Files
openclaw/src/auto-reply/reply/abort.test.ts
Tyler Yust b8f66c260d Agents: add nested subagent orchestration controls and reduce subagent token waste (#14447)
* Agents: add subagent orchestration controls

* Agents: add subagent orchestration controls (WIP uncommitted changes)

* feat(subagents): add depth-based spawn gating for sub-sub-agents

* feat(subagents): tool policy, registry, and announce chain for nested agents

* feat(subagents): system prompt, docs, changelog for nested sub-agents

* fix(subagents): prevent model fallback override, show model during active runs, and block context overflow fallback

Bug 1: When a session has an explicit model override (e.g., gpt/openai-codex),
the fallback candidate logic in resolveFallbackCandidates silently appended the
global primary model (opus) as a backstop. On reinjection/steer with a transient
error, the session could fall back to opus which has a smaller context window
and crash. Fix: when storedModelOverride is set, pass fallbacksOverride ?? []
instead of undefined, preventing the implicit primary backstop.

Bug 2: Active subagents showed 'model n/a' in /subagents list because
resolveModelDisplay only read entry.model/modelProvider (populated after run
completes). Fix: fall back to modelOverride/providerOverride fields which are
populated at spawn time via sessions.patch.

Bug 3: Context overflow errors (prompt too long, context_length_exceeded) could
theoretically escape runEmbeddedPiAgent and be treated as failover candidates
in runWithModelFallback, causing a switch to a model with a smaller context
window. Fix: in runWithModelFallback, detect context overflow errors via
isLikelyContextOverflowError and rethrow them immediately instead of trying the
next model candidate.

* fix(subagents): track spawn depth in session store and fix announce routing for nested agents

* Fix compaction status tracking and dedupe overflow compaction triggers

* fix(subagents): enforce depth block via session store and implement cascade kill

* fix: inject group chat context into system prompt

* fix(subagents): always write model to session store at spawn time

* Preserve spawnDepth when agent handler rewrites session entry

* fix(subagents): suppress announce on steer-restart

* fix(subagents): fallback spawned session model to runtime default

* fix(subagents): enforce spawn depth when caller key resolves by sessionId

* feat(subagents): implement active-first ordering for numeric targets and enhance task display

- Added a test to verify that subagents with numeric targets follow an active-first list ordering.
- Updated `resolveSubagentTarget` to sort subagent runs based on active status and recent activity.
- Enhanced task display in command responses to prevent truncation of long task descriptions.
- Introduced new utility functions for compacting task text and managing subagent run states.

* fix(subagents): show model for active runs via run record fallback

When the spawned model matches the agent's default model, the session
store's override fields are intentionally cleared (isDefault: true).
The model/modelProvider fields are only populated after the run
completes. This left active subagents showing 'model n/a'.

Fix: store the resolved model on SubagentRunRecord at registration
time, and use it as a fallback in both display paths (subagents tool
and /subagents command) when the session store entry has no model info.

Changes:
- SubagentRunRecord: add optional model field
- registerSubagentRun: accept and persist model param
- sessions-spawn-tool: pass resolvedModel to registerSubagentRun
- subagents-tool: pass run record model as fallback to resolveModelDisplay
- commands-subagents: pass run record model as fallback to resolveModelDisplay

* feat(chat): implement session key resolution and reset on sidebar navigation

- Added functions to resolve the main session key and reset chat state when switching sessions from the sidebar.
- Updated the `renderTab` function to handle session key changes when navigating to the chat tab.
- Introduced a test to verify that the session resets to "main" when opening chat from the sidebar navigation.

* fix: subagent timeout=0 passthrough and fallback prompt duplication

Bug 1: runTimeoutSeconds=0 now means 'no timeout' instead of applying 600s default
- sessions-spawn-tool: default to undefined (not 0) when neither timeout param
  is provided; use != null check so explicit 0 passes through to gateway
- agent.ts: accept 0 as valid timeout (resolveAgentTimeoutMs already handles
  0 → MAX_SAFE_TIMEOUT_MS)

Bug 2: model fallback no longer re-injects the original prompt as a duplicate
- agent.ts: track fallback attempt index; on retries use a short continuation
  message instead of the full original prompt since the session file already
  contains it from the first attempt
- Also skip re-sending images on fallback retries (already in session)

* feat(subagents): truncate long task descriptions in subagents command output

- Introduced a new utility function to format task previews, limiting their length to improve readability.
- Updated the command handler to use the new formatting function, ensuring task descriptions are truncated appropriately.
- Adjusted related tests to verify that long task descriptions are now truncated in the output.

* refactor(subagents): update subagent registry path resolution and improve command output formatting

- Replaced direct import of STATE_DIR with a utility function to resolve the state directory dynamically.
- Enhanced the formatting of command output for active and recent subagents, adding separators for better readability.
- Updated related tests to reflect changes in command output structure.

* fix(subagent): default sessions_spawn to no timeout when runTimeoutSeconds omitted

The previous fix (75a791106) correctly handled the case where
runTimeoutSeconds was explicitly set to 0 ("no timeout"). However,
when models omit the parameter entirely (which is common since the
schema marks it as optional), runTimeoutSeconds resolved to undefined.

undefined flowed through the chain as:
  sessions_spawn → timeout: undefined (since undefined != null is false)
  → gateway agent handler → agentCommand opts.timeout: undefined
  → resolveAgentTimeoutMs({ overrideSeconds: undefined })
  → DEFAULT_AGENT_TIMEOUT_SECONDS (600s = 10 minutes)

This caused subagents to be killed at exactly 10 minutes even though
the user's intent (via TOOLS.md) was for subagents to run without a
timeout.

Fix: default runTimeoutSeconds to 0 (no timeout) when neither
runTimeoutSeconds nor timeoutSeconds is provided by the caller.
Subagent spawns are long-running by design and should not inherit the
600s agent-command default timeout.

* fix(subagent): accept timeout=0 in agent-via-gateway path (second 600s default)

* fix: thread timeout override through getReplyFromConfig dispatch path

getReplyFromConfig called resolveAgentTimeoutMs({ cfg }) with no override,
always falling back to the config default (600s). Add timeoutOverrideSeconds
to GetReplyOptions and pass it through as overrideSeconds so callers of the
dispatch chain can specify a custom timeout (0 = no timeout).

This complements the existing timeout threading in agentCommand and the
cron isolated-agent runner, which already pass overrideSeconds correctly.

* feat(model-fallback): normalize OpenAI Codex model references and enhance fallback handling

- Added normalization for OpenAI Codex model references, specifically converting "gpt-5.3-codex" to "openai-codex" before execution.
- Updated the `resolveFallbackCandidates` function to utilize the new normalization logic.
- Enhanced tests to verify the correct behavior of model normalization and fallback mechanisms.
- Introduced a new test case to ensure that the normalization process works as expected for various input formats.

* feat(tests): add unit tests for steer failure behavior in openclaw-tools

- Introduced a new test file to validate the behavior of subagents when steer replacement dispatch fails.
- Implemented tests to ensure that the announce behavior is restored correctly and that the suppression reason is cleared as expected.
- Enhanced the subagent registry with a new function to clear steer restart suppression.
- Updated related components to support the new test scenarios.

* fix(subagents): replace stop command with kill in slash commands and documentation

- Updated the `/subagents` command to replace `stop` with `kill` for consistency in controlling sub-agent runs.
- Modified related documentation to reflect the change in command usage.
- Removed legacy timeoutSeconds references from the sessions-spawn-tool schema and tests to streamline timeout handling.
- Enhanced tests to ensure correct behavior of the updated commands and their interactions.

* feat(tests): add unit tests for readLatestAssistantReply function

- Introduced a new test file for the `readLatestAssistantReply` function to validate its behavior with various message scenarios.
- Implemented tests to ensure the function correctly retrieves the latest assistant message and handles cases where the latest message has no text.
- Mocked the gateway call to simulate different message histories for comprehensive testing.

* feat(tests): enhance subagent kill-all cascade tests and announce formatting

- Added a new test to verify that the `kill-all` command cascades through ended parents to active descendants in subagents.
- Updated the subagent announce formatting tests to reflect changes in message structure, including the replacement of "Findings:" with "Result:" and the addition of new expectations for message content.
- Improved the handling of long findings and stats in the announce formatting logic to ensure concise output.
- Refactored related functions to enhance clarity and maintainability in the subagent registry and tools.

* refactor(subagent): update announce formatting and remove unused constants

- Modified the subagent announce formatting to replace "Findings:" with "Result:" and adjusted related expectations in tests.
- Removed constants for maximum announce findings characters and summary words, simplifying the announcement logic.
- Updated the handling of findings to retain full content instead of truncating, ensuring more informative outputs.
- Cleaned up unused imports in the commands-subagents file to enhance code clarity.

* feat(tests): enhance billing error handling in user-facing text

- Added tests to ensure that normal text mentioning billing plans is not rewritten, preserving user context.
- Updated the `isBillingErrorMessage` and `sanitizeUserFacingText` functions to improve handling of billing-related messages.
- Introduced new test cases for various scenarios involving billing messages to ensure accurate processing and output.
- Enhanced the subagent announce flow to correctly manage active descendant runs, preventing premature announcements.

* feat(subagent): enhance workflow guidance and auto-announcement clarity

- Added a new guideline in the subagent system prompt to emphasize trust in push-based completion, discouraging busy polling for status updates.
- Updated documentation to clarify that sub-agents will automatically announce their results, improving user understanding of the workflow.
- Enhanced tests to verify the new guidance on avoiding polling loops and to ensure the accuracy of the updated prompts.

* fix(cron): avoid announcing interim subagent spawn acks

* chore: clean post-rebase imports

* fix(cron): fall back to child replies when parent stays interim

* fix(subagents): make active-run guidance advisory

* fix(subagents): update announce flow to handle active descendants and enhance test coverage

- Modified the announce flow to defer announcements when active descendant runs are present, ensuring accurate status reporting.
- Updated tests to verify the new behavior, including scenarios where no fallback requester is available and ensuring proper handling of finished subagents.
- Enhanced the announce formatting to include an `expectFinal` flag for better clarity in the announcement process.

* fix(subagents): enhance announce flow and formatting for user updates

- Updated the announce flow to provide clearer instructions for user updates based on active subagent runs and requester context.
- Refactored the announcement logic to improve clarity and ensure internal context remains private.
- Enhanced tests to verify the new message expectations and formatting, including updated prompts for user-facing updates.
- Introduced a new function to build reply instructions based on session context, improving the overall announcement process.

* fix: resolve prep blockers and changelog placement (#14447) (thanks @tyler6204)

* fix: restore cron delivery-plan import after rebase (#14447) (thanks @tyler6204)

* fix: resolve test failures from rebase conflicts (#14447) (thanks @tyler6204)

* fix: apply formatting after rebase (#14447) (thanks @tyler6204)
2026-02-14 22:03:45 -08:00

403 lines
12 KiB
TypeScript

import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { afterEach, describe, expect, it, vi } from "vitest";
import type { OpenClawConfig } from "../../config/config.js";
import {
getAbortMemory,
getAbortMemorySizeForTest,
isAbortTrigger,
resetAbortMemoryForTest,
setAbortMemory,
tryFastAbortFromMessage,
} from "./abort.js";
import { enqueueFollowupRun, getFollowupQueueDepth, type FollowupRun } from "./queue.js";
import { initSessionState } from "./session.js";
import { buildTestCtx } from "./test-ctx.js";
vi.mock("../../agents/pi-embedded.js", () => ({
abortEmbeddedPiRun: vi.fn().mockReturnValue(true),
resolveEmbeddedSessionLane: (key: string) => `session:${key.trim() || "main"}`,
}));
const commandQueueMocks = vi.hoisted(() => ({
clearCommandLane: vi.fn(),
}));
vi.mock("../../process/command-queue.js", () => commandQueueMocks);
const subagentRegistryMocks = vi.hoisted(() => ({
listSubagentRunsForRequester: vi.fn(() => []),
markSubagentRunTerminated: vi.fn(() => 1),
}));
vi.mock("../../agents/subagent-registry.js", () => ({
listSubagentRunsForRequester: subagentRegistryMocks.listSubagentRunsForRequester,
markSubagentRunTerminated: subagentRegistryMocks.markSubagentRunTerminated,
}));
describe("abort detection", () => {
afterEach(() => {
resetAbortMemoryForTest();
});
it("triggerBodyNormalized extracts /stop from RawBody for abort detection", async () => {
const root = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-abort-"));
const storePath = path.join(root, "sessions.json");
const cfg = { session: { store: storePath } } as OpenClawConfig;
const groupMessageCtx = {
Body: `[Context]\nJake: /stop\n[from: Jake]`,
RawBody: "/stop",
ChatType: "group",
SessionKey: "agent:main:whatsapp:group:g1",
};
const result = await initSessionState({
ctx: groupMessageCtx,
cfg,
commandAuthorized: true,
});
// /stop is detected via exact match in handleAbort, not isAbortTrigger
expect(result.triggerBodyNormalized).toBe("/stop");
});
it("isAbortTrigger matches bare word triggers (without slash)", () => {
expect(isAbortTrigger("stop")).toBe(true);
expect(isAbortTrigger("esc")).toBe(true);
expect(isAbortTrigger("abort")).toBe(true);
expect(isAbortTrigger("wait")).toBe(true);
expect(isAbortTrigger("exit")).toBe(true);
expect(isAbortTrigger("interrupt")).toBe(true);
expect(isAbortTrigger("hello")).toBe(false);
// /stop is NOT matched by isAbortTrigger - it's handled separately
expect(isAbortTrigger("/stop")).toBe(false);
});
it("removes abort memory entry when flag is reset", () => {
setAbortMemory("session-1", true);
expect(getAbortMemory("session-1")).toBe(true);
setAbortMemory("session-1", false);
expect(getAbortMemory("session-1")).toBeUndefined();
expect(getAbortMemorySizeForTest()).toBe(0);
});
it("caps abort memory tracking to a bounded max size", () => {
for (let i = 0; i < 2105; i += 1) {
setAbortMemory(`session-${i}`, true);
}
expect(getAbortMemorySizeForTest()).toBe(2000);
expect(getAbortMemory("session-0")).toBeUndefined();
expect(getAbortMemory("session-2104")).toBe(true);
});
it("fast-aborts even when text commands are disabled", async () => {
const root = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-abort-"));
const storePath = path.join(root, "sessions.json");
const cfg = { session: { store: storePath }, commands: { text: false } } as OpenClawConfig;
const result = await tryFastAbortFromMessage({
ctx: buildTestCtx({
CommandBody: "/stop",
RawBody: "/stop",
CommandAuthorized: true,
SessionKey: "telegram:123",
Provider: "telegram",
Surface: "telegram",
From: "telegram:123",
To: "telegram:123",
}),
cfg,
});
expect(result.handled).toBe(true);
});
it("fast-abort clears queued followups and session lane", async () => {
const root = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-abort-"));
const storePath = path.join(root, "sessions.json");
const cfg = { session: { store: storePath } } as OpenClawConfig;
const sessionKey = "telegram:123";
const sessionId = "session-123";
await fs.writeFile(
storePath,
JSON.stringify(
{
[sessionKey]: {
sessionId,
updatedAt: Date.now(),
},
},
null,
2,
),
);
const followupRun: FollowupRun = {
prompt: "queued",
enqueuedAt: Date.now(),
run: {
agentId: "main",
agentDir: path.join(root, "agent"),
sessionId,
sessionKey,
messageProvider: "telegram",
agentAccountId: "acct",
sessionFile: path.join(root, "session.jsonl"),
workspaceDir: path.join(root, "workspace"),
config: cfg,
provider: "anthropic",
model: "claude-opus-4-5",
timeoutMs: 1000,
blockReplyBreak: "text_end",
},
};
enqueueFollowupRun(
sessionKey,
followupRun,
{ mode: "collect", debounceMs: 0, cap: 20, dropPolicy: "summarize" },
"none",
);
expect(getFollowupQueueDepth(sessionKey)).toBe(1);
const result = await tryFastAbortFromMessage({
ctx: buildTestCtx({
CommandBody: "/stop",
RawBody: "/stop",
CommandAuthorized: true,
SessionKey: sessionKey,
Provider: "telegram",
Surface: "telegram",
From: "telegram:123",
To: "telegram:123",
}),
cfg,
});
expect(result.handled).toBe(true);
expect(getFollowupQueueDepth(sessionKey)).toBe(0);
expect(commandQueueMocks.clearCommandLane).toHaveBeenCalledWith(`session:${sessionKey}`);
});
it("fast-abort stops active subagent runs for requester session", async () => {
const root = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-abort-"));
const storePath = path.join(root, "sessions.json");
const cfg = { session: { store: storePath } } as OpenClawConfig;
const sessionKey = "telegram:parent";
const childKey = "agent:main:subagent:child-1";
const sessionId = "session-parent";
const childSessionId = "session-child";
await fs.writeFile(
storePath,
JSON.stringify(
{
[sessionKey]: {
sessionId,
updatedAt: Date.now(),
},
[childKey]: {
sessionId: childSessionId,
updatedAt: Date.now(),
},
},
null,
2,
),
);
subagentRegistryMocks.listSubagentRunsForRequester.mockReturnValueOnce([
{
runId: "run-1",
childSessionKey: childKey,
requesterSessionKey: sessionKey,
requesterDisplayKey: "telegram:parent",
task: "do work",
cleanup: "keep",
createdAt: Date.now(),
},
]);
const result = await tryFastAbortFromMessage({
ctx: buildTestCtx({
CommandBody: "/stop",
RawBody: "/stop",
CommandAuthorized: true,
SessionKey: sessionKey,
Provider: "telegram",
Surface: "telegram",
From: "telegram:parent",
To: "telegram:parent",
}),
cfg,
});
expect(result.stoppedSubagents).toBe(1);
expect(commandQueueMocks.clearCommandLane).toHaveBeenCalledWith(`session:${childKey}`);
});
it("cascade stop kills depth-2 children when stopping depth-1 agent", async () => {
const root = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-abort-"));
const storePath = path.join(root, "sessions.json");
const cfg = { session: { store: storePath } } as OpenClawConfig;
const sessionKey = "telegram:parent";
const depth1Key = "agent:main:subagent:child-1";
const depth2Key = "agent:main:subagent:child-1:subagent:grandchild-1";
const sessionId = "session-parent";
const depth1SessionId = "session-child";
const depth2SessionId = "session-grandchild";
await fs.writeFile(
storePath,
JSON.stringify(
{
[sessionKey]: {
sessionId,
updatedAt: Date.now(),
},
[depth1Key]: {
sessionId: depth1SessionId,
updatedAt: Date.now(),
},
[depth2Key]: {
sessionId: depth2SessionId,
updatedAt: Date.now(),
},
},
null,
2,
),
);
// First call: main session lists depth-1 children
// Second call (cascade): depth-1 session lists depth-2 children
// Third call (cascade from depth-2): no further children
subagentRegistryMocks.listSubagentRunsForRequester
.mockReturnValueOnce([
{
runId: "run-1",
childSessionKey: depth1Key,
requesterSessionKey: sessionKey,
requesterDisplayKey: "telegram:parent",
task: "orchestrator",
cleanup: "keep",
createdAt: Date.now(),
},
])
.mockReturnValueOnce([
{
runId: "run-2",
childSessionKey: depth2Key,
requesterSessionKey: depth1Key,
requesterDisplayKey: depth1Key,
task: "leaf worker",
cleanup: "keep",
createdAt: Date.now(),
},
])
.mockReturnValueOnce([]);
const result = await tryFastAbortFromMessage({
ctx: buildTestCtx({
CommandBody: "/stop",
RawBody: "/stop",
CommandAuthorized: true,
SessionKey: sessionKey,
Provider: "telegram",
Surface: "telegram",
From: "telegram:parent",
To: "telegram:parent",
}),
cfg,
});
// Should stop both depth-1 and depth-2 agents (cascade)
expect(result.stoppedSubagents).toBe(2);
expect(commandQueueMocks.clearCommandLane).toHaveBeenCalledWith(`session:${depth1Key}`);
expect(commandQueueMocks.clearCommandLane).toHaveBeenCalledWith(`session:${depth2Key}`);
});
it("cascade stop traverses ended depth-1 parents to stop active depth-2 children", async () => {
subagentRegistryMocks.listSubagentRunsForRequester.mockReset();
subagentRegistryMocks.markSubagentRunTerminated.mockClear();
const root = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-abort-"));
const storePath = path.join(root, "sessions.json");
const cfg = { session: { store: storePath } } as OpenClawConfig;
const sessionKey = "telegram:parent";
const depth1Key = "agent:main:subagent:child-ended";
const depth2Key = "agent:main:subagent:child-ended:subagent:grandchild-active";
const now = Date.now();
await fs.writeFile(
storePath,
JSON.stringify(
{
[sessionKey]: {
sessionId: "session-parent",
updatedAt: now,
},
[depth1Key]: {
sessionId: "session-child-ended",
updatedAt: now,
},
[depth2Key]: {
sessionId: "session-grandchild-active",
updatedAt: now,
},
},
null,
2,
),
);
// main -> ended depth-1 parent
// depth-1 parent -> active depth-2 child
// depth-2 child -> none
subagentRegistryMocks.listSubagentRunsForRequester
.mockReturnValueOnce([
{
runId: "run-1",
childSessionKey: depth1Key,
requesterSessionKey: sessionKey,
requesterDisplayKey: "telegram:parent",
task: "orchestrator",
cleanup: "keep",
createdAt: now - 1_000,
endedAt: now - 500,
outcome: { status: "ok" },
},
])
.mockReturnValueOnce([
{
runId: "run-2",
childSessionKey: depth2Key,
requesterSessionKey: depth1Key,
requesterDisplayKey: depth1Key,
task: "leaf worker",
cleanup: "keep",
createdAt: now - 500,
},
])
.mockReturnValueOnce([]);
const result = await tryFastAbortFromMessage({
ctx: buildTestCtx({
CommandBody: "/stop",
RawBody: "/stop",
CommandAuthorized: true,
SessionKey: sessionKey,
Provider: "telegram",
Surface: "telegram",
From: "telegram:parent",
To: "telegram:parent",
}),
cfg,
});
// Should skip killing the ended depth-1 run itself, but still kill depth-2.
expect(result.stoppedSubagents).toBe(1);
expect(commandQueueMocks.clearCommandLane).toHaveBeenCalledWith(`session:${depth2Key}`);
expect(subagentRegistryMocks.markSubagentRunTerminated).toHaveBeenCalledWith(
expect.objectContaining({ runId: "run-2", childSessionKey: depth2Key }),
);
});
});