Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input

# Conflicts: # docs/architecture.i18n.yaml # docs/architecture.md # docs/architecture.zh.md # docs/config-catalog.md # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/llm-streaming.i18n.yaml # docs/module-graph.md # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # packages/README.i18n.yaml # packages/client/connection/src/client/fixture.ts # packages/client/connection/src/index.ts # packages/client/runtime/README.i18n.yaml # packages/client/runtime/README.md # packages/client/runtime/README.zh.md # packages/client/runtime/src/client/sessions/conversation.ts # packages/client/ui-conversation/README.i18n.yaml # packages/client/ui-conversation/src/client/apply.ts # packages/client/ui-conversation/src/client/chat/ChatView.tsx # packages/client/ui-conversation/src/client/chat/MessageItem.tsx # packages/client/ui-conversation/src/client/contract/slots.ts # packages/client/ui-trajectory/tests/views.spec.tsx # packages/compact/compact-basic/README.i18n.yaml # packages/cordis/tool-cordis/src/api-catalog.ts # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/api/index.ts # packages/host/apiproxy/src/api/sessions.ts # packages/host/apiproxy/src/index.ts # packages/host/apiproxy/tests/fetch-carrier.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-deepseek/tests/adapter.spec.ts # packages/llm/llm-deepseek/tests/serialize.spec.ts # packages/llm/llm-pi-ai/README.i18n.yaml # packages/llm/llm-pi-ai/src/adapter.ts # packages/llm/llm-pi-ai/src/index.ts # packages/llm/llm-pi-ai/tests/adapter.spec.ts # packages/llm/llm/src/types.ts # packages/ui/tui/README.i18n.yaml # packages/ui/tui/src/index.ts # packages/ui/tui/tests/tui.spec.ts
2026-07-28 11:41:40 +08:00
parent a1835c3228 2a46685414
commit 004f598917
1499 changed files with 48621 additions and 21956 deletions
@@ -111,6 +111,8 @@ export class BasicCompactService extends CompactService {
  readonly config: ResolvedConfig

  private readonly warnedPressureConfigTargets = new Set<string>()
+  private readonly overflowRetries = new WeakMap<Agent, number>()
+  private readonly overflowAgents = new WeakMap<Session, Agent>()

  constructor(ctx: Context, config: BasicCompactConfig = {}) {
    super(ctx)
@@ -119,8 +121,8 @@ export class BasicCompactService extends CompactService {
  }

  /**
-   * Register the automatic post-step pressure and context-overflow recovery
-   * listeners. `compactIfNeeded` stays dynamically dispatched so subclass
+   * Register automatic between-step pressure and model-request overflow
+   * recovery. `compactIfNeeded` stays dynamically dispatched so subclass
   * overrides are honored at event time.
   */
  private _registerAutomaticCompaction(): void {
@@ -133,7 +135,7 @@ export class BasicCompactService extends CompactService {
      )
    }

-    ctx.on('agent/post-step', async (
+    ctx.on('agent/step', async (
      agent: Agent,
      _turn: number,
      _step: number,
@@ -142,35 +144,47 @@ export class BasicCompactService extends CompactService {
      if (signal.aborted) return
      try {
        const result = await this.compactIfNeeded(agent, 'pressure', signal)
-        if (result !== null) logResult(result, 'post-step pressure')
+        if (result !== null) logResult(result, 'step pressure')
      } catch (error: unknown) {
        if (error instanceof TargetPressureConfigError) {
          if (this.warnedPressureConfigTargets.has(error.targetKey)) return
          this.warnedPressureConfigTargets.add(error.targetKey)
        }
        const message = error instanceof Error ? error.message : String(error)
-        ctx.logger.warn(`post-step compaction failed: ${message}; continuing the turn`)
+        ctx.logger.warn(`step compaction failed: ${message}; continuing the turn`)
      }
    })

+    ctx.on('agent/settled', (agent) => {
+      this.overflowRetries.delete(agent)
+    })
+
+    // A successful response starts a fresh overflow-recovery sequence even
+    // when tool calls continue the same turn into another request.
+    ctx.on('session/event', (session, event) => {
+      if (event.type !== 'assistant/message') return
+      const agent = this.overflowAgents.get(session)
+      if (agent !== undefined) this.overflowRetries.delete(agent)
+    })
+
    ctx.on('agent/request-error', async (
      agent,
      _turn,
      _step,
      _error,
      failure,
-      priorFailures,
+      _priorFailures,
+      _retryPolicy,
      signal,
      next,
    ) => {
-      const priorOverflowFailures = priorFailures.filter(
-        item => item.code === CONTEXT_WINDOW_EXCEEDED_CODE,
-      ).length
      if (failure.code !== CONTEXT_WINDOW_EXCEEDED_CODE || signal.aborted) return next()
+      this.overflowAgents.set(agent.session, agent)
      const target = routedTarget(agent.session)
      if (target === undefined) return next()
      const policy = resolveTargetPolicy(this.config, target)
-      if (priorOverflowFailures >= policy.maxOverflowRetries) return next()
+      const retries = this.overflowRetries.get(agent) ?? 0
+      if (retries >= policy.maxOverflowRetries) return next()

      const generation = agent.session.surface.replaceGeneration
      let result: CompactionResult | null
@@ -181,27 +195,29 @@ export class BasicCompactService extends CompactService {
        // A model-free prune can land before later summary work fails. That
        // durable reduction is sufficient retry proof; do not discard it just
        // because the optional second phase threw. Cancellation still wins.
-        // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while recovery is awaited.
+        // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- the signal can abort while recovery is awaited.
        if (!signal.aborted && agent.session.surface.replaceGeneration > generation) {
          ctx.logger.warn(
            `context-overflow compaction failed after durable surface progress: ${message}; `
            + 'retrying from the replacement surface',
          )
-          return { action: 'retry' }
+          this.overflowRetries.set(agent, retries + 1)
+          return { kind: 'retry' }
        }
        ctx.logger.warn(
-          // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while recovery is awaited.
+          // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- the signal can abort while recovery is awaited.
          `context-overflow compaction failed: ${message}; ${signal.aborted
            ? 'cancellation prevents retry'
            : 'preserving the original request error'}`,
        )
        return next()
      }
-      // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while compaction is awaited.
+      // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- the signal can abort while compaction is awaited.
      if (signal.aborted
        || agent.session.surface.replaceGeneration <= generation) return next()
      if (result !== null) logResult(result, 'context overflow recovery')
-      return { action: 'retry' }
+      this.overflowRetries.set(agent, retries + 1)
+      return { kind: 'retry' }
    })
  }

@@ -228,12 +244,12 @@ export class BasicCompactService extends CompactService {
  }

  /**
-   * Compact for replayed post-step pressure or one provider-confirmed context
+   * Compact for replayed step-boundary pressure or one provider-confirmed context
   * overflow. Both triggers price the latest durable routed request envelope;
   * overflow bypasses the normal threshold and retained-tail policy so it can
   * force one useful balanced reduction.
   * @param agent - agent whose latest durable routed request is measured.
-   * @param trigger - normal post-step pressure or context-overflow recovery.
+   * @param trigger - normal step-boundary pressure or context-overflow recovery.
   * @param signal - live turn cancellation signal forwarded to summarization.
   * @returns the latest summary compaction result, or `null` when no summary ran.
   */
@@ -272,7 +288,7 @@ export class BasicCompactService extends CompactService {
      return this.compactRegion(range.start, range.end, agent, signal)
    }

-    const context = await this.ctx.llm.resolveModelContext(target.provider, target.model)
+    const context = (await this.ctx.llm.resolveModelInfo(target.provider, target.model, signal)).context
    const targetKey = `${target.provider}/${target.model}`
    if (context === undefined) {
      throw new TargetPressureConfigError(
@@ -177,10 +177,10 @@ export async function compactSurfaceRegion(

 /**
 * Reconstruct the last routed request's cacheable prefix for the shadowed
- * region: its system prompt and tool schemas, then the request-only message
- * prefix followed by the region's own derived messages in surface order. The
- * summarizer appends only the compaction instruction after this, so the call
- * is a genuine prefix of the conversation and reuses the provider's KV cache.
+ * region: its system prompt and tool schemas, then the region's own derived
+ * messages in surface order. The summarizer appends only the compaction
+ * instruction after this, so the call is a genuine prefix of the conversation
+ * and reuses the provider's KV cache.
 * @param session - session supplying the request header and per-node projection.
 * @param shadowedSeqs - the surface-node seqs, in order, being compacted.
 * @returns the replayed conversation prefix to condense.
@@ -199,7 +199,7 @@ function buildSummarizationInput(
  return {
    ...header?.system === undefined ? {} : { system: header.system },
    ...header?.tools === undefined ? {} : { tools: header.tools },
-    messages: [...header?.messagePrefix ?? [], ...regionMessages],
+    messages: regionMessages,
  }
 }

@@ -78,7 +78,7 @@ export interface SummarizationInput {
  readonly system?: string
  /** The conversation's tool schemas, reused for prefix-cache alignment; absent when the request carried none. */
  readonly tools?: readonly ToolSchema[]
-  /** The request prefix followed by the shadowed region, in surface order, that precedes the compaction instruction. */
+  /** The shadowed region, in surface order, that precedes the compaction instruction. */
  readonly messages: readonly Message[]
 }

@@ -38,7 +38,7 @@ export interface ModelCompactPolicyConfig extends CompactPolicyConfig {
 export interface BasicCompactConfig extends CompactPolicyConfig {
  /** Exact provider/model overrides; duplicate targets fail plugin load. */
  modelPolicies?: ModelCompactPolicyConfig[]
-  /** Enable automatic post-step pressure and overflow-recovery listeners. Defaults to `true`. */
+  /** Enable automatic step-boundary pressure and overflow-recovery listeners. Defaults to `true`. */
  auto?: boolean
 }