2026-01-30 03:15:10 +01:00
|
|
|
|
import type { OpenClawConfig } from "../config/config.js";
|
2026-02-23 16:18:55 +08:00
|
|
|
|
import {
|
|
|
|
|
|
resolveAgentModelFallbackValues,
|
|
|
|
|
|
resolveAgentModelPrimaryValue,
|
|
|
|
|
|
} from "../config/model-input.js";
|
2026-02-01 10:03:47 +09:00
|
|
|
|
import {
|
|
|
|
|
|
ensureAuthProfileStore,
|
2026-02-16 10:03:35 -03:00
|
|
|
|
getSoonestCooldownExpiry,
|
2026-02-01 10:03:47 +09:00
|
|
|
|
isProfileInCooldown,
|
2026-02-22 16:10:24 -08:00
|
|
|
|
resolveProfilesUnavailableReason,
|
2026-02-01 10:03:47 +09:00
|
|
|
|
resolveAuthProfileOrder,
|
|
|
|
|
|
} from "./auth-profiles.js";
|
2026-01-04 17:50:55 +01:00
|
|
|
|
import { DEFAULT_MODEL, DEFAULT_PROVIDER } from "./defaults.js";
|
2026-01-18 07:52:19 +00:00
|
|
|
|
import {
|
|
|
|
|
|
coerceToFailoverError,
|
|
|
|
|
|
describeFailoverError,
|
|
|
|
|
|
isFailoverError,
|
|
|
|
|
|
isTimeoutError,
|
|
|
|
|
|
} from "./failover-error.js";
|
2026-01-04 17:50:55 +01:00
|
|
|
|
import {
|
2026-02-05 16:54:44 -05:00
|
|
|
|
buildConfiguredAllowlistKeys,
|
2026-01-04 17:50:55 +01:00
|
|
|
|
buildModelAliasIndex,
|
|
|
|
|
|
modelKey,
|
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
|
|
|
|
normalizeModelRef,
|
2026-01-09 19:59:45 +01:00
|
|
|
|
resolveConfiguredModelRef,
|
2026-01-04 17:50:55 +01:00
|
|
|
|
resolveModelRefFromString,
|
|
|
|
|
|
} from "./model-selection.js";
|
2026-02-18 01:34:35 +00:00
|
|
|
|
import type { FailoverReason } from "./pi-embedded-helpers.js";
|
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
|
|
|
|
import { isLikelyContextOverflowError } from "./pi-embedded-helpers.js";
|
2026-01-04 17:50:55 +01:00
|
|
|
|
|
|
|
|
|
|
type ModelCandidate = {
|
|
|
|
|
|
provider: string;
|
|
|
|
|
|
model: string;
|
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
type FallbackAttempt = {
|
|
|
|
|
|
provider: string;
|
|
|
|
|
|
model: string;
|
|
|
|
|
|
error: string;
|
2026-01-09 21:57:52 +01:00
|
|
|
|
reason?: FailoverReason;
|
|
|
|
|
|
status?: number;
|
|
|
|
|
|
code?: string;
|
2026-01-04 17:50:55 +01:00
|
|
|
|
};
|
|
|
|
|
|
|
2026-02-09 18:56:58 -08:00
|
|
|
|
/**
|
2026-02-09 19:21:33 -08:00
|
|
|
|
* Fallback abort check. Only treats explicit AbortError names as user aborts.
|
2026-02-09 18:56:58 -08:00
|
|
|
|
* Message-based checks (e.g., "aborted") can mask timeouts and skip fallback.
|
|
|
|
|
|
*/
|
2026-02-09 19:21:33 -08:00
|
|
|
|
function isFallbackAbortError(err: unknown): boolean {
|
2026-01-31 16:19:20 +09:00
|
|
|
|
if (!err || typeof err !== "object") {
|
|
|
|
|
|
return false;
|
|
|
|
|
|
}
|
|
|
|
|
|
if (isFailoverError(err)) {
|
|
|
|
|
|
return false;
|
|
|
|
|
|
}
|
2026-01-04 17:50:55 +01:00
|
|
|
|
const name = "name" in err ? String(err.name) : "";
|
2026-01-20 19:23:06 +00:00
|
|
|
|
return name === "AbortError";
|
2026-01-04 17:50:55 +01:00
|
|
|
|
}
|
|
|
|
|
|
|
2026-01-18 07:52:19 +00:00
|
|
|
|
function shouldRethrowAbort(err: unknown): boolean {
|
2026-02-09 19:21:33 -08:00
|
|
|
|
return isFallbackAbortError(err) && !isTimeoutError(err);
|
2026-01-18 07:52:19 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
2026-02-15 06:07:01 +00:00
|
|
|
|
function createModelCandidateCollector(allowlist: Set<string> | null | undefined): {
|
|
|
|
|
|
candidates: ModelCandidate[];
|
2026-02-25 04:32:25 +00:00
|
|
|
|
addExplicitCandidate: (candidate: ModelCandidate) => void;
|
|
|
|
|
|
addAllowlistedCandidate: (candidate: ModelCandidate) => void;
|
2026-02-15 06:07:01 +00:00
|
|
|
|
} {
|
2026-01-04 19:35:00 +01:00
|
|
|
|
const seen = new Set<string>();
|
|
|
|
|
|
const candidates: ModelCandidate[] = [];
|
|
|
|
|
|
|
2026-01-14 14:31:43 +00:00
|
|
|
|
const addCandidate = (candidate: ModelCandidate, enforceAllowlist: boolean) => {
|
2026-01-31 16:19:20 +09:00
|
|
|
|
if (!candidate.provider || !candidate.model) {
|
|
|
|
|
|
return;
|
|
|
|
|
|
}
|
2026-01-04 19:35:00 +01:00
|
|
|
|
const key = modelKey(candidate.provider, candidate.model);
|
2026-01-31 16:19:20 +09:00
|
|
|
|
if (seen.has(key)) {
|
|
|
|
|
|
return;
|
|
|
|
|
|
}
|
|
|
|
|
|
if (enforceAllowlist && allowlist && !allowlist.has(key)) {
|
|
|
|
|
|
return;
|
|
|
|
|
|
}
|
2026-01-04 19:35:00 +01:00
|
|
|
|
seen.add(key);
|
|
|
|
|
|
candidates.push(candidate);
|
|
|
|
|
|
};
|
|
|
|
|
|
|
2026-02-25 04:32:25 +00:00
|
|
|
|
const addExplicitCandidate = (candidate: ModelCandidate) => {
|
|
|
|
|
|
addCandidate(candidate, false);
|
|
|
|
|
|
};
|
|
|
|
|
|
const addAllowlistedCandidate = (candidate: ModelCandidate) => {
|
|
|
|
|
|
addCandidate(candidate, true);
|
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
return { candidates, addExplicitCandidate, addAllowlistedCandidate };
|
2026-02-15 06:07:01 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
type ModelFallbackErrorHandler = (attempt: {
|
|
|
|
|
|
provider: string;
|
|
|
|
|
|
model: string;
|
|
|
|
|
|
error: unknown;
|
|
|
|
|
|
attempt: number;
|
|
|
|
|
|
total: number;
|
|
|
|
|
|
}) => void | Promise<void>;
|
|
|
|
|
|
|
|
|
|
|
|
type ModelFallbackRunResult<T> = {
|
|
|
|
|
|
result: T;
|
|
|
|
|
|
provider: string;
|
|
|
|
|
|
model: string;
|
|
|
|
|
|
attempts: FallbackAttempt[];
|
|
|
|
|
|
};
|
|
|
|
|
|
|
2026-03-02 21:30:12 +00:00
|
|
|
|
function buildFallbackSuccess<T>(params: {
|
|
|
|
|
|
result: T;
|
|
|
|
|
|
provider: string;
|
|
|
|
|
|
model: string;
|
|
|
|
|
|
attempts: FallbackAttempt[];
|
|
|
|
|
|
}): ModelFallbackRunResult<T> {
|
|
|
|
|
|
return {
|
|
|
|
|
|
result: params.result,
|
|
|
|
|
|
provider: params.provider,
|
|
|
|
|
|
model: params.model,
|
|
|
|
|
|
attempts: params.attempts,
|
|
|
|
|
|
};
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
async function runFallbackCandidate<T>(params: {
|
|
|
|
|
|
run: (provider: string, model: string) => Promise<T>;
|
|
|
|
|
|
provider: string;
|
|
|
|
|
|
model: string;
|
|
|
|
|
|
}): Promise<{ ok: true; result: T } | { ok: false; error: unknown }> {
|
|
|
|
|
|
try {
|
|
|
|
|
|
return {
|
|
|
|
|
|
ok: true,
|
|
|
|
|
|
result: await params.run(params.provider, params.model),
|
|
|
|
|
|
};
|
|
|
|
|
|
} catch (err) {
|
|
|
|
|
|
if (shouldRethrowAbort(err)) {
|
|
|
|
|
|
throw err;
|
|
|
|
|
|
}
|
|
|
|
|
|
return { ok: false, error: err };
|
|
|
|
|
|
}
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
async function runFallbackAttempt<T>(params: {
|
|
|
|
|
|
run: (provider: string, model: string) => Promise<T>;
|
|
|
|
|
|
provider: string;
|
|
|
|
|
|
model: string;
|
|
|
|
|
|
attempts: FallbackAttempt[];
|
|
|
|
|
|
}): Promise<{ success: ModelFallbackRunResult<T> } | { error: unknown }> {
|
|
|
|
|
|
const runResult = await runFallbackCandidate({
|
|
|
|
|
|
run: params.run,
|
|
|
|
|
|
provider: params.provider,
|
|
|
|
|
|
model: params.model,
|
|
|
|
|
|
});
|
|
|
|
|
|
if (runResult.ok) {
|
|
|
|
|
|
return {
|
|
|
|
|
|
success: buildFallbackSuccess({
|
|
|
|
|
|
result: runResult.result,
|
|
|
|
|
|
provider: params.provider,
|
|
|
|
|
|
model: params.model,
|
|
|
|
|
|
attempts: params.attempts,
|
|
|
|
|
|
}),
|
|
|
|
|
|
};
|
|
|
|
|
|
}
|
|
|
|
|
|
return { error: runResult.error };
|
|
|
|
|
|
}
|
|
|
|
|
|
|
2026-02-19 23:16:26 -04:00
|
|
|
|
function sameModelCandidate(a: ModelCandidate, b: ModelCandidate): boolean {
|
|
|
|
|
|
return a.provider === b.provider && a.model === b.model;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
2026-02-19 00:10:08 +00:00
|
|
|
|
function throwFallbackFailureSummary(params: {
|
|
|
|
|
|
attempts: FallbackAttempt[];
|
|
|
|
|
|
candidates: ModelCandidate[];
|
|
|
|
|
|
lastError: unknown;
|
|
|
|
|
|
label: string;
|
|
|
|
|
|
formatAttempt: (attempt: FallbackAttempt) => string;
|
|
|
|
|
|
}): never {
|
|
|
|
|
|
if (params.attempts.length <= 1 && params.lastError) {
|
|
|
|
|
|
throw params.lastError;
|
|
|
|
|
|
}
|
|
|
|
|
|
const summary =
|
|
|
|
|
|
params.attempts.length > 0 ? params.attempts.map(params.formatAttempt).join(" | ") : "unknown";
|
|
|
|
|
|
throw new Error(
|
|
|
|
|
|
`All ${params.label} failed (${params.attempts.length || params.candidates.length}): ${summary}`,
|
|
|
|
|
|
{
|
|
|
|
|
|
cause: params.lastError instanceof Error ? params.lastError : undefined,
|
|
|
|
|
|
},
|
|
|
|
|
|
);
|
|
|
|
|
|
}
|
|
|
|
|
|
|
2026-02-15 06:07:01 +00:00
|
|
|
|
function resolveImageFallbackCandidates(params: {
|
|
|
|
|
|
cfg: OpenClawConfig | undefined;
|
|
|
|
|
|
defaultProvider: string;
|
|
|
|
|
|
modelOverride?: string;
|
|
|
|
|
|
}): ModelCandidate[] {
|
|
|
|
|
|
const aliasIndex = buildModelAliasIndex({
|
|
|
|
|
|
cfg: params.cfg ?? {},
|
|
|
|
|
|
defaultProvider: params.defaultProvider,
|
|
|
|
|
|
});
|
|
|
|
|
|
const allowlist = buildConfiguredAllowlistKeys({
|
|
|
|
|
|
cfg: params.cfg,
|
|
|
|
|
|
defaultProvider: params.defaultProvider,
|
|
|
|
|
|
});
|
2026-02-25 04:32:25 +00:00
|
|
|
|
const { candidates, addExplicitCandidate, addAllowlistedCandidate } =
|
|
|
|
|
|
createModelCandidateCollector(allowlist);
|
2026-02-15 06:07:01 +00:00
|
|
|
|
|
2026-02-25 04:32:25 +00:00
|
|
|
|
const addRaw = (raw: string, opts?: { allowlist?: boolean }) => {
|
2026-01-04 19:35:00 +01:00
|
|
|
|
const resolved = resolveModelRefFromString({
|
|
|
|
|
|
raw: String(raw ?? ""),
|
|
|
|
|
|
defaultProvider: params.defaultProvider,
|
|
|
|
|
|
aliasIndex,
|
|
|
|
|
|
});
|
2026-01-31 16:19:20 +09:00
|
|
|
|
if (!resolved) {
|
|
|
|
|
|
return;
|
|
|
|
|
|
}
|
2026-02-25 04:32:25 +00:00
|
|
|
|
if (opts?.allowlist) {
|
|
|
|
|
|
addAllowlistedCandidate(resolved.ref);
|
|
|
|
|
|
return;
|
|
|
|
|
|
}
|
|
|
|
|
|
addExplicitCandidate(resolved.ref);
|
2026-01-04 19:35:00 +01:00
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
if (params.modelOverride?.trim()) {
|
2026-02-25 04:32:25 +00:00
|
|
|
|
addRaw(params.modelOverride);
|
2026-01-06 00:56:29 +00:00
|
|
|
|
} else {
|
2026-02-23 16:18:55 +08:00
|
|
|
|
const primary = resolveAgentModelPrimaryValue(params.cfg?.agents?.defaults?.imageModel);
|
2026-01-31 16:19:20 +09:00
|
|
|
|
if (primary?.trim()) {
|
2026-02-25 04:32:25 +00:00
|
|
|
|
addRaw(primary);
|
2026-01-31 16:19:20 +09:00
|
|
|
|
}
|
2026-01-04 19:35:00 +01:00
|
|
|
|
}
|
|
|
|
|
|
|
2026-02-23 16:18:55 +08:00
|
|
|
|
const imageFallbacks = resolveAgentModelFallbackValues(params.cfg?.agents?.defaults?.imageModel);
|
2026-01-06 00:56:29 +00:00
|
|
|
|
|
|
|
|
|
|
for (const raw of imageFallbacks) {
|
2026-02-25 03:46:34 +00:00
|
|
|
|
// Explicitly configured image fallbacks should remain reachable even when a
|
|
|
|
|
|
// model allowlist is present.
|
2026-02-25 04:32:25 +00:00
|
|
|
|
addRaw(raw);
|
2026-01-04 19:35:00 +01:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
return candidates;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
2026-01-04 17:50:55 +01:00
|
|
|
|
function resolveFallbackCandidates(params: {
|
2026-01-30 03:15:10 +01:00
|
|
|
|
cfg: OpenClawConfig | undefined;
|
2026-01-04 17:50:55 +01:00
|
|
|
|
provider: string;
|
|
|
|
|
|
model: string;
|
2026-01-09 14:59:02 +01:00
|
|
|
|
/** Optional explicit fallbacks list; when provided (even empty), replaces agents.defaults.model.fallbacks. */
|
|
|
|
|
|
fallbacksOverride?: string[];
|
2026-01-04 17:50:55 +01:00
|
|
|
|
}): ModelCandidate[] {
|
2026-01-09 19:59:45 +01:00
|
|
|
|
const primary = params.cfg
|
|
|
|
|
|
? resolveConfiguredModelRef({
|
|
|
|
|
|
cfg: params.cfg,
|
|
|
|
|
|
defaultProvider: DEFAULT_PROVIDER,
|
|
|
|
|
|
defaultModel: DEFAULT_MODEL,
|
|
|
|
|
|
})
|
|
|
|
|
|
: null;
|
2026-01-15 16:58:41 +00:00
|
|
|
|
const defaultProvider = primary?.provider ?? DEFAULT_PROVIDER;
|
|
|
|
|
|
const defaultModel = primary?.model ?? DEFAULT_MODEL;
|
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 providerRaw = String(params.provider ?? "").trim() || defaultProvider;
|
|
|
|
|
|
const modelRaw = String(params.model ?? "").trim() || defaultModel;
|
|
|
|
|
|
const normalizedPrimary = normalizeModelRef(providerRaw, modelRaw);
|
2026-02-19 23:16:26 -04:00
|
|
|
|
const configuredPrimary = normalizeModelRef(defaultProvider, defaultModel);
|
2026-01-04 17:50:55 +01:00
|
|
|
|
const aliasIndex = buildModelAliasIndex({
|
|
|
|
|
|
cfg: params.cfg ?? {},
|
2026-01-15 16:58:41 +00:00
|
|
|
|
defaultProvider,
|
2026-01-04 17:50:55 +01:00
|
|
|
|
});
|
2026-02-05 16:54:44 -05:00
|
|
|
|
const allowlist = buildConfiguredAllowlistKeys({
|
|
|
|
|
|
cfg: params.cfg,
|
|
|
|
|
|
defaultProvider,
|
|
|
|
|
|
});
|
2026-02-25 04:32:25 +00:00
|
|
|
|
const { candidates, addExplicitCandidate } = createModelCandidateCollector(allowlist);
|
2026-01-04 17:50:55 +01:00
|
|
|
|
|
2026-02-25 04:32:25 +00:00
|
|
|
|
addExplicitCandidate(normalizedPrimary);
|
2026-01-04 17:50:55 +01:00
|
|
|
|
|
2026-01-06 00:56:29 +00:00
|
|
|
|
const modelFallbacks = (() => {
|
2026-01-31 16:19:20 +09:00
|
|
|
|
if (params.fallbacksOverride !== undefined) {
|
|
|
|
|
|
return params.fallbacksOverride;
|
|
|
|
|
|
}
|
2026-02-25 01:46:20 +00:00
|
|
|
|
const configuredFallbacks = resolveAgentModelFallbackValues(
|
|
|
|
|
|
params.cfg?.agents?.defaults?.model,
|
|
|
|
|
|
);
|
2026-02-25 19:35:40 -06:00
|
|
|
|
// When user runs a different provider than config, only use configured fallbacks
|
|
|
|
|
|
// if the current model is already in that chain (e.g. session on first fallback).
|
|
|
|
|
|
if (normalizedPrimary.provider !== configuredPrimary.provider) {
|
|
|
|
|
|
const isConfiguredFallback = configuredFallbacks.some((raw) => {
|
|
|
|
|
|
const resolved = resolveModelRefFromString({
|
|
|
|
|
|
raw: String(raw ?? ""),
|
|
|
|
|
|
defaultProvider,
|
|
|
|
|
|
aliasIndex,
|
|
|
|
|
|
});
|
|
|
|
|
|
return resolved ? sameModelCandidate(resolved.ref, normalizedPrimary) : false;
|
2026-02-25 01:46:20 +00:00
|
|
|
|
});
|
2026-02-25 19:35:40 -06:00
|
|
|
|
return isConfiguredFallback ? configuredFallbacks : [];
|
|
|
|
|
|
}
|
|
|
|
|
|
// Same provider: always use full fallback chain (model version differences within provider).
|
|
|
|
|
|
return configuredFallbacks;
|
2026-01-06 00:56:29 +00:00
|
|
|
|
})();
|
|
|
|
|
|
|
|
|
|
|
|
for (const raw of modelFallbacks) {
|
2026-01-04 17:50:55 +01:00
|
|
|
|
const resolved = resolveModelRefFromString({
|
|
|
|
|
|
raw: String(raw ?? ""),
|
2026-01-15 16:58:41 +00:00
|
|
|
|
defaultProvider,
|
2026-01-04 17:50:55 +01:00
|
|
|
|
aliasIndex,
|
|
|
|
|
|
});
|
2026-01-31 16:19:20 +09:00
|
|
|
|
if (!resolved) {
|
|
|
|
|
|
continue;
|
|
|
|
|
|
}
|
2026-02-25 03:46:34 +00:00
|
|
|
|
// Fallbacks are explicit user intent; do not silently filter them by the
|
|
|
|
|
|
// model allowlist.
|
2026-02-25 04:32:25 +00:00
|
|
|
|
addExplicitCandidate(resolved.ref);
|
2026-01-04 17:50:55 +01:00
|
|
|
|
}
|
|
|
|
|
|
|
2026-01-14 14:31:43 +00:00
|
|
|
|
if (params.fallbacksOverride === undefined && primary?.provider && primary.model) {
|
2026-02-25 04:32:25 +00:00
|
|
|
|
addExplicitCandidate({ provider: primary.provider, model: primary.model });
|
2026-01-09 19:59:45 +01:00
|
|
|
|
}
|
|
|
|
|
|
|
2026-01-04 17:50:55 +01:00
|
|
|
|
return candidates;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
2026-02-16 10:03:35 -03:00
|
|
|
|
const lastProbeAttempt = new Map<string, number>();
|
2026-02-16 08:07:14 -05:00
|
|
|
|
const MIN_PROBE_INTERVAL_MS = 30_000; // 30 seconds between probes per key
|
|
|
|
|
|
const PROBE_MARGIN_MS = 2 * 60 * 1000;
|
|
|
|
|
|
const PROBE_SCOPE_DELIMITER = "::";
|
|
|
|
|
|
|
|
|
|
|
|
function resolveProbeThrottleKey(provider: string, agentDir?: string): string {
|
|
|
|
|
|
const scope = String(agentDir ?? "").trim();
|
|
|
|
|
|
return scope ? `${scope}${PROBE_SCOPE_DELIMITER}${provider}` : provider;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
function shouldProbePrimaryDuringCooldown(params: {
|
|
|
|
|
|
isPrimary: boolean;
|
|
|
|
|
|
hasFallbackCandidates: boolean;
|
|
|
|
|
|
now: number;
|
|
|
|
|
|
throttleKey: string;
|
|
|
|
|
|
authStore: ReturnType<typeof ensureAuthProfileStore>;
|
|
|
|
|
|
profileIds: string[];
|
|
|
|
|
|
}): boolean {
|
|
|
|
|
|
if (!params.isPrimary || !params.hasFallbackCandidates) {
|
|
|
|
|
|
return false;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
const lastProbe = lastProbeAttempt.get(params.throttleKey) ?? 0;
|
|
|
|
|
|
if (params.now - lastProbe < MIN_PROBE_INTERVAL_MS) {
|
|
|
|
|
|
return false;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
const soonest = getSoonestCooldownExpiry(params.authStore, params.profileIds);
|
|
|
|
|
|
if (soonest === null || !Number.isFinite(soonest)) {
|
|
|
|
|
|
return true;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
// Probe when cooldown already expired or within the configured margin.
|
|
|
|
|
|
return params.now >= soonest - PROBE_MARGIN_MS;
|
|
|
|
|
|
}
|
2026-02-16 10:03:35 -03:00
|
|
|
|
|
|
|
|
|
|
/** @internal – exposed for unit tests only */
|
|
|
|
|
|
export const _probeThrottleInternals = {
|
|
|
|
|
|
lastProbeAttempt,
|
|
|
|
|
|
MIN_PROBE_INTERVAL_MS,
|
2026-02-16 08:07:14 -05:00
|
|
|
|
PROBE_MARGIN_MS,
|
|
|
|
|
|
resolveProbeThrottleKey,
|
2026-02-16 10:03:35 -03:00
|
|
|
|
} as const;
|
|
|
|
|
|
|
2026-02-25 19:35:40 -06:00
|
|
|
|
type CooldownDecision =
|
|
|
|
|
|
| {
|
|
|
|
|
|
type: "skip";
|
|
|
|
|
|
reason: FailoverReason;
|
|
|
|
|
|
error: string;
|
|
|
|
|
|
}
|
|
|
|
|
|
| {
|
|
|
|
|
|
type: "attempt";
|
|
|
|
|
|
reason: FailoverReason;
|
|
|
|
|
|
markProbe: boolean;
|
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
function resolveCooldownDecision(params: {
|
|
|
|
|
|
candidate: ModelCandidate;
|
|
|
|
|
|
isPrimary: boolean;
|
|
|
|
|
|
requestedModel: boolean;
|
|
|
|
|
|
hasFallbackCandidates: boolean;
|
|
|
|
|
|
now: number;
|
|
|
|
|
|
probeThrottleKey: string;
|
|
|
|
|
|
authStore: ReturnType<typeof ensureAuthProfileStore>;
|
|
|
|
|
|
profileIds: string[];
|
|
|
|
|
|
}): CooldownDecision {
|
|
|
|
|
|
const shouldProbe = shouldProbePrimaryDuringCooldown({
|
|
|
|
|
|
isPrimary: params.isPrimary,
|
|
|
|
|
|
hasFallbackCandidates: params.hasFallbackCandidates,
|
|
|
|
|
|
now: params.now,
|
|
|
|
|
|
throttleKey: params.probeThrottleKey,
|
|
|
|
|
|
authStore: params.authStore,
|
|
|
|
|
|
profileIds: params.profileIds,
|
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
|
|
const inferredReason =
|
|
|
|
|
|
resolveProfilesUnavailableReason({
|
|
|
|
|
|
store: params.authStore,
|
|
|
|
|
|
profileIds: params.profileIds,
|
|
|
|
|
|
now: params.now,
|
|
|
|
|
|
}) ?? "rate_limit";
|
|
|
|
|
|
const isPersistentIssue =
|
|
|
|
|
|
inferredReason === "auth" ||
|
|
|
|
|
|
inferredReason === "auth_permanent" ||
|
|
|
|
|
|
inferredReason === "billing";
|
|
|
|
|
|
if (isPersistentIssue) {
|
|
|
|
|
|
return {
|
|
|
|
|
|
type: "skip",
|
|
|
|
|
|
reason: inferredReason,
|
|
|
|
|
|
error: `Provider ${params.candidate.provider} has ${inferredReason} issue (skipping all models)`,
|
|
|
|
|
|
};
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
// For primary: try when requested model or when probe allows.
|
|
|
|
|
|
// For same-provider fallbacks: only relax cooldown on rate_limit, which
|
|
|
|
|
|
// is commonly model-scoped and can recover on a sibling model.
|
|
|
|
|
|
const shouldAttemptDespiteCooldown =
|
|
|
|
|
|
(params.isPrimary && (!params.requestedModel || shouldProbe)) ||
|
|
|
|
|
|
(!params.isPrimary && inferredReason === "rate_limit");
|
|
|
|
|
|
if (!shouldAttemptDespiteCooldown) {
|
|
|
|
|
|
return {
|
|
|
|
|
|
type: "skip",
|
|
|
|
|
|
reason: inferredReason,
|
|
|
|
|
|
error: `Provider ${params.candidate.provider} is in cooldown (all profiles unavailable)`,
|
|
|
|
|
|
};
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
|
type: "attempt",
|
|
|
|
|
|
reason: inferredReason,
|
|
|
|
|
|
markProbe: params.isPrimary && shouldProbe,
|
|
|
|
|
|
};
|
|
|
|
|
|
}
|
|
|
|
|
|
|
2026-01-04 17:50:55 +01:00
|
|
|
|
export async function runWithModelFallback<T>(params: {
|
2026-01-30 03:15:10 +01:00
|
|
|
|
cfg: OpenClawConfig | undefined;
|
2026-01-04 17:50:55 +01:00
|
|
|
|
provider: string;
|
|
|
|
|
|
model: string;
|
2026-01-26 22:05:31 -05:00
|
|
|
|
agentDir?: string;
|
2026-01-09 14:59:02 +01:00
|
|
|
|
/** Optional explicit fallbacks list; when provided (even empty), replaces agents.defaults.model.fallbacks. */
|
|
|
|
|
|
fallbacksOverride?: string[];
|
2026-01-04 17:50:55 +01:00
|
|
|
|
run: (provider: string, model: string) => Promise<T>;
|
2026-02-15 06:07:01 +00:00
|
|
|
|
onError?: ModelFallbackErrorHandler;
|
|
|
|
|
|
}): Promise<ModelFallbackRunResult<T>> {
|
2026-01-09 14:59:02 +01:00
|
|
|
|
const candidates = resolveFallbackCandidates({
|
|
|
|
|
|
cfg: params.cfg,
|
|
|
|
|
|
provider: params.provider,
|
|
|
|
|
|
model: params.model,
|
|
|
|
|
|
fallbacksOverride: params.fallbacksOverride,
|
|
|
|
|
|
});
|
2026-01-26 22:05:31 -05:00
|
|
|
|
const authStore = params.cfg
|
|
|
|
|
|
? ensureAuthProfileStore(params.agentDir, { allowKeychainPrompt: false })
|
|
|
|
|
|
: null;
|
2026-01-04 17:50:55 +01:00
|
|
|
|
const attempts: FallbackAttempt[] = [];
|
|
|
|
|
|
let lastError: unknown;
|
|
|
|
|
|
|
2026-02-16 10:03:35 -03:00
|
|
|
|
const hasFallbackCandidates = candidates.length > 1;
|
|
|
|
|
|
|
2026-01-04 17:50:55 +01:00
|
|
|
|
for (let i = 0; i < candidates.length; i += 1) {
|
2026-01-31 16:03:28 +09:00
|
|
|
|
const candidate = candidates[i];
|
2026-01-26 21:59:38 -05:00
|
|
|
|
if (authStore) {
|
|
|
|
|
|
const profileIds = resolveAuthProfileOrder({
|
|
|
|
|
|
cfg: params.cfg,
|
|
|
|
|
|
store: authStore,
|
|
|
|
|
|
provider: candidate.provider,
|
|
|
|
|
|
});
|
|
|
|
|
|
const isAnyProfileAvailable = profileIds.some((id) => !isProfileInCooldown(authStore, id));
|
|
|
|
|
|
|
|
|
|
|
|
if (profileIds.length > 0 && !isAnyProfileAvailable) {
|
2026-02-16 10:03:35 -03:00
|
|
|
|
// All profiles for this provider are in cooldown.
|
2026-02-25 19:35:40 -06:00
|
|
|
|
const isPrimary = i === 0;
|
|
|
|
|
|
const requestedModel =
|
|
|
|
|
|
params.provider === candidate.provider && params.model === candidate.model;
|
2026-02-16 08:07:14 -05:00
|
|
|
|
const now = Date.now();
|
|
|
|
|
|
const probeThrottleKey = resolveProbeThrottleKey(candidate.provider, params.agentDir);
|
2026-02-25 19:35:40 -06:00
|
|
|
|
const decision = resolveCooldownDecision({
|
|
|
|
|
|
candidate,
|
|
|
|
|
|
isPrimary,
|
|
|
|
|
|
requestedModel,
|
2026-02-16 08:07:14 -05:00
|
|
|
|
hasFallbackCandidates,
|
|
|
|
|
|
now,
|
2026-02-25 19:35:40 -06:00
|
|
|
|
probeThrottleKey,
|
2026-02-16 08:07:14 -05:00
|
|
|
|
authStore,
|
|
|
|
|
|
profileIds,
|
|
|
|
|
|
});
|
2026-02-25 19:35:40 -06:00
|
|
|
|
|
|
|
|
|
|
if (decision.type === "skip") {
|
2026-02-16 10:03:35 -03:00
|
|
|
|
attempts.push({
|
|
|
|
|
|
provider: candidate.provider,
|
|
|
|
|
|
model: candidate.model,
|
2026-02-25 19:35:40 -06:00
|
|
|
|
error: decision.error,
|
|
|
|
|
|
reason: decision.reason,
|
2026-02-16 10:03:35 -03:00
|
|
|
|
});
|
|
|
|
|
|
continue;
|
|
|
|
|
|
}
|
2026-02-25 19:35:40 -06:00
|
|
|
|
|
|
|
|
|
|
if (decision.markProbe) {
|
|
|
|
|
|
lastProbeAttempt.set(probeThrottleKey, now);
|
|
|
|
|
|
}
|
2026-01-26 21:59:38 -05:00
|
|
|
|
}
|
|
|
|
|
|
}
|
2026-02-25 19:35:40 -06:00
|
|
|
|
|
2026-03-02 21:30:12 +00:00
|
|
|
|
const attemptRun = await runFallbackAttempt({ run: params.run, ...candidate, attempts });
|
|
|
|
|
|
if ("success" in attemptRun) {
|
|
|
|
|
|
return attemptRun.success;
|
|
|
|
|
|
}
|
|
|
|
|
|
const err = attemptRun.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
|
|
|
|
// Context overflow errors should be handled by the inner runner's
|
|
|
|
|
|
// compaction/retry logic, not by model fallback. If one escapes as a
|
|
|
|
|
|
// throw, rethrow it immediately rather than trying a different model
|
|
|
|
|
|
// that may have a smaller context window and fail worse.
|
|
|
|
|
|
const errMessage = err instanceof Error ? err.message : String(err);
|
|
|
|
|
|
if (isLikelyContextOverflowError(errMessage)) {
|
|
|
|
|
|
throw err;
|
|
|
|
|
|
}
|
2026-01-09 22:15:03 +01:00
|
|
|
|
const normalized =
|
|
|
|
|
|
coerceToFailoverError(err, {
|
|
|
|
|
|
provider: candidate.provider,
|
|
|
|
|
|
model: candidate.model,
|
|
|
|
|
|
}) ?? err;
|
2026-02-25 12:53:26 +08:00
|
|
|
|
|
|
|
|
|
|
// Even unrecognized errors should not abort the fallback loop when
|
|
|
|
|
|
// there are remaining candidates. Only abort/context-overflow errors
|
|
|
|
|
|
// (handled above) are truly non-retryable.
|
|
|
|
|
|
const isKnownFailover = isFailoverError(normalized);
|
|
|
|
|
|
if (!isKnownFailover && i === candidates.length - 1) {
|
2026-01-31 16:19:20 +09:00
|
|
|
|
throw err;
|
|
|
|
|
|
}
|
2026-01-09 22:15:03 +01:00
|
|
|
|
|
2026-02-25 12:53:26 +08:00
|
|
|
|
lastError = isKnownFailover ? normalized : err;
|
2026-01-09 22:15:03 +01:00
|
|
|
|
const described = describeFailoverError(normalized);
|
2026-01-04 17:50:55 +01:00
|
|
|
|
attempts.push({
|
|
|
|
|
|
provider: candidate.provider,
|
|
|
|
|
|
model: candidate.model,
|
2026-01-09 21:57:52 +01:00
|
|
|
|
error: described.message,
|
2026-02-25 12:53:26 +08:00
|
|
|
|
reason: described.reason ?? "unknown",
|
2026-01-09 21:57:52 +01:00
|
|
|
|
status: described.status,
|
|
|
|
|
|
code: described.code,
|
2026-01-04 17:50:55 +01:00
|
|
|
|
});
|
|
|
|
|
|
await params.onError?.({
|
|
|
|
|
|
provider: candidate.provider,
|
|
|
|
|
|
model: candidate.model,
|
2026-02-25 12:53:26 +08:00
|
|
|
|
error: isKnownFailover ? normalized : err,
|
2026-01-04 17:50:55 +01:00
|
|
|
|
attempt: i + 1,
|
|
|
|
|
|
total: candidates.length,
|
|
|
|
|
|
});
|
|
|
|
|
|
}
|
|
|
|
|
|
}
|
|
|
|
|
|
|
2026-02-19 00:10:08 +00:00
|
|
|
|
throwFallbackFailureSummary({
|
|
|
|
|
|
attempts,
|
|
|
|
|
|
candidates,
|
|
|
|
|
|
lastError,
|
|
|
|
|
|
label: "models",
|
|
|
|
|
|
formatAttempt: (attempt) =>
|
|
|
|
|
|
`${attempt.provider}/${attempt.model}: ${attempt.error}${
|
|
|
|
|
|
attempt.reason ? ` (${attempt.reason})` : ""
|
|
|
|
|
|
}`,
|
2026-01-14 14:31:43 +00:00
|
|
|
|
});
|
2026-01-04 17:50:55 +01:00
|
|
|
|
}
|
2026-01-04 19:35:00 +01:00
|
|
|
|
|
|
|
|
|
|
export async function runWithImageModelFallback<T>(params: {
|
2026-01-30 03:15:10 +01:00
|
|
|
|
cfg: OpenClawConfig | undefined;
|
2026-01-04 19:35:00 +01:00
|
|
|
|
modelOverride?: string;
|
|
|
|
|
|
run: (provider: string, model: string) => Promise<T>;
|
2026-02-15 06:07:01 +00:00
|
|
|
|
onError?: ModelFallbackErrorHandler;
|
|
|
|
|
|
}): Promise<ModelFallbackRunResult<T>> {
|
2026-01-04 19:35:00 +01:00
|
|
|
|
const candidates = resolveImageFallbackCandidates({
|
|
|
|
|
|
cfg: params.cfg,
|
|
|
|
|
|
defaultProvider: DEFAULT_PROVIDER,
|
|
|
|
|
|
modelOverride: params.modelOverride,
|
|
|
|
|
|
});
|
|
|
|
|
|
if (candidates.length === 0) {
|
|
|
|
|
|
throw new Error(
|
2026-01-09 12:44:23 +00:00
|
|
|
|
"No image model configured. Set agents.defaults.imageModel.primary or agents.defaults.imageModel.fallbacks.",
|
2026-01-04 19:35:00 +01:00
|
|
|
|
);
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
const attempts: FallbackAttempt[] = [];
|
|
|
|
|
|
let lastError: unknown;
|
|
|
|
|
|
|
|
|
|
|
|
for (let i = 0; i < candidates.length; i += 1) {
|
2026-01-31 16:03:28 +09:00
|
|
|
|
const candidate = candidates[i];
|
2026-03-02 21:30:12 +00:00
|
|
|
|
const attemptRun = await runFallbackAttempt({ run: params.run, ...candidate, attempts });
|
|
|
|
|
|
if ("success" in attemptRun) {
|
|
|
|
|
|
return attemptRun.success;
|
|
|
|
|
|
}
|
|
|
|
|
|
{
|
|
|
|
|
|
const err = attemptRun.error;
|
2026-01-04 19:35:00 +01:00
|
|
|
|
lastError = err;
|
|
|
|
|
|
attempts.push({
|
|
|
|
|
|
provider: candidate.provider,
|
|
|
|
|
|
model: candidate.model,
|
|
|
|
|
|
error: err instanceof Error ? err.message : String(err),
|
|
|
|
|
|
});
|
|
|
|
|
|
await params.onError?.({
|
|
|
|
|
|
provider: candidate.provider,
|
|
|
|
|
|
model: candidate.model,
|
|
|
|
|
|
error: err,
|
|
|
|
|
|
attempt: i + 1,
|
|
|
|
|
|
total: candidates.length,
|
|
|
|
|
|
});
|
|
|
|
|
|
}
|
|
|
|
|
|
}
|
|
|
|
|
|
|
2026-02-19 00:10:08 +00:00
|
|
|
|
throwFallbackFailureSummary({
|
|
|
|
|
|
attempts,
|
|
|
|
|
|
candidates,
|
|
|
|
|
|
lastError,
|
|
|
|
|
|
label: "image models",
|
|
|
|
|
|
formatAttempt: (attempt) => `${attempt.provider}/${attempt.model}: ${attempt.error}`,
|
2026-01-14 14:31:43 +00:00
|
|
|
|
});
|
2026-01-04 19:35:00 +01:00
|
|
|
|
}
|