2026-01-16 03:00:40 +00:00
import { describe , expect , it } from "vitest" ;
2026-02-16 00:57:47 +00:00
import {
2026-03-01 21:45:12 -06:00
downgradeOpenAIFunctionCallReasoningPairs ,
2026-02-16 00:57:47 +00:00
downgradeOpenAIReasoningBlocks ,
isMessagingToolDuplicate ,
normalizeTextForComparison ,
sanitizeToolCallId ,
sanitizeUserFacingText ,
stripThoughtSignatures ,
} from "./pi-embedded-helpers.js" ;
2026-01-16 03:00:40 +00:00
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 ) ;
} ,
) ;
2026-01-16 03:00:40 +00:00
it ( "sanitizes role ordering errors" , ( ) = > {
2026-02-09 19:52:24 -06:00
const result = sanitizeUserFacingText ( "400 Incorrect role information" , { errorContext : true } ) ;
2026-01-16 03:00:40 +00:00
expect ( result ) . toContain ( "Message ordering conflict" ) ;
} ) ;
it ( "sanitizes HTTP status errors with error hints" , ( ) = > {
2026-02-09 19:52:24 -06:00
expect ( sanitizeUserFacingText ( "500 Internal Server Error" , { errorContext : true } ) ) . toBe (
2026-01-22 22:24:25 +00:00
"HTTP 500: Internal Server Error" ,
2026-01-16 03:00:40 +00:00
) ;
} ) ;
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." ,
) ;
2026-02-07 17:07:12 -08:00
} ) ;
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 ) = > {
2026-02-14 20:10:50 -08:00
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 ) ;
} ) ;
2026-02-22 03:17:39 +09:00
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" ;
2026-02-22 03:17:39 +09:00
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
} ) ;
2026-01-16 03:00:40 +00:00
it ( "sanitizes raw API error payloads" , ( ) = > {
const raw = '{"type":"error","error":{"message":"Something exploded","type":"server_error"}}' ;
2026-02-09 19:52:24 -06:00
expect ( sanitizeUserFacingText ( raw , { errorContext : true } ) ) . toBe (
"LLM error server_error: Something exploded" ,
) ;
2026-01-16 03:00:40 +00:00
} ) ;
2026-01-25 10:22:47 +00:00
2026-02-15 00:40:02 +08:00
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 ) ;
2026-02-15 04:23:05 +13:00
} ) ;
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 ) ;
2026-02-15 04:23:05 +13:00
} ) ;
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 ( "" ) ;
2026-02-15 04:23:05 +13:00
} ) ;
2026-01-16 03:00:40 +00:00
} ) ;
2026-02-16 00:57:47 +00:00
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}$/ ) ;
} ) ;
2026-02-18 23:37:03 +00:00
} ) ;
it . each ( [
{
modeLabel : "default" ,
run : ( ) = > sanitizeToolCallId ( "" ) ,
assert : ( value : string ) = > expect ( value ) . toBe ( "defaulttoolid" ) ,
} ,
{
modeLabel : "strict" ,
run : ( ) = > sanitizeToolCallId ( "" , "strict" ) ,
assert : ( value : string ) = > expect ( value ) . toBe ( "defaulttoolid" ) ,
} ,
{
modeLabel : "strict9" ,
run : ( ) = > sanitizeToolCallId ( "" , "strict9" ) ,
assert : ( value : string ) = > expect ( value ) . toMatch ( /^[a-zA-Z0-9]{9}$/ ) ,
} ,
] ) ( "returns default for empty IDs in $modeLabel mode" , ( { run , assert } ) = > {
assert ( run ( ) ) ;
2026-02-16 00:57:47 +00:00
} ) ;
} ) ;
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 ) ;
} ) ;
2026-02-15 22:45:01 -08:00
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 ) ;
} ) ;
2026-02-16 00:57:47 +00:00
} ) ;
2026-03-01 21:45:12 -06:00
describe ( "downgradeOpenAIFunctionCallReasoningPairs" , ( ) = > {
2026-03-02 06:40:42 +00:00
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 : [
2026-03-01 21:45:12 -06:00
{
2026-03-02 06:40:42 +00:00
type : "thinking" ,
thinking : "internal" ,
thinkingSignature : JSON.stringify ( { id : "rs_123" , type : "reasoning" } ) ,
2026-03-01 21:45:12 -06:00
} ,
2026-03-02 06:40:42 +00:00
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" ) ,
2026-03-01 21:45:12 -06:00
] ;
// oxlint-disable-next-line typescript/no-explicit-any
expect ( downgradeOpenAIFunctionCallReasoningPairs ( input as any ) ) . toEqual ( [
2026-03-02 06:40:42 +00:00
makePlainAssistantTurn ( callIdWithoutReasoning ) ,
makeToolResult ( callIdWithoutReasoning , "ok" ) ,
2026-03-01 21:45:12 -06:00
] ) ;
} ) ;
it ( "keeps fc ids when replayable reasoning is present" , ( ) = > {
const input = [
2026-03-02 06:40:42 +00:00
makeReasoningAssistantTurn ( callIdWithReasoning ) ,
makeToolResult ( callIdWithReasoning , "ok" ) ,
2026-03-01 21:45:12 -06:00
] ;
// 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 = [
2026-03-02 06:40:42 +00:00
makePlainAssistantTurn ( callIdWithReasoning ) ,
makeToolResult ( callIdWithReasoning , "turn1" ) ,
makeReasoningAssistantTurn ( callIdWithReasoning ) ,
makeToolResult ( callIdWithReasoning , "turn2" ) ,
2026-03-01 21:45:12 -06:00
] ;
// oxlint-disable-next-line typescript/no-explicit-any
expect ( downgradeOpenAIFunctionCallReasoningPairs ( input as any ) ) . toEqual ( [
2026-03-02 06:40:42 +00:00
makePlainAssistantTurn ( callIdWithoutReasoning ) ,
makeToolResult ( callIdWithoutReasoning , "turn1" ) ,
makeReasoningAssistantTurn ( callIdWithReasoning ) ,
makeToolResult ( callIdWithReasoning , "turn2" ) ,
2026-03-01 21:45:12 -06:00
] ) ;
} ) ;
} ) ;
2026-02-16 00:57:47 +00:00
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 ) ;
2026-02-16 00:57:47 +00:00
} ) ;
} ) ;
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 ) ;
2026-02-16 00:57:47 +00:00
} ) ;
} ) ;