Merge branch 'master' into fix/subagent-depth-budget

packages/core/agent-loop/src/agent.ts

@@ -387,7 +387,7 @@ export class ReactLoopAgent implements Agent {
   [startDriver](): void {
     if (this._status === 'disposed') return
     this.driverStarted = true
-    this.done = this.loopCtx.agents.withInitiator(this, () => runLoop(this.loopCtx, this, {
+    this.done = this.loopCtx.agents.withInitiator(this, () => runLoop(this.loopCtx, {
       inbox: this.#inbox,
       maxParallelToolCalls: this.maxParallelToolCalls,
       setStatus: (status) => { this.setStatus(status) },

packages/core/agent-loop/src/loop.ts

@@ -19,7 +19,6 @@ import { renderPrompt } from '@deepseek-ai/dsh-system-prompt'
 import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt'
 import type {} from '@deepseek-ai/dsh-tools'
 import { executeToolCalls } from './tool-calls.ts'
-import type { ReactLoopAgent } from './agent.ts'
 import type { Inbox } from './inbox.ts'
 
 /** An Error with an optional machine-readable code (e.g., from LlmError or a throwing plugin). */
@@ -95,12 +94,17 @@ export interface LoopHandle {
 
 /**
  * Drive queued batches as durable turns until disposal. Plugin failures end the
- * current turn without terminating the driver.
- * @param ctx - the plugin context the loop reaches events (agent/…, session/flush) and services (systemPrompt, llm, tools) through.
- * @param agent - the agent this invocation drives for its whole lifetime (its inbox, session, and options).
+ * current turn without terminating the driver. The caller establishes the
+ * `ctx.agents.withInitiator()` boundary before entry; package-private
+ * orchestration recovers that exact Agent and captures its Session locally.
+ * @param ctx - the plugin context the loop reaches its initiating Agent,
+ * events (agent/…, session/flush), and services (systemPrompt, llm, tools)
+ * through.
  * @param handle - the bridge to the agent's mutable state: status/abort setters plus the disposal and cancel-marker reads.
+ * @throws when no initiating Agent is active.
  */
-export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopHandle): Promise<void> {
+export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> {
+  const agent = ctx.agents.requireInitiator()
   // Per-instance prefix and request-header state; conversation history remains in the session log.
   const transmission = createTransmissionLog()
 
@@ -138,7 +142,7 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH
     const turn = lastTurnNumber(session) + 1
     let terminalStopped = false
     try {
-      terminalStopped = await runTurn(ctx, events, agent, handle, turn, transmission)
+      terminalStopped = await runTurn(ctx, events, handle, turn, transmission)
     } catch (error: unknown) {
       // Pre-turn failure has no durable boundary to close; report it without appending outside a turn.
       const err = toError(error)
@@ -161,9 +165,17 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH
 }
 
 async function runTurn(
-  ctx: Context, events: AgentEventDispatch, agent: ReactLoopAgent, handle: LoopHandle, turn: number, transmission: TransmissionLog,
+  ctx: Context, events: AgentEventDispatch, handle: LoopHandle, turn: number, transmission: TransmissionLog,
 ): Promise<boolean> {
+  const agent = ctx.agents.requireInitiator()
   const { session } = agent
+  const drainSteering = (): boolean => {
+    const messages = handle.inbox.drainSteering()
+    for (const message of messages) {
+      session.append('steering/message', { turn, content: message.content, source: message.source }, { surfaceOp: 'append' })
+    }
+    return messages.length > 0
+  }
 
   // Drain before opening the turn, but append only after `turn/start`.
   const queued = handle.inbox.drainQueued()
@@ -262,7 +274,7 @@ async function runTurn(
 
       // Steering from the previous round's continuation listeners joins before
       // the request.
-      drainSteering(agent, handle.inbox, turn)
+      drainSteering()
 
       // The step's AbortController exists BEFORE any async pre-step work so a
       // dispose() or cancel() — in a synchronous turn-start listener or an
@@ -336,7 +348,7 @@ async function runTurn(
       let stepOutcome: { hadToolCalls: boolean; finish: FinishReason } | { error: Error }
       try {
         stepOutcome = await runStep(
-          ctx, events, agent, handle, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, abort.signal)
+          ctx, events, handle, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, abort.signal)
       } catch (error: unknown) {
         stepOutcome = { error: toError(error) }
       } finally {
@@ -365,7 +377,7 @@ async function runTurn(
       if (stepReason) reason = stepReason
 
       // Steering that arrived during streaming/tool execution.
-      const steered = drainSteering(agent, handle.inbox, turn)
+      const steered = drainSteering()
 
       closeStep()
 
@@ -454,15 +466,6 @@ async function runTurn(
   return terminalStopped
 }
 
-/** Drain the steering queue into the session. Returns whether any arrived. */
-function drainSteering(agent: ReactLoopAgent, inbox: Inbox, turn: number): boolean {
-  const messages = inbox.drainSteering()
-  for (const message of messages) {
-    agent.session.append('steering/message', { turn, content: message.content, source: message.source }, { surfaceOp: 'append' })
-  }
-  return messages.length > 0
-}
-
 /**
  * Run one committed step: transform call config, log the request header, build
  * the request from the cached prefix plus the step-boundary snapshot, stream and
@@ -472,7 +475,6 @@ function drainSteering(agent: ReactLoopAgent, inbox: Inbox, turn: number): boole
 async function runStep(
   ctx: Context,
   events: AgentEventDispatch,
-  agent: ReactLoopAgent,
   handle: LoopHandle,
   turn: number,
   step: number,
@@ -482,6 +484,7 @@ async function runStep(
   transmission: TransmissionLog,
   signal: AbortSignal,
 ): Promise<{ hadToolCalls: boolean; finish: FinishReason }> {
+  const agent = ctx.agents.requireInitiator()
   const { session, options } = agent
 
   // Seed the first request from agent options and later requests from the logged header;
@@ -538,15 +541,47 @@ async function runStep(
   const stepError = finishError(assembler.finish)
   if (stepError) throw stepError
 
+  const recordAssistantMessage = (
+    assembledContent: ContentBlock[],
+    message: Message,
+    preserveReplayState = true,
+  ): void => {
+    session.append(
+      'assistant/message',
+      {
+        turn,
+        step,
+        content: message.content,
+        provenance: assistantProvenance(
+          header.config,
+          assembler.replayState,
+          preserveReplayState && isDeepStrictEqual(message.content, assembledContent),
+        ),
+        ...assembler.usage === undefined ? {} : { usage: assembler.usage },
+      },
+      { surfaceOp: 'append', sourceEventSeqs: chunkSeqs },
+    )
+  }
+
+  // A rejected result still records the successful provider call without retaining rejected output.
+  const processStepResult = async (assembledContent: ContentBlock[], message: Message): Promise<Message> => {
+    try {
+      return await events.waterfall(
+        'agent/step-result', turn, step, message, () => Promise.resolve(message),
+      )
+    } catch (error: unknown) {
+      recordAssistantMessage(assembledContent, { ...message, content: [] }, false)
+      throw error
+    }
+  }
+
   if (assembler.finish.kind === 'max-tokens') {
     const assembled = assembler.message()
     const assembledContent = structuredClone(assembled.content)
     let message: Message = withoutToolCalls(assembled)
-    message = withoutToolCalls(await processStepResult(
-      events, session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs,
-    ))
+    message = withoutToolCalls(await processStepResult(assembledContent, message))
     // Preserve usage even when max-token truncation produced no content.
-    recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs)
+    recordAssistantMessage(assembledContent, message)
     return { hadToolCalls: false, finish: assembler.finish }
   }
 
@@ -554,86 +589,23 @@ async function runStep(
   const assembled = assembler.message()
   const assembledContent = structuredClone(assembled.content)
   let message: Message = assembled
-  message = await processStepResult(
-    events, session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs,
-  )
+  message = await processStepResult(assembledContent, message)
 
   // Every successful call records its completion anchor, including explicit
   // empty chunk provenance for a contentless, usage-less provider response.
-  recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs)
+  recordAssistantMessage(assembledContent, message)
 
   // Dispatch may overlap; policy, durable results, and result context stay model-ordered.
   const toolCalls = message.content.filter(block => block.type === 'tool-call')
   if (toolCalls.length === 0) return { hadToolCalls: false, finish: assembler.finish }
   return handle.withToolBatch(async (acceptContext) => {
     await executeToolCalls(
-      ctx, agent, turn, step, toolCalls, signal, handle.maxParallelToolCalls, acceptContext,
+      ctx, turn, step, toolCalls, signal, handle.maxParallelToolCalls, acceptContext,
     )
     return { hadToolCalls: true, finish: assembler.finish }
   })
 }
 
-/** Preserve successful-call accounting without retaining output that result processing rejected. */
-async function processStepResult(
-  events: AgentEventDispatch,
-  session: Session,
-  turn: number,
-  step: number,
-  config: LlmCallConfig,
-  assembledContent: ContentBlock[],
-  message: Message,
-  assembler: BlockAssembler,
-  chunkSeqs: number[],
-): Promise<Message> {
-  try {
-    return await events.waterfall(
-      'agent/step-result', turn, step, message, () => Promise.resolve(message),
-    )
-  } catch (error: unknown) {
-    recordAssistantMessage(
-      session,
-      turn,
-      step,
-      config,
-      assembledContent,
-      { ...message, content: [] },
-      assembler,
-      chunkSeqs,
-      false,
-    )
-    throw error
-  }
-}
-
-/** Record one content-or-usage assistant message with replay-safe provenance. */
-function recordAssistantMessage(
-  session: Session,
-  turn: number,
-  step: number,
-  config: LlmCallConfig,
-  assembledContent: ContentBlock[],
-  message: Message,
-  assembler: BlockAssembler,
-  chunkSeqs: number[],
-  preserveReplayState = true,
-): void {
-  session.append(
-    'assistant/message',
-    {
-      turn,
-      step,
-      content: message.content,
-      provenance: assistantProvenance(
-        config,
-        assembler.replayState,
-        preserveReplayState && isDeepStrictEqual(message.content, assembledContent),
-      ),
-      ...assembler.usage === undefined ? {} : { usage: assembler.usage },
-    },
-    { surfaceOp: 'append', sourceEventSeqs: chunkSeqs },
-  )
-}
-
 /** Build durable assistant provenance, dropping replay state after any content rewrite. */
 function assistantProvenance(config: LlmCallConfig, replayState: unknown, contentUnchanged: boolean): NonNullable<Message['provenance']> {
   return {

packages/core/agent-loop/src/tool-calls.ts

@@ -12,9 +12,7 @@
 import type { Context } from 'cordis'
 import { assertNever, type ToolCallBlock } from '@deepseek-ai/dsh-llm'
 import type { HookContext } from '@deepseek-ai/dsh-agent'
-import type { Session } from '@deepseek-ai/dsh-session'
 import { TOOL_REGISTRY_SCHEDULER, type ToolExecutionInput, type ToolExecutionMode, type ToolExecutionResult, type ToolRunContext } from '@deepseek-ai/dsh-tools'
-import type { ReactLoopAgent } from './agent.ts'
 
 /** One tool call after argument parsing, ready to schedule. */
 interface PlannedCall {
@@ -33,9 +31,10 @@ interface Slot {
  * Schedule one assistant step's tool calls by their live concurrency mode.
  * Started calls receive ordered results. Abort drains them and rethrows after
  * accepting their context into the batch FIFO owned by the caller.
+ * The committed step's AgentLoop driver boundary supplies the initiating Agent
+ * that becomes each explicit {@link ToolExecutionInput.agent}.
  *
- * @param ctx - loop context that owns the tool registry.
- * @param agent - agent and session receiving the call lifecycle.
+ * @param ctx - loop context that owns the tool registry and carries the initiating Agent.
  * @param turn - current turn number.
  * @param step - current step number.
  * @param toolCalls - assistant calls in model order.
@@ -45,7 +44,6 @@ interface Slot {
  */
 export async function executeToolCalls(
   ctx: Context,
-  agent: ReactLoopAgent,
   turn: number,
   step: number,
   toolCalls: ToolCallBlock[],
@@ -53,7 +51,7 @@ export async function executeToolCalls(
   maxParallel: number,
   acceptContext: (context: HookContext) => void,
 ): Promise<void> {
-  const { session } = agent
+  const agent = ctx.agents.requireInitiator()
 
   // Inputs are distinct because tools/execute wrappers may replace `exec.signal`.
   const planned: PlannedCall[] = toolCalls.map(block => ({
@@ -74,7 +72,7 @@ export async function executeToolCalls(
     const first = planned[next]!
     const mode = ctx.tools.executionMode(first.exec).kind
     const group = mode === 'parallel' ? planned.slice(next) : [first]
-    next += await runGroup(ctx, session, turn, step, group, mode, signal, maxParallel, acceptContext)
+    next += await runGroup(ctx, turn, step, group, mode, signal, maxParallel, acceptContext)
   }
 }
 
@@ -96,7 +94,6 @@ function parseArguments(raw: string): unknown {
  */
 async function runGroup(
   ctx: Context,
-  session: Session,
   turn: number,
   step: number,
   group: PlannedCall[],
@@ -105,6 +102,30 @@ async function runGroup(
   maxParallel: number,
   acceptContext: (context: HookContext) => void,
 ): Promise<number> {
+  const { session } = ctx.agents.requireInitiator()
+  const appendToolCall = (block: ToolCallBlock): number => {
+    return session.append('tool/call', {
+      turn,
+      step,
+      callId: block.id,
+      name: block.name,
+      arguments: block.arguments,
+    }).seq
+  }
+  const appendToolResult = (block: ToolCallBlock, result: ToolExecutionResult, callSeq: number): void => {
+    session.append('tool/result', {
+      turn,
+      step,
+      // Correlation stays with the loop's authoritative model-transcript call id;
+      // registry results deliberately do not duplicate it.
+      callId: block.id,
+      content: result.content,
+      isError: result.isError,
+      ...result.error ? { error: result.error } : {},
+      // Persist presentation payloads so UI bridges reproduce result cards on replay.
+      ...result.meta !== undefined ? { meta: result.meta } : {},
+    }, { surfaceOp: 'append', sourceEventSeqs: [callSeq] })
+  }
   /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */
   if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted'))
   const slots: (Slot | undefined)[] = group.map(() => undefined)
@@ -125,7 +146,7 @@ async function runGroup(
         ? await ctx.tools[TOOL_REGISTRY_SCHEDULER].finalize(slot.exec, slot.result)
         : ctx.tools[TOOL_REGISTRY_SCHEDULER].finish(slot.exec, slot.result)
       // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded index
-      appendToolResult(session, turn, step, call!.block, result, callSeqs[committed]!)
+      appendToolResult(call!.block, result, callSeqs[committed]!)
       for (const context of result.additionalContexts ?? []) acceptContext(context)
       committed++
     }
@@ -136,7 +157,7 @@ async function runGroup(
   const startCall = async (index: number): Promise<void> => {
     // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded index
     const call = group[index]!
-    callSeqs[index] = appendToolCall(session, turn, step, call.block)
+    callSeqs[index] = appendToolCall(call.block)
     started++
     const prepared = await ctx.tools[TOOL_REGISTRY_SCHEDULER].prepare(call.exec)
     switch (prepared.kind) {
@@ -198,32 +219,3 @@ async function runGroup(
   if (committed !== started) throw new Error('tool-call scheduler: uncommitted settled calls')
   return started
 }
-
-/** Append a started call and return its provenance sequence. */
-function appendToolCall(session: Session, turn: number, step: number, block: ToolCallBlock): number {
-  const event = session.append('tool/call', { turn, step, callId: block.id, name: block.name, arguments: block.arguments })
-  return event.seq
-}
-
-/** Append a model-ordered result linked to its call event. */
-function appendToolResult(
-  session: Session,
-  turn: number,
-  step: number,
-  block: ToolCallBlock,
-  result: ToolExecutionResult,
-  callSeq: number,
-): void {
-  session.append('tool/result', {
-    turn, step,
-    // Correlation stays with the loop's authoritative model-transcript call id;
-    // registry results deliberately do not duplicate it.
-    callId: block.id,
-    content: result.content,
-    isError: result.isError,
-    ...result.error ? { error: result.error } : {},
-    // The tool's private presentation payload (e.g. a result-time diff),
-    // persisted so a UI bridge reproduces the card on replay.
-    ...result.meta !== undefined ? { meta: result.meta } : {},
-  }, { surfaceOp: 'append', sourceEventSeqs: [callSeq] })
-}