Preserve interrupted post-tool context

docs/core-data-structures/tools.md

@@ -151,10 +151,11 @@ interface ToolExecutionResult {
    * NEXT request (Claude Code's PostToolUse `additionalContext`). It is NOT part
    * of this call's `content` — `content`/`feedback` shape the tool RESULT, but
    * `additionalContext` is a SEPARATE `context/message`. A step can carry
-   * multiple tool calls, so the loop BUFFERS every call's `additionalContext`
-   * and appends them only AFTER all `tool/result`s for the step, keeping
-   * tool-call/result adjacency intact. Carried on the result purely to ferry it
-   * from `execute()` up to the loop's per-step buffer.
+   * multiple tool calls, so the loop accepts every call's `additionalContext`
+   * into the active-batch FIFO and appends it only when that batch settles. A
+   * successful batch places context AFTER all its `tool/result`s; an interrupted
+   * batch places it after every recorded result and before turn close. Carried
+   * on the result purely to ferry it from `execute()` up to that FIFO.
    */
   additionalContext?: HookContext
   /**

docs/rfc/implemented/feature/2026-06-30-interception-seams.md

@@ -36,7 +36,7 @@ Core dispatch and the tool body sit inside normalization boundaries, so tool, li
 
 1. **Open the turn before prompt policy.** A fully blocked batch becomes a zero-step `rejected` turn, preserving enclosure and giving ACP a durable terminal event. Every veto also records `prompt/blocked` with the original prompt and reason, so mixed batches retain blocked inputs. Allowed `additionalContext` is injected into the open turn.
 
-2. **Post-tool `additionalContext` is buffered and appended AFTER all `tool/result`s.** `content`/`feedback` shape the result `execute()` returns, but `additionalContext` is a SEPARATE `context/message`, and a single step can carry multiple tool calls. Appending context right after each result would interleave `result(c1) → context → result(c2)` and break tool-call/result adjacency. So `execute()` surfaces `additionalContext` on its `ToolExecutionResult`, and the loop buffers every per-call context for the step and appends them as `context/message`(s) only after every `tool/result` is appended.
+2. **Post-tool `additionalContext` enters the active-batch FIFO and appends when that batch settles.** `content`/`feedback` shape the result `execute()` returns, but `additionalContext` is a SEPARATE `context/message`, and a single step can carry multiple tool calls. Appending context right after each result would interleave `result(c1) → context → result(c2)` and break tool-call/result adjacency. So `execute()` surfaces `additionalContext` on its `ToolExecutionResult`; the loop accepts each context into the same FIFO as asynchronous injections, then appends the FIFO after the complete result batch on success or after every recorded result before an interrupted turn closes.
 
 3. **A forced `continue` `reason` is enqueued through the steering channel**, so the next step's top-of-loop drain records it as steering for the continued turn — next-*step* steering within the SAME turn, not a next-*turn* prompt (matching the existing `hasSteering` force-continue override).
 

docs/tool-execution-pipeline.md

@@ -20,9 +20,9 @@ flowchart TD
   owned["Tool-owned session events<br/><code>todo/write</code>, <code>fs/observed</code>, <code>hook/invoked</code>, <code>hook/result</code>, <code>tool/code-dispatch</code>"]
   post["<code>tools/post-execute</code> waterfall<br/>accept, block, replace, add context"]
   final["<code>tools/result</code> synchronous notification<br/>frozen authoritative outcome"]
-  context["Buffered additionalContext<br/>context/message after all tool results"]
+  context["Batch-deferred additionalContext<br/>context/message after recorded tool results"]
   toolResult["Session event: <code>tool/result</code><br/>single model-facing outcome"]
-  allResults["All calls in the step settled<br/>and tool/result events recorded"]
+  allResults["Tool batch settled<br/>recorded tool/result events complete"]
   presentResult["UI completed card<br/>presentResult(args, result)"]
   model --> toolCall
   toolCall --> presentCall

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

@@ -8,7 +8,7 @@
 
 import type { Context } from 'cordis'
 import { agentEvents } from '@deepseek-ai/dsh-agent'
-import type { AgentId, AgentOptions, AgentStatus, SendOptions } from '@deepseek-ai/dsh-agent'
+import type { AgentId, AgentOptions, AgentStatus, HookContext, SendOptions } from '@deepseek-ai/dsh-agent'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import { deepFreeze } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
@@ -288,11 +288,21 @@ export class ReactLoopAgent implements Agent {
     }
   }
 
-  /** Run one tool-call batch and drain its deferred context before resolving or rejecting. */
-  private async withToolBatch<T>(run: () => Promise<T>): Promise<T> {
+  /**
+   * Run one tool-call batch and drain its deferred context before settlement.
+   * The loop-owned acceptor remains valid after public disposal begins because
+   * the interrupted turn stays open until this batch settles.
+   */
+  private async withToolBatch<T>(
+    run: (acceptContext: (context: HookContext) => void) => Promise<T>,
+  ): Promise<T> {
     this.toolBatchActive = true
+    const acceptContext = (context: HookContext): void => {
+      const accepted = this.acceptMessage(context.content, { source: context.source })
+      this.deferredInjections.push(accepted)
+    }
     try {
-      return await run()
+      return await run(acceptContext)
     } finally {
       this.toolBatchActive = false
       this.drainDeferredInjections()

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

@@ -85,8 +85,8 @@ export interface LoopHandle {
   clearCancel(): void
   /** Settle idle waiters when pre-running cancellation skips a turn, without emitting `agent/status`. */
   settleIdle(): void
-  /** Run an active tool-call batch and drain deferred context before resolving or rejecting. */
-  readonly withToolBatch: <T>(run: () => Promise<T>) => Promise<T>
+  /** Run an active tool-call batch, accepting post-tool context into the FIFO drained before settlement. */
+  readonly withToolBatch: <T>(run: (acceptContext: (context: HookContext) => void) => Promise<T>) => Promise<T>
 }
 
 /**
@@ -559,9 +559,7 @@ async function runStep(
   // Tool execution stays sequential; recheck abort around each normalized result.
   const toolCalls = message.content.filter(block => block.type === 'tool-call')
   if (toolCalls.length === 0) return { hadToolCalls: false, finish: assembler.finish }
-  return handle.withToolBatch(async () => {
-    // Buffer context until all results are appended to preserve call/result adjacency.
-    const pendingContext: HookContext[] = []
+  return handle.withToolBatch(async (acceptContext) => {
     for (const call of toolCalls) {
       /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */
       if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted'))
@@ -591,7 +589,9 @@ async function runStep(
         // Persist tool-owned presentation data for replay.
         ...result.meta !== undefined ? { meta: result.meta } : {},
       }, { surfaceOp: 'append', sourceEventSeqs: [callEvent.seq] })
-      if (result.additionalContext) pendingContext.push(result.additionalContext)
+      // Accept into the batch FIFO immediately; it remains deferred until every
+      // result settles and survives abort, cancellation, or disposal afterward.
+      if (result.additionalContext) acceptContext(result.additionalContext)
       // The signal may flip while the tool is awaited.
       /* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */
       // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition
@@ -599,11 +599,6 @@ async function runStep(
       /* v8 ignore stop */
     }
 
-    // Append buffered context after the complete result batch.
-    for (const context of pendingContext) {
-      agent.inject(context.content, { source: context.source })
-    }
-
     return { hadToolCalls: true, finish: assembler.finish }
   })
 }

packages/core/agent-loop/tests/contract-regressions.spec.ts

@@ -3,7 +3,7 @@ import { Context } from 'cordis'
 import LlmService, { CallId, ContentBlock, MessageSource, StreamChunk } from '@deepseek-ai/dsh-llm'
 import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
-import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
+import ToolRegistry, { defineTool, type PostToolDecision } from '@deepseek-ai/dsh-tools'
 import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/dsh-agent'
 import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
 import { prepareReactLoopAgent } from '../src/agent.ts'
@@ -154,6 +154,13 @@ describe('abort during tool execution ends the turn', () => {
         return [{ type: 'text', text: 'done' }]
       },
     }))
+    ctx.on('tools/post-execute', async (): Promise<PostToolDecision> => ({
+      kind: 'accept',
+      additionalContext: {
+        content: [{ type: 'text', text: 'accepted result context after abort' }],
+        source: { kind: 'plugin', plugin: 'test' },
+      },
+    }))
 
     send(agent, 'go')
     await waitForIdle(ctx, agent)
@@ -163,9 +170,65 @@ describe('abort during tool execution ends the turn', () => {
       .filter(event => event.type === 'tool/result' || event.type === 'context/message'
         || event.type === 'step/end' || event.type === 'turn/end')
       .map(event => event.type))
-      .toEqual(['tool/result', 'context/message', 'step/end', 'turn/end'])
+      .toEqual(['tool/result', 'context/message', 'context/message', 'step/end', 'turn/end'])
+    expect(events
+      .filter(event => event.type === 'context/message')
+      .map(event => event.data.content))
+      .toEqual([
+        [{ type: 'text', text: 'accepted before abort' }],
+        [{ type: 'text', text: 'accepted result context after abort' }],
+      ])
+  })
+
+  it('records post-tool context when a later call aborts the batch', async () => {
+    const adapter = new MockAdapter([[
+      { type: 'block-start', index: 0, blockType: 'tool-call' },
+      { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('c1'), name: 'first', arguments: '{}' } },
+      { type: 'block-start', index: 1, blockType: 'tool-call' },
+      { type: 'block-end', index: 1, block: { type: 'tool-call', id: CallId('c2'), name: 'aborter', arguments: '{}' } },
+      { type: 'finish', reason: { kind: 'tool-calls' } },
+    ] satisfies StreamChunk[]])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(AgentId('a-later-abort-context'), { model: 'mock' })
+    ctx.tools.register(defineTool({
+      name: 'first',
+      description: '',
+      parameters: {},
+      async execute() {
+        return [{ type: 'text', text: 'first done' }]
+      },
+    }))
+    ctx.tools.register(defineTool({
+      name: 'aborter',
+      description: '',
+      parameters: {},
+      async execute() {
+        ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt')
+        return [{ type: 'text', text: 'aborted' }]
+      },
+    }))
+    ctx.on('tools/post-execute', async (exec, _result, next): Promise<PostToolDecision> => {
+      if (exec.callId !== CallId('c1')) return next()
+      return {
+        kind: 'accept',
+        additionalContext: {
+          content: [{ type: 'text', text: 'accepted after first result' }],
+          source: { kind: 'plugin', plugin: 'test' },
+        },
+      }
+    })
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+
+    const events = [...agent.session.events]
+    expect(events
+      .filter(event => event.type === 'tool/result' || event.type === 'context/message'
+        || event.type === 'step/end' || event.type === 'turn/end')
+      .map(event => event.type))
+      .toEqual(['tool/result', 'tool/result', 'context/message', 'step/end', 'turn/end'])
     expect(events.find(event => event.type === 'context/message')?.data.content)
-      .toEqual([{ type: 'text', text: 'accepted before abort' }])
+      .toEqual([{ type: 'text', text: 'accepted after first result' }])
   })
 
   it('drains deferred context before disposal reaches quiescence', async () => {
@@ -192,13 +255,25 @@ describe('abort during tool execution ends the turn', () => {
         return [{ type: 'text', text: 'done' }]
       },
     }))
+    ctx.on('tools/post-execute', async (): Promise<PostToolDecision> => ({
+      kind: 'accept',
+      additionalContext: {
+        content: [{ type: 'text', text: 'accepted result context during disposal' }],
+        source: { kind: 'plugin', plugin: 'test' },
+      },
+    }))
 
     send(agent, 'go')
     await started.promise
     await fiber.dispose()
 
-    expect(agent.session.events.find(event => event.type === 'context/message')?.data.content)
-      .toEqual([{ type: 'text', text: 'accepted before disposal' }])
+    expect(agent.session.events
+      .filter(event => event.type === 'context/message')
+      .map(event => event.data.content))
+      .toEqual([
+        [{ type: 'text', text: 'accepted before disposal' }],
+        [{ type: 'text', text: 'accepted result context during disposal' }],
+      ])
     expect(agent.session.events.find(event => event.type === 'turn/end')?.data.reason)
       .toEqual({ kind: 'disposed' })
   })

packages/core/tools/src/index.ts

@@ -238,8 +238,8 @@ export interface ToolExecutionResult {
    */
   error?: ToolErrorInfo
   /**
-   * Model-facing context for the next request, separate from this tool result.
-   * The loop buffers it until all step results are logged, preserving pairing.
+   * Model-facing context for the next request, separate from this tool result. The loop
+   * accepts it into the active-batch FIFO, then appends after recorded results even if interrupted.
    */
   additionalContext?: HookContext
   /**
@@ -843,7 +843,7 @@ export class ToolRegistry extends Service {
    * its {@link PostToolDecision}: `accept` keeps the call successful (replacing
    * `content` when given), `block` turns it into an `isError` whose content is
    * the corrective `feedback`. Either decision may attach `additionalContext`,
-   * which is ferried on the returned result for the loop's per-step buffer.
+   * which is ferried on the returned result for the loop's active-batch FIFO.
    * Runs inside `execute`'s outer try/catch (a throwing listener → isError).
    */
   private async postExecute(exec: ToolExecution, result: ToolExecutionResult): Promise<ToolExecutionResult> {

scripts/gen-doc-graphs.ts

@@ -850,9 +850,9 @@ function renderToolPipeline(): string {
     `  owned["Tool-owned session events<br/>${mermaidCode('todo/write')}, ${mermaidCode('fs/observed')}, ${mermaidCode('hook/invoked')}, ${mermaidCode('hook/result')}, ${mermaidCode('tool/code-dispatch')}"]`,
     `  post["${mermaidCode('tools/post-execute')} waterfall<br/>accept, block, replace, add context"]`,
     `  final["${mermaidCode('tools/result')} synchronous notification<br/>frozen authoritative outcome"]`,
-    '  context["Buffered additionalContext<br/>context/message after all tool results"]',
+    '  context["Batch-deferred additionalContext<br/>context/message after recorded tool results"]',
     `  toolResult["Session event: ${mermaidCode('tool/result')}<br/>single model-facing outcome"]`,
-    '  allResults["All calls in the step settled<br/>and tool/result events recorded"]',
+    '  allResults["Tool batch settled<br/>recorded tool/result events complete"]',
     '  presentResult["UI completed card<br/>presentResult(args, result)"]',
     '  model --> toolCall',
     '  toolCall --> presentCall',