Resolve compaction policy per routed model

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

@@ -544,7 +544,7 @@ 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 Agent Note), 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#L43)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L50)
 
 ## 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#L97)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L118)
 
 ### ctx.llm.registerAdapter(providers, adapter)
 
@@ -29,7 +29,7 @@ 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#L112)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L133)
 
 ### ctx.llm.listProviders()
 
@@ -45,7 +45,7 @@ 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#L143)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L164)
 
 ### ctx.llm.listModels(provider)
 
@@ -65,7 +65,30 @@ 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#L153)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L174)
+
+### ctx.llm.resolveModelContext(provider, model)
+
+```ts website-api
+/**
+ * Resolve context capacity from the adapter that owns one exact route.
+ * This query is independent of the advisory model catalog: an unlisted model
+ * may return metadata, while `undefined` never rejects later routing.
+ * @param provider - registered provider route to inspect.
+ * @param model - exact model id passed to the adapter.
+ * @returns detached context metadata, or `undefined` when the adapter has none.
+ */
+async resolveModelContext( provider: string, model: string, ): Promise<LlmModelContext | undefined>
+```
+
+Resolve context capacity from the adapter that owns one exact route. This query is independent of the advisory model catalog: an unlisted model may return metadata, while `undefined` never rejects later routing.
+
+- `provider` — registered provider route to inspect.
+- `model` — exact model id passed to the adapter.
+
+**Returns** detached context metadata, or `undefined` when the adapter has none.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L209)
 
 ### ctx.llm.stream(options)
 
@@ -91,4 +114,4 @@ Stream one model call as raw chunks (token-level deltas). Throws `LlmError` with
 
 **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#L264)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L308)

website/zh-CN/api/harness/token-meter.md

@@ -6,18 +6,7 @@
 
 Replay owner for one service-wide estimator and isolated per-session folds.
 
-[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/token-meter/src/index.ts#L106)
-
-### ctx.tokenMeter.contextWindow
-
-```ts website-api
-/** Provider context-window capacity used by pressure consumers. */
-readonly contextWindow: number
-```
-
-Provider context-window capacity used by pressure consumers.
-
-[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/token-meter/src/index.ts#L112)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/token-meter/src/index.ts#L82)
 
 ### ctx.tokenMeter.measure(session, requestHeader?)
 
@@ -50,7 +39,7 @@ Provider usage is reused only when the latest successful call's canonical reques
 
 **Returns** a detached deeply immutable pressure and surface measurement.
 
-[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/token-meter/src/index.ts#L143)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/token-meter/src/index.ts#L114)
 
 ### ctx.tokenMeter.estimateMessage(message)
 
@@ -69,4 +58,4 @@ Heuristically price one model-visible message.
 
 **Returns** content and role-framing tokens under the fixed service heuristic.
 
-[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/token-meter/src/index.ts#L181)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/token-meter/src/index.ts#L152)