效。解析器会接收可选的取消信号，并且必须在信号中止后迅速完成结算。`LlmRuntime.resolveModelInfo()` 会校验聚合结果并返回分离值。在最终适配器边界，`resolveCallConfig()` 仅在 `maxTokens` 缺失时填入输出默认值，并校验和填入推理强度，因此直接调用也无法绕过任何一项已配置行为；直接分派会在等待解析前捕获一项适配器注册。agent loop 则使用 `prepareCall()`，使模型解析、请求头持久记录和分派全程使用同一项注册，保留来自同一次查询的分离上下文元数据，并报告适配器填入的配置字段。适配器查找发生在 `llm/stream` waterfall 的终端 continuation，因此 listener 可以在查找前短路调用，或路由一个可变的一次性请求。AgentLoop 在外层 waterfall 返回流句柄时观察到一次请求尝试；这个有限边界不能证明惰性终端适配器已构造完成或开始提供方 I/O。`block-start` / `block-end` 的 `index` 关联与 assembler 共同意味着适配器只需 emit 格式正确的分片——块重组不是每个适配器各自的问题。`ctx.llm.stream()` 与 `llm/stream` waterfall 在一个轮次中的位置见 [architecture.md](../architecture.md#turn-flow)。
 
 ```ts type-equiv
 /** One model call whose config and adapter registration were resolved together. */
@@ -809,7 +809,7 @@ registerModelDiscovery( settingsNs: string, discover: (request: LlmModelDiscover
 async discoverModels( settingsNs: string, request: LlmModelDiscoveryRequest, ): Promise<LlmDiscoveredModel[]>
 
 /**
- * Read the retry policy captured when one provider route was registered.
+ * Resolve the retry policy captured when one provider route was registered.
  * @param provider - registered provider route to inspect.
  * @returns the provider-owned policy, with normal defaults already resolved.
  */

packages/extensions/tool-cordis/src/api-catalog.ts

@@ -832,7 +832,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
       },
       {
         signature: 'providerRetryPolicy(provider: string): ResolvedRetryPolicy',
-        description: 'Read the retry policy captured when one provider route was registered.',
+        description: 'Resolve the retry policy captured when one provider route was registered.',
         parameters: [{ name: 'provider', description: 'registered provider route to inspect.' }],
         returns: 'the provider-owned policy, with normal defaults already resolved.',
       },

packages/llm/llm-deepseek/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/llm/llm-deepseek/README.md
-README.md: 65c17f504e74408b37518149007c006d3836c4c6
-README.zh.md: 217d00c66ff332b67546e3efca2025347c1d28e0
+README.md: 9bb28e6876b82c521341769123a8b2d0e5d98e09
+README.zh.md: 21c55cfa32bf68e0cac4c0bd72c94c86d955fc00

packages/llm/llm-deepseek/README.md

@@ -45,7 +45,7 @@ The same exact-model result exposes ordered `off`, `low`, `high`, and `max` effo
 
 `thinking: disabled` is a deployment lock that publishes only `off` with `off` as its default. Omitting `reasoningEffort` or configuring it as `off` is valid; configuring `low`, `high`, or `max` fails plugin loading, and a direct per-request attempt to enable thinking fails before network I/O. A request with `GenerateOptions.purpose: 'session-title'` also forces thinking disabled and omits the already-resolved effort, reserving its bounded output for visible title text without changing conversation or compaction defaults.
 
-`streamIdleTimeoutMs` bounds each outstanding provider read, including the initial `fetch`, without counting time the consumer spends between chunks. DeepSeek SSE comments rearm an outstanding read as transport activity but never become `StreamChunk` values or session-log events. One stable abort signal reaches the request and body reader for the whole call; expiry stops the transport and throws `LlmError('TIMEOUT')`, while an earlier caller abort throws `LlmError('ABORTED')`. The adapter makes exactly one provider request per `stream()` call; it registers the resolved provider policy, and `dsh-llm-retry` separately executes it at durable agent-step boundaries.
+`streamIdleTimeoutMs` bounds each outstanding provider read, including the initial `fetch`, without counting time the consumer spends between chunks. DeepSeek SSE comments rearm an outstanding read as transport activity but never become `StreamChunk` values or session-log events. One stable abort signal reaches the request and body reader for the whole call; expiry stops the transport and throws `LlmError('TIMEOUT')`, while an earlier caller abort throws `LlmError('ABORTED')`. The adapter makes exactly one provider request per `stream()` call; it registers the configured policy as provider metadata, and `dsh-llm-retry` separately executes it at durable agent-step boundaries.
 
 ## Dynamic configuration (settings + credentials)
 
@@ -54,7 +54,7 @@ Connection facts are not frozen at load. `resolveAdapterOptions` is the one expl
 - **`ctx.settings`** — the plugin registers the `llm-deepseek` namespace with this same `Config` schema and its `cordis.yml` entry as the composition `base`, so a `llm-deepseek:` section in the user settings document overrides any field without a restart. Without a mounted settings service the entry config alone drives the adapter, unchanged. A live settings snapshot that passes the schema but fails a beyond-schema bound (a duplicate catalog id, a broken thinking/effort pair) keeps the last good facts and logs the failure; the entry config itself still fails plugin load.
 - **`ctx.credentials`** — the API key resolves per stream call, from the *same* resolved snapshot that supplies the endpoint. Configuration carries only `apiKeyEnv`, never a literal key: the reference resolves through the credential seam, and without a mounted seam through the trusted environment layers. Because credential facts travel with the connection facts, a settings snapshot the resolver rejects contributes neither its endpoint nor its key: the whole previous generation keeps serving. Every resolved key is format-checked before use, so a value no HTTP header can carry is refused with `LlmError('INVALID_CREDENTIAL')` naming the failing entry point — never any part of the key — instead of surfacing as an opaque `fetch` `TypeError`. A request with no key anywhere fails with `MISSING_CREDENTIAL` naming every configuration entry point, while the route stays registered and the catalog stays browsable — first-run onboarding is "browse models, store the key, prompt again", with no restart between.
 
-The adapter-owned registration fact is the resolved retry policy: when its value changes, the plugin re-registers the route in place (same adapter instance, one synchronous section). `ctx.llm.providerRetryPolicy('deepseek-official')` therefore reports the current provider policy, including the shared five-retry normal default when configuration omits it.
+The one registration-captured fact is the retry policy: when its resolved value changes, the plugin re-registers the route in place (same adapter instance, one synchronous section), so `ctx.llm.providerRetryPolicy('deepseek-official')` always reports the current policy.
 
 The plugin also declares its route in the configurable-provider directory (`ctx.llm.listConfigurableProviders()`): provider `deepseek-official`, settings namespace `llm-deepseek`, empty settings path — the whole section is the profile. Configuration surfaces use that entry to offer this adapter alongside dormant pi-ai providers.
 

packages/llm/llm-deepseek/README.zh.md

@@ -45,7 +45,7 @@ harness LLM（大语言模型）seam 的 DeepSeek chat-completions 适配器：
 
 `thinking: disabled` 是部署锁定：它只公布 `off`，并以 `off` 为默认值。省略 `reasoningEffort` 或将其配置为 `off` 均有效；配置 `low`、`high` 或 `max` 会使插件加载失败，直接按请求启用思考也会在网络 I/O 前失败。携带 `GenerateOptions.purpose: 'session-title'` 的请求也会强制禁用思考并省略已解析的推理强度，将有界输出保留给可见标题文本，不改变会话或压缩（compaction）默认值。
 
-`streamIdleTimeoutMs` 会限制每次未完成提供方读取，包括初始 `fetch`，但不计入消费方在分片间花费的时间。DeepSeek SSE 注释会作为传输活动使尚未完成的读取重新布防，但绝不会成为 `StreamChunk` 值或会话日志事件。同一个稳定的 abort 信号会在整个调用期间传递给请求与 body reader；过期会停止传输并抛出 `LlmError('TIMEOUT')`，较早的调用方 abort 则抛出 `LlmError('ABORTED')`。适配器每次 `stream()` 调用恰好发起一次提供方请求；它会注册解析后的提供方策略，再由 `dsh-llm-retry` 在持久化的 agent（智能体）步骤边界单独执行该策略。
+`streamIdleTimeoutMs` 会限制每次未完成提供方读取，包括初始 `fetch`，但不计入消费方在分片间花费的时间。DeepSeek SSE 注释会作为传输活动使尚未完成的读取重新布防，但绝不会成为 `StreamChunk` 值或会话日志事件。同一个稳定的 abort 信号会在整个调用期间传递给请求与 body reader；过期会停止传输并抛出 `LlmError('TIMEOUT')`，较早的调用方 abort 则抛出 `LlmError('ABORTED')`。适配器每次 `stream()` 调用恰好发起一次提供方请求；它把已配置策略注册为提供方元数据，再由 `dsh-llm-retry` 在持久化的 agent（智能体）步骤边界单独执行该策略。
 
 ## 动态配置（settings + credentials）
 
@@ -54,7 +54,7 @@ harness LLM（大语言模型）seam 的 DeepSeek chat-completions 适配器：
 - **`ctx.settings`**——插件用同一份 `Config` schema 注册 `llm-deepseek` namespace，并以其 `cordis.yml` 条目为组合 `base`，因此用户设置文档中的 `llm-deepseek:` 分节可以免重启覆盖任何字段。未挂载 settings 服务时，仅由 entry 配置驱动适配器，行为不变。存活 settings 快照若通过 schema 却违反 schema 之外的约束（重复的 catalog id、无法成立的 thinking／推理强度组合），则保留最后可用事实并记录失败；entry 配置本身仍会使插件加载失败。
 - **`ctx.credentials`**——API 密钥按每次 stream 调用解析，取自与端点*同一*份解析后的快照。配置只携带 `apiKeyEnv`，从不携带字面密钥：该引用经凭据 seam 解析，未挂载 seam 时则经受信环境层解析。由于凭据事实与连接事实同行，被 resolver 拒绝的 settings 快照既不贡献自己的端点，也不贡献自己的密钥：整个先前世代继续服务。每个解析出的密钥在使用前都会被校验格式，因此 HTTP 标头无法承载的值会以 `LlmError('INVALID_CREDENTIAL')` 被拒绝，点名失败的入口，但绝不透露密钥的任何部分，而不是以语义不明的 `fetch` `TypeError` 形式浮现。任何地方都没有密钥的请求以 `MISSING_CREDENTIAL` 失败，并点名每个配置入口，同时路由保持注册、catalog 保持可浏览——首次运行的上手流程就是「浏览模型、存入密钥、再次发起提示」，中间无需任何重启。
 
-适配器拥有的注册事实是解析后的重试策略：其值变化时，插件会原地重新注册该路由（同一适配器实例、一个同步区段）。因此，`ctx.llm.providerRetryPolicy('deepseek-official')` 会报告当前提供方策略；省略配置时，其中包含共享的 normal 模式五次重试默认值。
+唯一在注册期捕获的事实是重试策略：其解析值变化时，插件原地重新注册该路由（同一适配器实例、一个同步区段），因此 `ctx.llm.providerRetryPolicy('deepseek-official')` 始终报告当前策略。
 
 该插件还会在可配置提供方目录（`ctx.llm.listConfigurableProviders()`）中声明自己的路由：提供方为 `deepseek-official`，settings namespace 为 `llm-deepseek`，settings path 为空——整个分节就是 profile。配置界面借助该条目，把本适配器与休眠的 pi-ai 提供方一并呈现。
 

packages/llm/llm-pi-ai/src/config.ts

@@ -294,8 +294,7 @@ function rejectRemovedFields(provider: string, source: PiAiProviderProfile): voi
  * Validate profiles and return a detached route-keyed map suitable for
  * per-request reads. This is the one explicit resolve step, so an omitted dict
  * resolves to the empty (dormant) route set here rather than through a hidden
- * fallback, and each route's models, retry policy, and pi-ai provider are
- * materialized once.
+ * fallback, and each route's models and pi-ai provider are materialized once.
  * @param providers - configured provider profiles keyed by route.
  * @returns validated profiles in configuration order.
  */

packages/llm/llm/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/llm/llm/README.md
-README.md: 1ff98b9103f434a0d3669b13eec291ec68ba55f7
-README.zh.md: 3e3683c3465d83125f455780c6a0104e3998fba5
+README.md: e6b3c4924ad4e7cf115abdbfb38d22d0f524e377
+README.zh.md: 51f034af632c19ca91c1d2f91a7c9c22714870e0

packages/llm/llm/README.md

@@ -21,7 +21,7 @@ Each provider adapter supplies its resolved route policy. Omitting provider conf
 - `ctx.llm.registerModelDiscovery(settingsNs: string, discover): () => void` Offer to interrogate provider endpoints for the settings namespace this plugin owns. One offer per namespace (`INVALID_DISCOVERY`/`DUPLICATE_DISCOVERY`), disposed with the calling fiber.
 - `ctx.llm.listModelDiscoveryNamespaces(): string[]` List the namespaces that can interrogate an endpoint, so a surface offers the action only where it works.
 - `ctx.llm.discoverModels(settingsNs: string, request: LlmModelDiscoveryRequest): Promise<LlmDiscoveredModel[]>` Ask one endpoint which models it advertises.
-- `ctx.llm.providerRetryPolicy(provider: string): ResolvedRetryPolicy` Return the provider-owned retry policy captured during registration, with normal defaults already resolved.
+- `ctx.llm.providerRetryPolicy(provider: string): ResolvedRetryPolicy` Return the provider-owned retry policy captured during registration, with normal defaults resolved.
 - `ctx.llm.listModels(provider: string): Promise<LlmModelInfo[]>` Discover the models one registered provider currently advertises.
 - `ctx.llm.resolveModelInfo(provider: string, model: string, signal?: AbortSignal): Promise<LlmResolvedModelInfo>` Resolve validated exact-model identity plus available context, output-default, and reasoning metadata from the owning adapter, with optional cancellation for asynchronous adapters.
 - `ctx.llm.resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<LlmCallConfig>` Validate an explicit effort and materialize adapter-configured call defaults without clamping.
@@ -32,7 +32,7 @@ Each provider adapter supplies its resolved route policy. Omitting provider conf
 
 Interrogating an endpoint is configuration-time work over a *draft*, keyed by settings namespace rather than by provider route — the provider a surface is adding does not exist yet, so there is no route to name. The request may still *name* a route it is editing, and an adapter that already describes that route answers from its own knowledge without a network call; `baseURL` is optional and one of the two is required. The request otherwise carries the endpoint, the protocol, and a credential the harness uses for that one interrogation and never stores — nothing here reads or writes settings or credentials, and the reply is candidate metadata a surface may offer for adoption, never a registered catalog. `LlmDiscoveredModel` makes every field but `id` optional because most provider listings disclose an id and nothing else; a surface adopting one still owes the capacities its adapter requires. Duplicate and unusable ids are dropped, an unserved namespace fails with `NO_DISCOVERY`, and a request naming neither a route nor an endpoint fails with `INVALID_DISCOVERY`.
 
-Provider and model metadata is a discovery surface, not a routing whitelist. `registerAdapter()` still owns provider exclusivity and captures each route's effective retry policy, while an adapter may accept model ids absent from `listModels()`; consumers must not reject a request because its model is unlisted. Returned selector metadata is detached and invalid or duplicate adapter entries fail with `INVALID_ADAPTER` or `INVALID_CATALOG`.
+Provider and model metadata is a discovery surface, not a routing whitelist. `registerAdapter()` still owns provider exclusivity and captures the adapter's retry policy for each route, while an adapter may accept model ids absent from `listModels()`; consumers must not reject a request because its model is unlisted. Returned selector metadata is detached and invalid or duplicate adapter entries fail with `INVALID_ADAPTER` or `INVALID_CATALOG`.
 
 Every topology commit point — adapter routes registering or disposing, directory entries appearing or withdrawing — emits the payload-free `llm/adapters-updated` event after the mutation, so consumers re-read `listProviders()`/`listModels()`/`listConfigurableProviders()` instead of polling. Observer failures are contained (logged, non-vetoing); only `INVARIANT`-coded failures rethrow after the fan-out.
 

packages/llm/llm/README.zh.md

@@ -21,7 +21,7 @@
 - `ctx.llm.registerModelDiscovery(settingsNs: string, discover): () => void` 为本插件拥有的 settings namespace 提供查询提供方端点的能力。每个 namespace 只能有一个（`INVALID_DISCOVERY`/`DUPLICATE_DISCOVERY`），并随调用 fiber dispose。
 - `ctx.llm.listModelDiscoveryNamespaces(): string[]` 列出可以询问端点的 namespace，让界面只在可用之处提供该动作。
 - `ctx.llm.discoverModels(settingsNs: string, request: LlmModelDiscoveryRequest): Promise<LlmDiscoveredModel[]>` 询问某个端点它公布了哪些模型。
-- `ctx.llm.providerRetryPolicy(provider: string): ResolvedRetryPolicy` 返回注册时捕获的提供方重试策略，其中 normal 默认值已经解析。
+- `ctx.llm.providerRetryPolicy(provider: string): ResolvedRetryPolicy` 返回注册时捕获的提供方自身的重试策略，并解析 normal 默认值。
 - `ctx.llm.listModels(provider: string): Promise<LlmModelInfo[]>` 发现某个已注册提供方当前公布的模型。
 - `ctx.llm.resolveModelInfo(provider: string, model: string, signal?: AbortSignal): Promise<LlmResolvedModelInfo>` 从拥有该精确路由的适配器中，解析并校验确切模型身份，以及可用上下文、输出默认值和推理（reasoning）元数据；异步适配器可选地支持取消。
 - `ctx.llm.resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<LlmCallConfig>` 校验显式推理强度，并填入适配器配置的调用默认值，但不自动调整。
@@ -32,7 +32,7 @@
 
 询问端点属于配置期针对**草稿**的操作，以 settings namespace 而非提供方路由为键——界面正在新增的提供方还不存在，也就没有路由可点名。但请求仍可**点名**它正在编辑的路由，而已经描述该路由的适配器会用自己的知识作答，无需联网；路由名称和 `baseURL` 至少需要提供一项。除此之外，请求携带端点、协议，以及一条 harness 只用于这一次询问、绝不存储的凭据。这里既不读取也不写入 settings 或 credentials；返回内容是界面可以提供给用户采纳的候选元数据，而不是已注册的 catalog。`LlmDiscoveredModel` 除 `id` 外每个字段都是可选的，因为大多数提供方列表只公布 id；采纳其中一条的界面仍要补上其适配器所需的容量。重复与不可用的 id 会被丢弃，无人服务的 namespace 以 `NO_DISCOVERY` 失败，既不点名路由也不给端点的请求以 `INVALID_DISCOVERY` 失败。
 
-提供方和模型元数据用于发现，不构成路由白名单。`registerAdapter()` 仍拥有提供方路由的排他性，并为每条路由捕获有效重试策略；适配器可以接受未出现在 `listModels()` 中的模型 id，消费方不得仅因模型未列出而拒绝请求。返回的 selector 元数据已分离；无效或重复的适配器条目会以 `INVALID_ADAPTER` 或 `INVALID_CATALOG` 失败。
+提供方和模型元数据用于发现，不构成路由白名单。`registerAdapter()` 仍拥有提供方路由的排他性，并为每条路由捕获适配器的重试策略；适配器可以接受未出现在 `listModels()` 中的模型 id，消费方不得仅因模型未列出而拒绝请求。返回的 selector 元数据已分离；无效或重复的适配器条目会以 `INVALID_ADAPTER` 或 `INVALID_CATALOG` 失败。
 
 每个拓扑提交点——适配器路由注册或 dispose、目录条目出现或撤回——都会在变更之后发出无载荷的 `llm/adapters-updated` 事件，消费方因此会重新读取 `listProviders()`/`listModels()`/`listConfigurableProviders()`，而不是轮询。观察者故障会被记录并隔离，不能否决变更；只有带 `INVARIANT` 码的故障会在通知完所有观察者后重新抛出。
 
@@ -48,7 +48,7 @@
 
 ### 扩展点
 
-- 继承 `LlmAdapter` 并调用 `ctx.llm.registerAdapter(providers, adapter)`，添加一条或多条提供方路由。`GenerateOptions.provider` 选择适配器；`GenerateOptions.model` 属于适配器，可以动态解析。覆盖 `providerRetryPolicy()` 可提供由提供方持有的恢复配置；覆盖 `providerInfo()` 和异步 `listModels()` 以公开 selector 元数据；精确身份、容量、输出默认值或可选推理强度可用时，实现 `resolveModel()`；异步解析器必须响应其可选的取消 signal。默认实现使用有界 normal 重试策略，将路由和模型 id 用作名称，不公布模型，也不返回容量、输出默认值或推理元数据。
+- 继承 `LlmAdapter` 并调用 `ctx.llm.registerAdapter(providers, adapter)`，添加一条或多条提供方路由。`GenerateOptions.provider` 选择适配器；`GenerateOptions.model` 属于适配器，可以动态解析。覆盖 `providerRetryPolicy()` 以提供由提供方定义的恢复配置，覆盖 `providerInfo()` 和异步 `listModels()` 以公开 selector 元数据；精确身份、容量、输出默认值或可选推理强度可用时，实现 `resolveModel()`；异步解析器必须响应其可选的取消 signal。默认实现使用有界的 normal 重试策略，将路由和模型 id 用作名称，不公布模型，也不返回容量、输出默认值或推理元数据。
 - 包装 `llm/stream` 时，通过 `ctx.on()` waterfall listener 实现缓存、日志或路由。包装层如果在已经发出分片后重试，就没有可持久记录的尝试边界；因此，随产品交付的 agent 重试策略改用 `agent/request-error`。
 
 ### 消息（`message.ts`）与内容块（`types.ts`）

packages/llm/llm/src/index.ts

@@ -288,6 +288,7 @@ export class LlmRuntime extends Service {
     string,
     (request: LlmModelDiscoveryRequest) => Promise<readonly LlmDiscoveredModel[]>
   >()
+
   constructor(ctx: Context) {
     super(ctx, 'llm')
   }
@@ -558,7 +559,7 @@ export class LlmRuntime extends Service {
   }
 
   /**
-   * Read the retry policy captured when one provider route was registered.
+   * Resolve the retry policy captured when one provider route was registered.
    * @param provider - registered provider route to inspect.
    * @returns the provider-owned policy, with normal defaults already resolved.
    */

packages/llm/llm/src/retry-policy.ts

@@ -1,5 +1,5 @@
 /**
- * Provider-route request-retry policy configuration and resolution.
+ * Provider-owned request-retry policy configuration and resolution.
  *
  * Adapters expose one resolved policy per registered provider route; the
  * optional dsh-llm-retry plugin executes it on the agent's failed-step extension point.
@@ -53,7 +53,7 @@ export interface AlwaysRetryPolicyConfig {
   backoff?: BackoffConfig
 }
 
-/** Model-request retry policy configuration for one provider route. */
+/** Provider-owned model-request retry policy configuration. */
 export type RetryPolicyConfig = NormalRetryPolicyConfig | AlwaysRetryPolicyConfig
 
 /** Fully resolved backoff shared by both retry modes. */
@@ -141,9 +141,9 @@ function resolveBackoff(config: BackoffConfig | undefined, path: string): Resolv
 }
 
 /**
- * Validate, default, and detach one retry policy.
+ * Validate, default, and detach one provider-owned retry policy.
  * @param config - optional provider configuration; omission selects normal defaults.
- * @param path - diagnostic path naming the configuration that owns the value.
+ * @param path - diagnostic path naming the provider config that owns the value.
  * @returns an immutable policy safe to capture in provider registration state.
  */
 export function resolveRetryPolicy(

packages/llm/llm/tests/service.spec.ts

@@ -203,7 +203,7 @@ describe('LlmRuntime', () => {
     expect(adapter.lastOptions?.messages[0]).toBe(message)
   })
 
-  it('captures provider-owned retry policies and defaults omitted policies', async () => {
+  it('captures provider-owned retry policy at registration and defaults omission', async () => {
     const configured = resolveRetryPolicy({ mode: 'always' }, 'test retryPolicy')
     const adapter = new class extends ScriptedAdapter {
       override providerRetryPolicy(provider: string) {