2026-01-23 18:32:32 +00:00
|
|
|
import fs from "node:fs/promises";
|
|
|
|
|
import { tmpdir } from "node:os";
|
|
|
|
|
import path from "node:path";
|
2026-01-08 01:09:13 +00:00
|
|
|
import { describe, expect, it, vi } from "vitest";
|
2026-02-16 23:20:16 -05:00
|
|
|
import { loadSessionStore, saveSessionStore, type SessionEntry } from "../../config/sessions.js";
|
2026-02-17 13:36:48 +09:00
|
|
|
import type { FollowupRun } from "./queue.js";
|
2026-01-08 01:09:13 +00:00
|
|
|
import { createMockTypingController } from "./test-helpers.js";
|
|
|
|
|
|
|
|
|
|
const runEmbeddedPiAgentMock = vi.fn();
|
|
|
|
|
|
|
|
|
|
vi.mock("../../agents/model-fallback.js", () => ({
|
|
|
|
|
runWithModelFallback: async ({
|
|
|
|
|
provider,
|
|
|
|
|
model,
|
|
|
|
|
run,
|
|
|
|
|
}: {
|
|
|
|
|
provider: string;
|
|
|
|
|
model: string;
|
|
|
|
|
run: (provider: string, model: string) => Promise<unknown>;
|
|
|
|
|
}) => ({
|
|
|
|
|
result: await run(provider, model),
|
|
|
|
|
provider,
|
|
|
|
|
model,
|
|
|
|
|
}),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
vi.mock("../../agents/pi-embedded.js", () => ({
|
|
|
|
|
runEmbeddedPiAgent: (params: unknown) => runEmbeddedPiAgentMock(params),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
import { createFollowupRunner } from "./followup-runner.js";
|
|
|
|
|
|
2026-01-08 08:49:16 +01:00
|
|
|
const baseQueuedRun = (messageProvider = "whatsapp"): FollowupRun =>
|
2026-01-08 01:09:13 +00:00
|
|
|
({
|
|
|
|
|
prompt: "hello",
|
|
|
|
|
summaryLine: "hello",
|
|
|
|
|
enqueuedAt: Date.now(),
|
2026-01-08 08:49:16 +01:00
|
|
|
originatingTo: "channel:C1",
|
2026-01-08 01:09:13 +00:00
|
|
|
run: {
|
|
|
|
|
sessionId: "session",
|
|
|
|
|
sessionKey: "main",
|
2026-01-08 08:49:16 +01:00
|
|
|
messageProvider,
|
|
|
|
|
agentAccountId: "primary",
|
2026-01-08 01:09:13 +00:00
|
|
|
sessionFile: "/tmp/session.jsonl",
|
|
|
|
|
workspaceDir: "/tmp",
|
|
|
|
|
config: {},
|
|
|
|
|
skillsSnapshot: {},
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
model: "claude",
|
|
|
|
|
thinkLevel: "low",
|
|
|
|
|
verboseLevel: "off",
|
|
|
|
|
elevatedLevel: "off",
|
|
|
|
|
bashElevated: {
|
|
|
|
|
enabled: false,
|
|
|
|
|
allowed: false,
|
|
|
|
|
defaultLevel: "off",
|
|
|
|
|
},
|
|
|
|
|
timeoutMs: 1_000,
|
|
|
|
|
blockReplyBreak: "message_end",
|
|
|
|
|
},
|
|
|
|
|
}) as FollowupRun;
|
|
|
|
|
|
2026-01-23 18:32:32 +00:00
|
|
|
describe("createFollowupRunner compaction", () => {
|
|
|
|
|
it("adds verbose auto-compaction notice and tracks count", async () => {
|
|
|
|
|
const storePath = path.join(
|
2026-01-30 03:15:10 +01:00
|
|
|
await fs.mkdtemp(path.join(tmpdir(), "openclaw-compaction-")),
|
2026-01-23 18:32:32 +00:00
|
|
|
"sessions.json",
|
|
|
|
|
);
|
|
|
|
|
const sessionEntry: SessionEntry = {
|
|
|
|
|
sessionId: "session",
|
|
|
|
|
updatedAt: Date.now(),
|
|
|
|
|
};
|
|
|
|
|
const sessionStore: Record<string, SessionEntry> = {
|
|
|
|
|
main: sessionEntry,
|
|
|
|
|
};
|
|
|
|
|
const onBlockReply = vi.fn(async () => {});
|
|
|
|
|
|
|
|
|
|
runEmbeddedPiAgentMock.mockImplementationOnce(
|
|
|
|
|
async (params: {
|
|
|
|
|
onAgentEvent?: (evt: { stream: string; data: Record<string, unknown> }) => void;
|
|
|
|
|
}) => {
|
|
|
|
|
params.onAgentEvent?.({
|
|
|
|
|
stream: "compaction",
|
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
|
|
|
data: { phase: "end", willRetry: true },
|
2026-01-23 18:32:32 +00:00
|
|
|
});
|
|
|
|
|
return { payloads: [{ text: "final" }], meta: {} };
|
|
|
|
|
},
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
const runner = createFollowupRunner({
|
|
|
|
|
opts: { onBlockReply },
|
|
|
|
|
typing: createMockTypingController(),
|
|
|
|
|
typingMode: "instant",
|
|
|
|
|
sessionEntry,
|
|
|
|
|
sessionStore,
|
|
|
|
|
sessionKey: "main",
|
|
|
|
|
storePath,
|
|
|
|
|
defaultModel: "anthropic/claude-opus-4-5",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const queued = {
|
|
|
|
|
prompt: "hello",
|
|
|
|
|
summaryLine: "hello",
|
|
|
|
|
enqueuedAt: Date.now(),
|
|
|
|
|
run: {
|
|
|
|
|
sessionId: "session",
|
|
|
|
|
sessionKey: "main",
|
|
|
|
|
messageProvider: "whatsapp",
|
|
|
|
|
sessionFile: "/tmp/session.jsonl",
|
|
|
|
|
workspaceDir: "/tmp",
|
|
|
|
|
config: {},
|
|
|
|
|
skillsSnapshot: {},
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
model: "claude",
|
|
|
|
|
thinkLevel: "low",
|
|
|
|
|
verboseLevel: "on",
|
|
|
|
|
elevatedLevel: "off",
|
|
|
|
|
bashElevated: {
|
|
|
|
|
enabled: false,
|
|
|
|
|
allowed: false,
|
|
|
|
|
defaultLevel: "off",
|
|
|
|
|
},
|
|
|
|
|
timeoutMs: 1_000,
|
|
|
|
|
blockReplyBreak: "message_end",
|
|
|
|
|
},
|
|
|
|
|
} as FollowupRun;
|
|
|
|
|
|
|
|
|
|
await runner(queued);
|
|
|
|
|
|
|
|
|
|
expect(onBlockReply).toHaveBeenCalled();
|
|
|
|
|
expect(onBlockReply.mock.calls[0][0].text).toContain("Auto-compaction complete");
|
|
|
|
|
expect(sessionStore.main.compactionCount).toBe(1);
|
|
|
|
|
});
|
2026-02-12 23:02:30 +00:00
|
|
|
|
|
|
|
|
it("updates totalTokens after auto-compaction using lastCallUsage", async () => {
|
|
|
|
|
const storePath = path.join(
|
|
|
|
|
await fs.mkdtemp(path.join(tmpdir(), "openclaw-followup-compaction-")),
|
|
|
|
|
"sessions.json",
|
|
|
|
|
);
|
|
|
|
|
const sessionKey = "main";
|
|
|
|
|
const sessionEntry: SessionEntry = {
|
|
|
|
|
sessionId: "session",
|
|
|
|
|
updatedAt: Date.now(),
|
|
|
|
|
totalTokens: 180_000,
|
|
|
|
|
compactionCount: 0,
|
|
|
|
|
};
|
|
|
|
|
const sessionStore: Record<string, SessionEntry> = { [sessionKey]: sessionEntry };
|
|
|
|
|
await saveSessionStore(storePath, sessionStore);
|
|
|
|
|
const onBlockReply = vi.fn(async () => {});
|
|
|
|
|
|
|
|
|
|
runEmbeddedPiAgentMock.mockImplementationOnce(
|
|
|
|
|
async (params: {
|
|
|
|
|
onAgentEvent?: (evt: { stream: string; data: Record<string, unknown> }) => void;
|
|
|
|
|
}) => {
|
|
|
|
|
params.onAgentEvent?.({
|
|
|
|
|
stream: "compaction",
|
|
|
|
|
data: { phase: "end", willRetry: false },
|
|
|
|
|
});
|
|
|
|
|
return {
|
|
|
|
|
payloads: [{ text: "done" }],
|
|
|
|
|
meta: {
|
|
|
|
|
agentMeta: {
|
|
|
|
|
// Accumulated usage across pre+post compaction calls.
|
|
|
|
|
usage: { input: 190_000, output: 8_000, total: 198_000 },
|
|
|
|
|
// Last call usage reflects post-compaction context.
|
|
|
|
|
lastCallUsage: { input: 11_000, output: 2_000, total: 13_000 },
|
|
|
|
|
model: "claude-opus-4-5",
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
},
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
const runner = createFollowupRunner({
|
|
|
|
|
opts: { onBlockReply },
|
|
|
|
|
typing: createMockTypingController(),
|
|
|
|
|
typingMode: "instant",
|
|
|
|
|
sessionEntry,
|
|
|
|
|
sessionStore,
|
|
|
|
|
sessionKey,
|
|
|
|
|
storePath,
|
|
|
|
|
defaultModel: "anthropic/claude-opus-4-5",
|
|
|
|
|
agentCfgContextTokens: 200_000,
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await runner(baseQueuedRun());
|
|
|
|
|
|
|
|
|
|
const store = loadSessionStore(storePath, { skipCache: true });
|
|
|
|
|
expect(store[sessionKey]?.compactionCount).toBe(1);
|
|
|
|
|
expect(store[sessionKey]?.totalTokens).toBe(11_000);
|
|
|
|
|
// We only keep the total estimate after compaction.
|
|
|
|
|
expect(store[sessionKey]?.inputTokens).toBeUndefined();
|
|
|
|
|
expect(store[sessionKey]?.outputTokens).toBeUndefined();
|
|
|
|
|
});
|
2026-01-23 18:32:32 +00:00
|
|
|
});
|
|
|
|
|
|
2026-01-08 01:09:13 +00:00
|
|
|
describe("createFollowupRunner messaging tool dedupe", () => {
|
|
|
|
|
it("drops payloads already sent via messaging tool", async () => {
|
|
|
|
|
const onBlockReply = vi.fn(async () => {});
|
|
|
|
|
runEmbeddedPiAgentMock.mockResolvedValueOnce({
|
|
|
|
|
payloads: [{ text: "hello world!" }],
|
|
|
|
|
messagingToolSentTexts: ["hello world!"],
|
|
|
|
|
meta: {},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const runner = createFollowupRunner({
|
|
|
|
|
opts: { onBlockReply },
|
|
|
|
|
typing: createMockTypingController(),
|
|
|
|
|
typingMode: "instant",
|
|
|
|
|
defaultModel: "anthropic/claude-opus-4-5",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await runner(baseQueuedRun());
|
|
|
|
|
|
|
|
|
|
expect(onBlockReply).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("delivers payloads when not duplicates", async () => {
|
|
|
|
|
const onBlockReply = vi.fn(async () => {});
|
|
|
|
|
runEmbeddedPiAgentMock.mockResolvedValueOnce({
|
|
|
|
|
payloads: [{ text: "hello world!" }],
|
|
|
|
|
messagingToolSentTexts: ["different message"],
|
|
|
|
|
meta: {},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const runner = createFollowupRunner({
|
|
|
|
|
opts: { onBlockReply },
|
|
|
|
|
typing: createMockTypingController(),
|
|
|
|
|
typingMode: "instant",
|
|
|
|
|
defaultModel: "anthropic/claude-opus-4-5",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await runner(baseQueuedRun());
|
|
|
|
|
|
|
|
|
|
expect(onBlockReply).toHaveBeenCalledTimes(1);
|
|
|
|
|
});
|
2026-01-08 08:49:16 +01:00
|
|
|
|
|
|
|
|
it("suppresses replies when a messaging tool sent via the same provider + target", async () => {
|
|
|
|
|
const onBlockReply = vi.fn(async () => {});
|
|
|
|
|
runEmbeddedPiAgentMock.mockResolvedValueOnce({
|
|
|
|
|
payloads: [{ text: "hello world!" }],
|
|
|
|
|
messagingToolSentTexts: ["different message"],
|
2026-01-14 14:31:43 +00:00
|
|
|
messagingToolSentTargets: [{ tool: "slack", provider: "slack", to: "channel:C1" }],
|
2026-01-08 08:49:16 +01:00
|
|
|
meta: {},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const runner = createFollowupRunner({
|
|
|
|
|
opts: { onBlockReply },
|
|
|
|
|
typing: createMockTypingController(),
|
|
|
|
|
typingMode: "instant",
|
|
|
|
|
defaultModel: "anthropic/claude-opus-4-5",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await runner(baseQueuedRun("slack"));
|
|
|
|
|
|
|
|
|
|
expect(onBlockReply).not.toHaveBeenCalled();
|
|
|
|
|
});
|
2026-01-24 11:04:53 +00:00
|
|
|
|
2026-02-16 20:08:27 +01:00
|
|
|
it("drops media URL from payload when messaging tool already sent it", async () => {
|
|
|
|
|
const onBlockReply = vi.fn(async () => {});
|
|
|
|
|
runEmbeddedPiAgentMock.mockResolvedValueOnce({
|
|
|
|
|
payloads: [{ mediaUrl: "/tmp/img.png" }],
|
|
|
|
|
messagingToolSentMediaUrls: ["/tmp/img.png"],
|
|
|
|
|
meta: {},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const runner = createFollowupRunner({
|
|
|
|
|
opts: { onBlockReply },
|
|
|
|
|
typing: createMockTypingController(),
|
|
|
|
|
typingMode: "instant",
|
|
|
|
|
defaultModel: "anthropic/claude-opus-4-5",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await runner(baseQueuedRun());
|
|
|
|
|
|
|
|
|
|
// Media stripped → payload becomes non-renderable → not delivered.
|
|
|
|
|
expect(onBlockReply).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("delivers media payload when not a duplicate", async () => {
|
|
|
|
|
const onBlockReply = vi.fn(async () => {});
|
|
|
|
|
runEmbeddedPiAgentMock.mockResolvedValueOnce({
|
|
|
|
|
payloads: [{ mediaUrl: "/tmp/img.png" }],
|
|
|
|
|
messagingToolSentMediaUrls: ["/tmp/other.png"],
|
|
|
|
|
meta: {},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const runner = createFollowupRunner({
|
|
|
|
|
opts: { onBlockReply },
|
|
|
|
|
typing: createMockTypingController(),
|
|
|
|
|
typingMode: "instant",
|
|
|
|
|
defaultModel: "anthropic/claude-opus-4-5",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await runner(baseQueuedRun());
|
|
|
|
|
|
|
|
|
|
expect(onBlockReply).toHaveBeenCalledTimes(1);
|
|
|
|
|
});
|
|
|
|
|
|
2026-01-24 11:04:53 +00:00
|
|
|
it("persists usage even when replies are suppressed", async () => {
|
|
|
|
|
const storePath = path.join(
|
2026-01-30 03:15:10 +01:00
|
|
|
await fs.mkdtemp(path.join(tmpdir(), "openclaw-followup-usage-")),
|
2026-01-24 11:04:53 +00:00
|
|
|
"sessions.json",
|
|
|
|
|
);
|
|
|
|
|
const sessionKey = "main";
|
|
|
|
|
const sessionEntry: SessionEntry = { sessionId: "session", updatedAt: Date.now() };
|
|
|
|
|
const sessionStore: Record<string, SessionEntry> = { [sessionKey]: sessionEntry };
|
|
|
|
|
await saveSessionStore(storePath, sessionStore);
|
|
|
|
|
|
|
|
|
|
const onBlockReply = vi.fn(async () => {});
|
|
|
|
|
runEmbeddedPiAgentMock.mockResolvedValueOnce({
|
|
|
|
|
payloads: [{ text: "hello world!" }],
|
|
|
|
|
messagingToolSentTexts: ["different message"],
|
|
|
|
|
messagingToolSentTargets: [{ tool: "slack", provider: "slack", to: "channel:C1" }],
|
|
|
|
|
meta: {
|
|
|
|
|
agentMeta: {
|
2026-02-12 23:02:30 +00:00
|
|
|
usage: { input: 1_000, output: 50 },
|
|
|
|
|
lastCallUsage: { input: 400, output: 20 },
|
2026-01-24 11:04:53 +00:00
|
|
|
model: "claude-opus-4-5",
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const runner = createFollowupRunner({
|
|
|
|
|
opts: { onBlockReply },
|
|
|
|
|
typing: createMockTypingController(),
|
|
|
|
|
typingMode: "instant",
|
|
|
|
|
sessionEntry,
|
|
|
|
|
sessionStore,
|
|
|
|
|
sessionKey,
|
|
|
|
|
storePath,
|
|
|
|
|
defaultModel: "anthropic/claude-opus-4-5",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await runner(baseQueuedRun("slack"));
|
|
|
|
|
|
|
|
|
|
expect(onBlockReply).not.toHaveBeenCalled();
|
|
|
|
|
const store = loadSessionStore(storePath, { skipCache: true });
|
2026-02-12 23:02:30 +00:00
|
|
|
// totalTokens should reflect the last call usage snapshot, not the accumulated input.
|
|
|
|
|
expect(store[sessionKey]?.totalTokens).toBe(400);
|
2026-01-24 11:04:53 +00:00
|
|
|
expect(store[sessionKey]?.model).toBe("claude-opus-4-5");
|
2026-02-12 23:02:30 +00:00
|
|
|
// Accumulated usage is still stored for usage/cost tracking.
|
|
|
|
|
expect(store[sessionKey]?.inputTokens).toBe(1_000);
|
|
|
|
|
expect(store[sessionKey]?.outputTokens).toBe(50);
|
2026-01-24 11:04:53 +00:00
|
|
|
});
|
2026-01-08 01:09:13 +00:00
|
|
|
});
|