Files
openclaw/src/agents/pi-embedded-helpers.sanitizeuserfacingtext.test.ts

454 lines
15 KiB
TypeScript
Raw Normal View History

import { describe, expect, it } from "vitest";
import {
downgradeOpenAIFunctionCallReasoningPairs,
downgradeOpenAIReasoningBlocks,
isMessagingToolDuplicate,
normalizeTextForComparison,
sanitizeToolCallId,
sanitizeUserFacingText,
stripThoughtSignatures,
} from "./pi-embedded-helpers.js";
describe("sanitizeUserFacingText", () => {
it("strips final tags", () => {
expect(sanitizeUserFacingText("<final>Hello</final>")).toBe("Hello");
expect(sanitizeUserFacingText("Hi <final>there</final>!")).toBe("Hi there!");
});
2026-02-21 21:43:24 +00:00
it.each(["202 results found", "400 days left"])(
"does not clobber normal numeric prefix: %s",
(text) => {
expect(sanitizeUserFacingText(text)).toBe(text);
},
);
it("sanitizes role ordering errors", () => {
const result = sanitizeUserFacingText("400 Incorrect role information", { errorContext: true });
expect(result).toContain("Message ordering conflict");
});
it("sanitizes HTTP status errors with error hints", () => {
expect(sanitizeUserFacingText("500 Internal Server Error", { errorContext: true })).toBe(
2026-01-22 22:24:25 +00:00
"HTTP 500: Internal Server Error",
);
});
2026-02-21 21:43:24 +00:00
it.each([
"Context overflow: prompt too large for the model. Try /reset (or /new) to start a fresh session, or use a larger-context model.",
"Request size exceeds model context window",
])("sanitizes direct context-overflow error: %s", (text) => {
expect(sanitizeUserFacingText(text, { errorContext: true })).toContain(
"Context overflow: prompt too large for the model.",
);
});
2026-02-21 21:43:24 +00:00
it.each([
"Changelog note: we fixed false positives for `Context overflow: prompt too large for the model. Try /reset (or /new) to start a fresh session, or use a larger-context model.` in 2026.2.9",
"nah it failed, hit a context overflow. the prompt was too large for the model. want me to retry it with a different approach?",
"Problem: When a subagent reads a very large file, it can exceed the model context window. Auto-compaction cannot help in that case.",
])("does not rewrite regular context-overflow mentions: %s", (text) => {
expect(sanitizeUserFacingText(text)).toBe(text);
});
2026-02-21 21:43:24 +00:00
it.each([
"If your API billing is low, top up credits in your provider dashboard and retry payment verification.",
"Firebase downgraded us to the free Spark plan; check whether we need to re-enable billing.",
])("does not rewrite regular billing mentions: %s", (text) => {
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
expect(sanitizeUserFacingText(text)).toBe(text);
});
it("does not rewrite billing error-shaped text without errorContext", () => {
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 text = "billing: please upgrade your plan";
expect(sanitizeUserFacingText(text)).toBe(text);
});
it("rewrites billing error-shaped text with errorContext", () => {
const text = "billing: please upgrade your plan";
expect(sanitizeUserFacingText(text, { errorContext: true })).toContain("billing 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("sanitizes raw API error payloads", () => {
const raw = '{"type":"error","error":{"message":"Something exploded","type":"server_error"}}';
expect(sanitizeUserFacingText(raw, { errorContext: true })).toBe(
"LLM error server_error: Something exploded",
);
});
it("returns a friendly message for rate limit errors in Error: prefixed payloads", () => {
expect(sanitizeUserFacingText("Error: 429 Rate limit exceeded", { errorContext: true })).toBe(
"⚠️ API rate limit reached. Please try again later.",
);
});
2026-02-21 21:43:24 +00:00
it.each([
{
input: "Hello there!\n\nHello there!",
expected: "Hello there!",
},
{
input: "Hello there!\n\nDifferent line.",
expected: "Hello there!\n\nDifferent line.",
},
])("normalizes paragraph blocks", ({ input, expected }) => {
expect(sanitizeUserFacingText(input)).toBe(expected);
});
2026-02-21 21:43:24 +00:00
it.each([
{ input: "\n\nHello there!", expected: "Hello there!" },
{ input: "\nHello there!", expected: "Hello there!" },
{ input: "\n\n\nMultiple newlines", expected: "Multiple newlines" },
{ input: "\n \nHello", expected: "Hello" },
{ input: " \n\nHello", expected: "Hello" },
])("strips leading empty lines: %j", ({ input, expected }) => {
expect(sanitizeUserFacingText(input)).toBe(expected);
});
it("preserves trailing whitespace and internal newlines", () => {
expect(sanitizeUserFacingText("Hello\n\nWorld\n")).toBe("Hello\n\nWorld\n");
expect(sanitizeUserFacingText("Line 1\nLine 2")).toBe("Line 1\nLine 2");
});
2026-02-21 21:43:24 +00:00
it.each(["\n\n", " \n "])("returns empty for whitespace-only input: %j", (input) => {
expect(sanitizeUserFacingText(input)).toBe("");
});
});
describe("stripThoughtSignatures", () => {
it("returns non-array content unchanged", () => {
expect(stripThoughtSignatures("hello")).toBe("hello");
expect(stripThoughtSignatures(null)).toBe(null);
expect(stripThoughtSignatures(undefined)).toBe(undefined);
expect(stripThoughtSignatures(123)).toBe(123);
});
it("removes msg_-prefixed thought_signature from content blocks", () => {
const input = [
{ type: "text", text: "hello", thought_signature: "msg_abc123" },
{ type: "thinking", thinking: "test", thought_signature: "AQID" },
];
const result = stripThoughtSignatures(input);
expect(result).toHaveLength(2);
expect(result[0]).toEqual({ type: "text", text: "hello" });
expect(result[1]).toEqual({
type: "thinking",
thinking: "test",
thought_signature: "AQID",
});
expect("thought_signature" in result[0]).toBe(false);
expect("thought_signature" in result[1]).toBe(true);
});
it("preserves blocks without thought_signature", () => {
const input = [
{ type: "text", text: "hello" },
{ type: "toolCall", id: "call_1", name: "read", arguments: {} },
];
const result = stripThoughtSignatures(input);
expect(result).toEqual(input);
});
it("handles mixed blocks with and without thought_signature", () => {
const input = [
{ type: "text", text: "hello", thought_signature: "msg_abc" },
{ type: "toolCall", id: "call_1", name: "read", arguments: {} },
{ type: "thinking", thinking: "hmm", thought_signature: "msg_xyz" },
];
const result = stripThoughtSignatures(input);
expect(result).toEqual([
{ type: "text", text: "hello" },
{ type: "toolCall", id: "call_1", name: "read", arguments: {} },
{ type: "thinking", thinking: "hmm" },
]);
});
it("handles empty array", () => {
expect(stripThoughtSignatures([])).toEqual([]);
});
it("handles null/undefined blocks in array", () => {
const input = [null, undefined, { type: "text", text: "hello" }];
const result = stripThoughtSignatures(input);
expect(result).toEqual([null, undefined, { type: "text", text: "hello" }]);
});
});
describe("sanitizeToolCallId", () => {
describe("strict mode (default)", () => {
it("keeps valid alphanumeric tool call IDs", () => {
expect(sanitizeToolCallId("callabc123")).toBe("callabc123");
});
it("strips underscores and hyphens", () => {
expect(sanitizeToolCallId("call_abc-123")).toBe("callabc123");
expect(sanitizeToolCallId("call_abc_def")).toBe("callabcdef");
});
it("strips invalid characters", () => {
expect(sanitizeToolCallId("call_abc|item:456")).toBe("callabcitem456");
});
});
describe("strict mode (alphanumeric only)", () => {
it("strips all non-alphanumeric characters", () => {
expect(sanitizeToolCallId("call_abc-123", "strict")).toBe("callabc123");
expect(sanitizeToolCallId("call_abc|item:456", "strict")).toBe("callabcitem456");
expect(sanitizeToolCallId("whatsapp_login_1768799841527_1", "strict")).toBe(
"whatsapplogin17687998415271",
);
});
});
describe("strict9 mode (Mistral tool call IDs)", () => {
it("returns alphanumeric IDs with length 9", () => {
const out = sanitizeToolCallId("call_abc|item:456", "strict9");
expect(out).toMatch(/^[a-zA-Z0-9]{9}$/);
});
});
it.each([
{
modeLabel: "default",
run: () => sanitizeToolCallId(""),
assert: (value: string) => expect(value).toBe("defaulttoolid"),
},
{
modeLabel: "strict",
run: () => sanitizeToolCallId("", "strict"),
assert: (value: string) => expect(value).toBe("defaulttoolid"),
},
{
modeLabel: "strict9",
run: () => sanitizeToolCallId("", "strict9"),
assert: (value: string) => expect(value).toMatch(/^[a-zA-Z0-9]{9}$/),
},
])("returns default for empty IDs in $modeLabel mode", ({ run, assert }) => {
assert(run());
});
});
describe("downgradeOpenAIReasoningBlocks", () => {
it("keeps reasoning signatures when followed by content", () => {
const input = [
{
role: "assistant",
content: [
{
type: "thinking",
thinking: "internal reasoning",
thinkingSignature: JSON.stringify({ id: "rs_123", type: "reasoning" }),
},
{ type: "text", text: "answer" },
],
},
];
// oxlint-disable-next-line typescript/no-explicit-any
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual(input);
});
it("drops orphaned reasoning blocks without following content", () => {
const input = [
{
role: "assistant",
content: [
{
type: "thinking",
thinkingSignature: JSON.stringify({ id: "rs_abc", type: "reasoning" }),
},
],
},
{ role: "user", content: "next" },
];
// oxlint-disable-next-line typescript/no-explicit-any
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual([
{ role: "user", content: "next" },
]);
});
it("drops object-form orphaned signatures", () => {
const input = [
{
role: "assistant",
content: [
{
type: "thinking",
thinkingSignature: { id: "rs_obj", type: "reasoning" },
},
],
},
];
// oxlint-disable-next-line typescript/no-explicit-any
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual([]);
});
it("keeps non-reasoning thinking signatures", () => {
const input = [
{
role: "assistant",
content: [
{
type: "thinking",
thinking: "t",
thinkingSignature: "reasoning_content",
},
],
},
];
// oxlint-disable-next-line typescript/no-explicit-any
expect(downgradeOpenAIReasoningBlocks(input as any)).toEqual(input);
});
it("is idempotent for orphaned reasoning cleanup", () => {
const input = [
{
role: "assistant",
content: [
{
type: "thinking",
thinkingSignature: JSON.stringify({ id: "rs_orphan", type: "reasoning" }),
},
],
},
{ role: "user", content: "next" },
];
// oxlint-disable-next-line typescript/no-explicit-any
const once = downgradeOpenAIReasoningBlocks(input as any);
// oxlint-disable-next-line typescript/no-explicit-any
const twice = downgradeOpenAIReasoningBlocks(once as any);
expect(twice).toEqual(once);
});
});
describe("downgradeOpenAIFunctionCallReasoningPairs", () => {
const callIdWithReasoning = "call_123|fc_123";
const callIdWithoutReasoning = "call_123";
const readArgs = {} as Record<string, never>;
const makeToolCall = (id: string) => ({
type: "toolCall",
id,
name: "read",
arguments: readArgs,
});
const makeToolResult = (toolCallId: string, text: string) => ({
role: "toolResult",
toolCallId,
toolName: "read",
content: [{ type: "text", text }],
});
const makeReasoningAssistantTurn = (id: string) => ({
role: "assistant",
content: [
{
type: "thinking",
thinking: "internal",
thinkingSignature: JSON.stringify({ id: "rs_123", type: "reasoning" }),
},
makeToolCall(id),
],
});
const makePlainAssistantTurn = (id: string) => ({
role: "assistant",
content: [makeToolCall(id)],
});
it("strips fc ids when reasoning cannot be replayed", () => {
const input = [
makePlainAssistantTurn(callIdWithReasoning),
makeToolResult(callIdWithReasoning, "ok"),
];
// oxlint-disable-next-line typescript/no-explicit-any
expect(downgradeOpenAIFunctionCallReasoningPairs(input as any)).toEqual([
makePlainAssistantTurn(callIdWithoutReasoning),
makeToolResult(callIdWithoutReasoning, "ok"),
]);
});
it("keeps fc ids when replayable reasoning is present", () => {
const input = [
makeReasoningAssistantTurn(callIdWithReasoning),
makeToolResult(callIdWithReasoning, "ok"),
];
// oxlint-disable-next-line typescript/no-explicit-any
expect(downgradeOpenAIFunctionCallReasoningPairs(input as any)).toEqual(input);
});
it("only rewrites tool results paired to the downgraded assistant turn", () => {
const input = [
makePlainAssistantTurn(callIdWithReasoning),
makeToolResult(callIdWithReasoning, "turn1"),
makeReasoningAssistantTurn(callIdWithReasoning),
makeToolResult(callIdWithReasoning, "turn2"),
];
// oxlint-disable-next-line typescript/no-explicit-any
expect(downgradeOpenAIFunctionCallReasoningPairs(input as any)).toEqual([
makePlainAssistantTurn(callIdWithoutReasoning),
makeToolResult(callIdWithoutReasoning, "turn1"),
makeReasoningAssistantTurn(callIdWithReasoning),
makeToolResult(callIdWithReasoning, "turn2"),
]);
});
});
describe("normalizeTextForComparison", () => {
2026-02-21 21:43:24 +00:00
it.each([
{ input: "Hello World", expected: "hello world" },
{ input: " hello ", expected: "hello" },
{ input: "hello world", expected: "hello world" },
{ input: "Hello 👋 World 🌍", expected: "hello world" },
{ input: " Hello 👋 WORLD 🌍 ", expected: "hello world" },
])("normalizes comparison text", ({ input, expected }) => {
expect(normalizeTextForComparison(input)).toBe(expected);
});
});
describe("isMessagingToolDuplicate", () => {
2026-02-21 21:43:24 +00:00
it.each([
{
input: "hello world",
sentTexts: [],
expected: false,
},
{
input: "short",
sentTexts: ["short"],
expected: false,
},
{
input: "Hello, this is a test message!",
sentTexts: ["Hello, this is a test message!"],
expected: true,
},
{
input: "HELLO, THIS IS A TEST MESSAGE!",
sentTexts: ["hello, this is a test message!"],
expected: true,
},
{
input: "Hello! 👋 This is a test message!",
sentTexts: ["Hello! This is a test message!"],
expected: true,
},
{
input: 'I sent the message: "Hello, this is a test message!"',
sentTexts: ["Hello, this is a test message!"],
expected: true,
},
{
input: "Hello, this is a test message!",
sentTexts: ['I sent the message: "Hello, this is a test message!"'],
expected: true,
},
{
input: "This is completely different content.",
sentTexts: ["Hello, this is a test message!"],
expected: false,
},
])("returns $expected for duplicate check", ({ input, sentTexts, expected }) => {
expect(isMessagingToolDuplicate(input, sentTexts)).toBe(expected);
});
});