Files
openclaw/src/agents/pi-embedded-utils.test.ts

594 lines
16 KiB
TypeScript
Raw Normal View History

import type { AssistantMessage } from "@mariozechner/pi-ai";
import { describe, expect, it } from "vitest";
import {
extractAssistantText,
formatReasoningMessage,
promoteThinkingTagsToBlocks,
stripDowngradedToolCallText,
} from "./pi-embedded-utils.js";
2026-02-17 10:51:16 +09:00
function makeAssistantMessage(
message: Omit<AssistantMessage, "api" | "provider" | "model" | "usage" | "stopReason"> &
Partial<Pick<AssistantMessage, "api" | "provider" | "model" | "usage" | "stopReason">>,
): AssistantMessage {
return {
api: "responses",
provider: "openai",
model: "gpt-5",
2026-02-17 15:48:44 +09:00
usage: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
totalTokens: 0,
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },
},
2026-02-17 10:51:16 +09:00
stopReason: "stop",
...message,
};
}
describe("extractAssistantText", () => {
2026-02-21 21:43:24 +00:00
it("strips tool-only Minimax invocation XML from text", () => {
const cases = [
`<invoke name="Bash">
<parameter name="command">netstat -tlnp | grep 18789</parameter>
</invoke>
</minimax:tool_call>`,
2026-02-21 21:43:24 +00:00
`<invoke name="Bash">
<parameter name="command">test</parameter>
</invoke>
</minimax:tool_call>`,
];
for (const text of cases) {
const msg = makeAssistantMessage({
role: "assistant",
content: [{ type: "text", text }],
timestamp: Date.now(),
});
expect(extractAssistantText(msg)).toBe("");
}
});
it("strips multiple tool invocations", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: `Let me check that.<invoke name="Read">
<parameter name="path">/home/admin/test.txt</parameter>
</invoke>
</minimax:tool_call>`,
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("Let me check that.");
});
it("keeps invoke snippets without Minimax markers", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: `Example:\n<invoke name="Bash">\n<parameter name="command">ls</parameter>\n</invoke>`,
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe(
`Example:\n<invoke name="Bash">\n<parameter name="command">ls</parameter>\n</invoke>`,
);
});
it("preserves normal text without tool invocations", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: "This is a normal response without any tool calls.",
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("This is a normal response without any tool calls.");
});
it("sanitizes HTTP-ish error text only when stopReason is error", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
stopReason: "error",
errorMessage: "500 Internal Server Error",
content: [{ type: "text", text: "500 Internal Server Error" }],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("HTTP 500: Internal Server Error");
});
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
it("does not rewrite normal text that references billing plans", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
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
role: "assistant",
content: [
{
type: "text",
text: "Firebase downgraded Chore Champ to the Spark plan; confirm whether billing should be re-enabled.",
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
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
const result = extractAssistantText(msg);
expect(result).toBe(
"Firebase downgraded Chore Champ to the Spark plan; confirm whether billing should be re-enabled.",
);
});
it("strips Minimax tool invocations with extra attributes", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: `Before<invoke name='Bash' data-foo="bar">\n<parameter name="command">ls</parameter>\n</invoke>\n</minimax:tool_call>After`,
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("Before\nAfter");
});
it("strips minimax tool_call open and close tags", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: "Start<minimax:tool_call>Inner</minimax:tool_call>End",
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("StartInnerEnd");
});
it("ignores invoke blocks without minimax markers", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: "Before<invoke>Keep</invoke>After",
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("Before<invoke>Keep</invoke>After");
});
it("strips invoke blocks when minimax markers are present elsewhere", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: "Before<invoke>Drop</invoke><minimax:tool_call>After",
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("BeforeAfter");
});
it("strips invoke blocks with nested tags", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: `A<invoke name="Bash"><param><deep>1</deep></param></invoke></minimax:tool_call>B`,
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("AB");
});
it("strips tool XML mixed with regular content", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: `I'll help you with that.<invoke name="Bash">
<parameter name="command">ls -la</parameter>
</invoke>
</minimax:tool_call>Here are the results.`,
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("I'll help you with that.\nHere are the results.");
});
it("handles multiple invoke blocks in one message", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: `First check.<invoke name="Read">
<parameter name="path">file1.txt</parameter>
</invoke>
</minimax:tool_call>Second check.<invoke name="Bash">
<parameter name="command">pwd</parameter>
</invoke>
</minimax:tool_call>Done.`,
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("First check.\nSecond check.\nDone.");
});
it("handles stray closing tags without opening tags", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: "Some text here.</minimax:tool_call>More text.",
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("Some text here.More text.");
});
it("handles multiple text blocks", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: "First block.",
},
{
type: "text",
text: `<invoke name="Bash">
<parameter name="command">ls</parameter>
</invoke>
</minimax:tool_call>`,
},
{
type: "text",
text: "Third block.",
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("First block.\nThird block.");
});
it("strips downgraded Gemini tool call text representations", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: `[Tool Call: exec (ID: toolu_vrtx_014w1P6B6w4V92v4VzG7Qk12)]
Arguments: { "command": "git status", "timeout": 120000 }`,
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("");
});
it("strips multiple downgraded tool calls", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: `[Tool Call: read (ID: toolu_1)]
Arguments: { "path": "/some/file.txt" }
[Tool Call: exec (ID: toolu_2)]
Arguments: { "command": "ls -la" }`,
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("");
});
it("strips tool results for downgraded calls", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: `[Tool Result for ID toolu_123]
{"status": "ok", "data": "some result"}`,
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("");
});
it("preserves text around downgraded tool calls", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: `Let me check that for you.
[Tool Call: browser (ID: toolu_abc)]
Arguments: { "action": "act", "request": "click button" }`,
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("Let me check that for you.");
});
it("preserves trailing text after downgraded tool call blocks", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: `Intro text.
[Tool Call: read (ID: toolu_1)]
Arguments: {
"path": "/tmp/file.txt"
}
Back to the user.`,
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("Intro text.\nBack to the user.");
});
it("handles multiple text blocks with tool calls and results", () => {
2026-02-17 10:51:16 +09:00
const msg = makeAssistantMessage({
role: "assistant",
content: [
{
type: "text",
text: "Here's what I found:",
},
{
type: "text",
text: `[Tool Call: read (ID: toolu_1)]
Arguments: { "path": "/test.txt" }`,
},
{
type: "text",
text: `[Tool Result for ID toolu_1]
File contents here`,
},
{
type: "text",
text: "Done checking.",
},
],
timestamp: Date.now(),
2026-02-17 10:51:16 +09:00
});
const result = extractAssistantText(msg);
expect(result).toBe("Here's what I found:\nDone checking.");
});
2026-02-21 21:43:24 +00:00
it("strips reasoning/thinking tag variants", () => {
const cases = [
{
name: "think tag",
text: "<think>El usuario quiere retomar una tarea...</think>Aquí está tu respuesta.",
expected: "Aquí está tu respuesta.",
},
{
name: "think tag with attributes",
text: `<think reason="deliberate">Hidden</think>Visible`,
expected: "Visible",
},
{
name: "unclosed think tag",
text: "<think>Pensando sobre el problema...",
expected: "",
},
{
name: "thinking tag",
text: "Before<thinking>internal reasoning</thinking>After",
expected: "BeforeAfter",
},
{
name: "antthinking tag",
text: "<antthinking>Some reasoning</antthinking>The actual answer.",
expected: "The actual answer.",
},
{
name: "final wrapper",
text: "<final>\nAnswer\n</final>",
expected: "Answer",
},
{
name: "thought tag",
text: "<thought>Internal deliberation</thought>Final response.",
expected: "Final response.",
},
{
name: "multiple think blocks",
text: "Start<think>first thought</think>Middle<think>second thought</think>End",
expected: "StartMiddleEnd",
},
] as const;
for (const testCase of cases) {
const msg = makeAssistantMessage({
role: "assistant",
content: [{ type: "text", text: testCase.text }],
timestamp: Date.now(),
});
expect(extractAssistantText(msg), testCase.name).toBe(testCase.expected);
}
});
});
describe("formatReasoningMessage", () => {
it("returns empty string for whitespace-only input", () => {
expect(formatReasoningMessage(" \n \t ")).toBe("");
});
it("wraps single line in italics", () => {
expect(formatReasoningMessage("Single line of reasoning")).toBe(
"Reasoning:\n_Single line of reasoning_",
);
});
it("wraps each line separately for multiline text (Telegram fix)", () => {
expect(formatReasoningMessage("Line one\nLine two\nLine three")).toBe(
"Reasoning:\n_Line one_\n_Line two_\n_Line three_",
);
});
it("preserves empty lines between reasoning text", () => {
expect(formatReasoningMessage("First block\n\nSecond block")).toBe(
"Reasoning:\n_First block_\n\n_Second block_",
);
});
it("handles mixed empty and non-empty lines", () => {
expect(formatReasoningMessage("A\n\nB\nC")).toBe("Reasoning:\n_A_\n\n_B_\n_C_");
});
it("trims leading/trailing whitespace", () => {
expect(formatReasoningMessage(" \n Reasoning here \n ")).toBe(
"Reasoning:\n_Reasoning here_",
);
});
});
describe("stripDowngradedToolCallText", () => {
2026-02-21 21:43:24 +00:00
it("strips downgraded marker blocks while preserving surrounding user-facing text", () => {
const cases = [
{
name: "historical context only",
text: `[Historical context: a different model called tool "exec" with arguments {"command":"git status"}]`,
expected: "",
},
{
name: "text before historical context",
text: `Here is the answer.\n[Historical context: a different model called tool "read"]`,
expected: "Here is the answer.",
},
{
name: "text around historical context",
text: `Before.\n[Historical context: tool call info]\nAfter.`,
expected: "Before.\nAfter.",
},
{
name: "multiple historical context blocks",
text: `[Historical context: first tool call]\n[Historical context: second tool call]`,
expected: "",
},
{
name: "mixed tool call and historical context",
text: `Intro.\n[Tool Call: exec (ID: toolu_1)]\nArguments: { "command": "ls" }\n[Historical context: a different model called tool "read"]`,
expected: "Intro.",
},
{
name: "no markers",
text: "Just a normal response with no markers.",
expected: "Just a normal response with no markers.",
},
] as const;
for (const testCase of cases) {
expect(stripDowngradedToolCallText(testCase.text), testCase.name).toBe(testCase.expected);
}
});
2026-02-21 21:43:24 +00:00
});
describe("promoteThinkingTagsToBlocks", () => {
it("does not crash on malformed null content entries", () => {
const msg = makeAssistantMessage({
role: "assistant",
content: [null as never, { type: "text", text: "<thinking>hello</thinking>ok" }],
timestamp: Date.now(),
});
expect(() => promoteThinkingTagsToBlocks(msg)).not.toThrow();
const types = msg.content.map((b: { type?: string }) => b?.type);
expect(types).toContain("thinking");
expect(types).toContain("text");
});
it("does not crash on undefined content entries", () => {
const msg = makeAssistantMessage({
role: "assistant",
content: [undefined as never, { type: "text", text: "no tags here" }],
timestamp: Date.now(),
});
expect(() => promoteThinkingTagsToBlocks(msg)).not.toThrow();
});
it("passes through well-formed content unchanged when no thinking tags", () => {
const msg = makeAssistantMessage({
role: "assistant",
content: [{ type: "text", text: "hello world" }],
timestamp: Date.now(),
});
promoteThinkingTagsToBlocks(msg);
expect(msg.content).toEqual([{ type: "text", text: "hello world" }]);
});
});
2026-02-21 21:43:24 +00:00
describe("empty input handling", () => {
it("returns empty string", () => {
const helpers = [formatReasoningMessage, stripDowngradedToolCallText];
for (const helper of helpers) {
expect(helper("")).toBe("");
}
});
});