fix(llm): scope adapter failures to model calls

Replace the process-wide adapter-failure WeakSet with a per-call scope bound to the exact AsyncIterable returned by LlmService.stream(). Give every call a unique wrapper so waterfall middleware can reuse an iterable without sharing provenance.

Move agent-loop recovery classification to the model-stream boundary. Only the final adapter behind that exact call can become an agent/request-error; nested llm/stream calls remain ordinary outer middleware failures while preserving the original Error.

Cover nested calls, reused middleware iterables, and end-to-end agent-loop recovery. Update the package and RFC contracts, bilingual pairing record, and generated API and catalog references.

website/zh-CN/api/harness/events.md

@@ -342,7 +342,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t
 
 - `options` — the full request. A LOOP-built request arrives deep-frozen (mutation throws): its content is a pure function of the session log (the reconstructability RFC), so listeners read it, never rewrite it. A hand-built one-shot (compaction summarize) is the caller's own object and stays mutable here.
 
-[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L42)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L43)
 
 ## session/*
 

website/zh-CN/api/harness/llm.md

@@ -6,7 +6,7 @@
 
 The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall.
 
-[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L96)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L97)
 
 ### ctx.llm.registerAdapter(providers, adapter)
 
@@ -21,7 +21,7 @@ Register an adapter for the given provider routes. Throws `LlmError` with code `
 
 **Returns** the disposer that unregisters all of them.
 
-[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L111)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L112)
 
 ### ctx.llm.listProviders()
 
@@ -33,7 +33,7 @@ Describe provider routes with a registered adapter.
 
 **Returns** detached provider metadata in registration order.
 
-[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L142)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L143)
 
 ### ctx.llm.listModels(provider)
 
@@ -47,7 +47,7 @@ Discover models advertised by one registered provider. Catalog membership is adv
 
 **Returns** detached model metadata in adapter-preferred order.
 
-[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L152)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L153)
 
 ### ctx.llm.stream(options)
 
@@ -55,10 +55,10 @@ Discover models advertised by one registered provider. Catalog membership is adv
 stream(options: GenerateOptions): AsyncIterable<StreamChunk>
 ```
 
-Stream one model call as raw chunks (token-level deltas). Throws `LlmError` with code `NO_ADAPTER` if no adapter is registered for `options.provider`. Replay state is retained only when the same adapter instance owns its historical provider and the target provider. Final adapter selection, dispatch, and iteration failures retain their original Error identity and are tagged for narrow agent-loop request recovery; middleware failures remain untagged.
+Stream one model call as raw chunks (token-level deltas). Throws `LlmError` with code `NO_ADAPTER` if no adapter is registered for `options.provider`. Replay state is retained only when the same adapter instance owns its historical provider and the target provider. Final adapter selection, dispatch, and iteration failures retain their original Error identity and are tagged in a call-local scope for narrow agent-loop request recovery; middleware and nested-call failures remain untagged for the outer call.
 
 - `options` — the full request; `options.provider` selects the adapter.
 
 **Returns** the chunk stream, possibly wrapped by `llm/stream` listeners.
 
-[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L259)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L264)