2026-01-25 14:54:48 +02:00
|
|
|
import { describe, it, expect, vi } from "vitest";
|
2026-02-01 10:03:47 +09:00
|
|
|
import type { OpenClawConfig } from "../config/config.js";
|
2026-02-21 17:21:48 -05:00
|
|
|
import { resetLogger, setLoggerOverride } from "../logging/logger.js";
|
2026-01-09 05:27:54 +00:00
|
|
|
import {
|
2026-02-24 19:07:56 -05:00
|
|
|
buildAllowedModelSet,
|
2026-02-25 14:36:27 +09:00
|
|
|
inferUniqueProviderFromConfiguredModels,
|
2026-01-09 05:27:54 +00:00
|
|
|
parseModelRef,
|
2026-01-25 14:54:48 +02:00
|
|
|
buildModelAliasIndex,
|
2026-03-01 19:24:09 +05:30
|
|
|
normalizeModelSelection,
|
2026-02-24 19:07:56 -05:00
|
|
|
normalizeProviderId,
|
2026-03-02 18:25:35 +00:00
|
|
|
normalizeProviderIdForAuth,
|
2026-03-01 19:24:09 +05:30
|
|
|
modelKey,
|
2026-02-24 19:07:56 -05:00
|
|
|
resolveAllowedModelRef,
|
|
|
|
|
resolveConfiguredModelRef,
|
2026-03-02 12:00:02 +08:00
|
|
|
resolveThinkingDefault,
|
2026-02-24 19:07:56 -05:00
|
|
|
resolveModelRefFromString,
|
2026-01-09 05:27:54 +00:00
|
|
|
} from "./model-selection.js";
|
2026-01-09 04:18:21 +00:00
|
|
|
|
2026-03-02 06:40:42 +00:00
|
|
|
const EXPLICIT_ALLOWLIST_CONFIG = {
|
|
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
model: { primary: "openai/gpt-5.2" },
|
|
|
|
|
models: {
|
|
|
|
|
"anthropic/claude-sonnet-4-6": { alias: "sonnet" },
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
} as OpenClawConfig;
|
|
|
|
|
|
|
|
|
|
const BUNDLED_ALLOWLIST_CATALOG = [
|
|
|
|
|
{ provider: "anthropic", id: "claude-sonnet-4-5", name: "Claude Sonnet 4.5" },
|
|
|
|
|
{ provider: "openai", id: "gpt-5.2", name: "gpt-5.2" },
|
|
|
|
|
];
|
|
|
|
|
|
|
|
|
|
const ANTHROPIC_OPUS_CATALOG = [
|
|
|
|
|
{
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
id: "claude-opus-4-6",
|
|
|
|
|
name: "Claude Opus 4.6",
|
|
|
|
|
reasoning: true,
|
|
|
|
|
},
|
|
|
|
|
];
|
|
|
|
|
|
|
|
|
|
function resolveAnthropicOpusThinking(cfg: OpenClawConfig) {
|
|
|
|
|
return resolveThinkingDefault({
|
|
|
|
|
cfg,
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
model: "claude-opus-4-6",
|
|
|
|
|
catalog: ANTHROPIC_OPUS_CATALOG,
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
describe("model-selection", () => {
|
|
|
|
|
describe("normalizeProviderId", () => {
|
|
|
|
|
it("should normalize provider names", () => {
|
|
|
|
|
expect(normalizeProviderId("Anthropic")).toBe("anthropic");
|
|
|
|
|
expect(normalizeProviderId("Z.ai")).toBe("zai");
|
|
|
|
|
expect(normalizeProviderId("z-ai")).toBe("zai");
|
|
|
|
|
expect(normalizeProviderId("OpenCode-Zen")).toBe("opencode");
|
|
|
|
|
expect(normalizeProviderId("qwen")).toBe("qwen-portal");
|
2026-01-31 06:04:10 +01:00
|
|
|
expect(normalizeProviderId("kimi-code")).toBe("kimi-coding");
|
2026-02-24 00:03:00 -05:00
|
|
|
expect(normalizeProviderId("bedrock")).toBe("amazon-bedrock");
|
|
|
|
|
expect(normalizeProviderId("aws-bedrock")).toBe("amazon-bedrock");
|
|
|
|
|
expect(normalizeProviderId("amazon-bedrock")).toBe("amazon-bedrock");
|
2026-01-06 11:35:35 -03:00
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-03-02 18:25:35 +00:00
|
|
|
describe("normalizeProviderIdForAuth", () => {
|
|
|
|
|
it("maps coding-plan variants to base provider for auth lookup", () => {
|
|
|
|
|
expect(normalizeProviderIdForAuth("volcengine-plan")).toBe("volcengine");
|
|
|
|
|
expect(normalizeProviderIdForAuth("byteplus-plan")).toBe("byteplus");
|
|
|
|
|
expect(normalizeProviderIdForAuth("openai")).toBe("openai");
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
describe("parseModelRef", () => {
|
|
|
|
|
it("should parse full model refs", () => {
|
|
|
|
|
expect(parseModelRef("anthropic/claude-3-5-sonnet", "openai")).toEqual({
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
model: "claude-3-5-sonnet",
|
|
|
|
|
});
|
2026-01-06 00:56:29 +00:00
|
|
|
});
|
|
|
|
|
|
2026-02-14 20:17:01 -08:00
|
|
|
it("preserves nested model ids after provider prefix", () => {
|
|
|
|
|
expect(parseModelRef("nvidia/moonshotai/kimi-k2.5", "anthropic")).toEqual({
|
|
|
|
|
provider: "nvidia",
|
|
|
|
|
model: "moonshotai/kimi-k2.5",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-02-05 16:54:44 -05:00
|
|
|
it("normalizes anthropic alias refs to canonical model ids", () => {
|
|
|
|
|
expect(parseModelRef("anthropic/opus-4.6", "openai")).toEqual({
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
model: "claude-opus-4-6",
|
|
|
|
|
});
|
|
|
|
|
expect(parseModelRef("opus-4.6", "anthropic")).toEqual({
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
model: "claude-opus-4-6",
|
|
|
|
|
});
|
2026-02-18 00:00:20 +01:00
|
|
|
expect(parseModelRef("anthropic/sonnet-4.6", "openai")).toEqual({
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
model: "claude-sonnet-4-6",
|
|
|
|
|
});
|
|
|
|
|
expect(parseModelRef("sonnet-4.6", "anthropic")).toEqual({
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
model: "claude-sonnet-4-6",
|
|
|
|
|
});
|
2026-02-05 16:54:44 -05:00
|
|
|
});
|
|
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
it("should use default provider if none specified", () => {
|
|
|
|
|
expect(parseModelRef("claude-3-5-sonnet", "anthropic")).toEqual({
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
model: "claude-3-5-sonnet",
|
|
|
|
|
});
|
2026-01-12 07:57:11 +00:00
|
|
|
});
|
|
|
|
|
|
2026-03-08 02:34:43 +00:00
|
|
|
it("normalizes deprecated google flash preview ids to the working model id", () => {
|
|
|
|
|
expect(parseModelRef("google/gemini-3.1-flash-preview", "openai")).toEqual({
|
|
|
|
|
provider: "google",
|
|
|
|
|
model: "gemini-3-flash-preview",
|
|
|
|
|
});
|
|
|
|
|
expect(parseModelRef("gemini-3.1-flash-preview", "google")).toEqual({
|
|
|
|
|
provider: "google",
|
|
|
|
|
model: "gemini-3-flash-preview",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-03-08 05:12:48 +00:00
|
|
|
it("normalizes gemini 3.1 flash-lite to the preview model id", () => {
|
|
|
|
|
expect(parseModelRef("google/gemini-3.1-flash-lite", "openai")).toEqual({
|
|
|
|
|
provider: "google",
|
|
|
|
|
model: "gemini-3.1-flash-lite-preview",
|
|
|
|
|
});
|
|
|
|
|
expect(parseModelRef("gemini-3.1-flash-lite", "google")).toEqual({
|
|
|
|
|
provider: "google",
|
|
|
|
|
model: "gemini-3.1-flash-lite-preview",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-03-01 21:45:12 -06:00
|
|
|
it("keeps openai gpt-5.3 codex refs on the openai provider", () => {
|
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(parseModelRef("openai/gpt-5.3-codex", "anthropic")).toEqual({
|
2026-03-01 21:45:12 -06:00
|
|
|
provider: "openai",
|
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
|
|
|
model: "gpt-5.3-codex",
|
|
|
|
|
});
|
|
|
|
|
expect(parseModelRef("gpt-5.3-codex", "openai")).toEqual({
|
2026-03-01 21:45:12 -06:00
|
|
|
provider: "openai",
|
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
|
|
|
model: "gpt-5.3-codex",
|
|
|
|
|
});
|
|
|
|
|
expect(parseModelRef("openai/gpt-5.3-codex-codex", "anthropic")).toEqual({
|
2026-03-01 21:45:12 -06:00
|
|
|
provider: "openai",
|
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
|
|
|
model: "gpt-5.3-codex-codex",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
it("should return null for empty strings", () => {
|
|
|
|
|
expect(parseModelRef("", "anthropic")).toBeNull();
|
|
|
|
|
expect(parseModelRef(" ", "anthropic")).toBeNull();
|
2026-01-09 05:07:16 +00:00
|
|
|
});
|
2026-01-12 21:32:53 -06:00
|
|
|
|
2026-02-22 22:08:46 +05:00
|
|
|
it("should preserve openrouter/ prefix for native models", () => {
|
|
|
|
|
expect(parseModelRef("openrouter/aurora-alpha", "openai")).toEqual({
|
|
|
|
|
provider: "openrouter",
|
|
|
|
|
model: "openrouter/aurora-alpha",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("should pass through openrouter external provider models as-is", () => {
|
|
|
|
|
expect(parseModelRef("openrouter/anthropic/claude-sonnet-4-5", "openai")).toEqual({
|
|
|
|
|
provider: "openrouter",
|
|
|
|
|
model: "anthropic/claude-sonnet-4-5",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-02-23 11:04:31 -05:00
|
|
|
it("normalizes Vercel Claude shorthand to anthropic-prefixed model ids", () => {
|
|
|
|
|
expect(parseModelRef("vercel-ai-gateway/claude-opus-4.6", "openai")).toEqual({
|
|
|
|
|
provider: "vercel-ai-gateway",
|
|
|
|
|
model: "anthropic/claude-opus-4.6",
|
|
|
|
|
});
|
|
|
|
|
expect(parseModelRef("vercel-ai-gateway/opus-4.6", "openai")).toEqual({
|
|
|
|
|
provider: "vercel-ai-gateway",
|
|
|
|
|
model: "anthropic/claude-opus-4-6",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("keeps already-prefixed Vercel Anthropic models unchanged", () => {
|
|
|
|
|
expect(parseModelRef("vercel-ai-gateway/anthropic/claude-opus-4.6", "openai")).toEqual({
|
|
|
|
|
provider: "vercel-ai-gateway",
|
|
|
|
|
model: "anthropic/claude-opus-4.6",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("passes through non-Claude Vercel model ids unchanged", () => {
|
|
|
|
|
expect(parseModelRef("vercel-ai-gateway/openai/gpt-5.2", "openai")).toEqual({
|
|
|
|
|
provider: "vercel-ai-gateway",
|
|
|
|
|
model: "openai/gpt-5.2",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
it("should handle invalid slash usage", () => {
|
|
|
|
|
expect(parseModelRef("/", "anthropic")).toBeNull();
|
|
|
|
|
expect(parseModelRef("anthropic/", "anthropic")).toBeNull();
|
|
|
|
|
expect(parseModelRef("/model", "anthropic")).toBeNull();
|
2026-01-12 21:32:53 -06:00
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-02-25 14:36:27 +09:00
|
|
|
describe("inferUniqueProviderFromConfiguredModels", () => {
|
|
|
|
|
it("infers provider when configured model match is unique", () => {
|
|
|
|
|
const cfg = {
|
|
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
models: {
|
|
|
|
|
"anthropic/claude-sonnet-4-6": {},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
} as OpenClawConfig;
|
|
|
|
|
|
|
|
|
|
expect(
|
|
|
|
|
inferUniqueProviderFromConfiguredModels({
|
|
|
|
|
cfg,
|
|
|
|
|
model: "claude-sonnet-4-6",
|
|
|
|
|
}),
|
|
|
|
|
).toBe("anthropic");
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("returns undefined when configured matches are ambiguous", () => {
|
|
|
|
|
const cfg = {
|
|
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
models: {
|
|
|
|
|
"anthropic/claude-sonnet-4-6": {},
|
|
|
|
|
"minimax/claude-sonnet-4-6": {},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
} as OpenClawConfig;
|
|
|
|
|
|
|
|
|
|
expect(
|
|
|
|
|
inferUniqueProviderFromConfiguredModels({
|
|
|
|
|
cfg,
|
|
|
|
|
model: "claude-sonnet-4-6",
|
|
|
|
|
}),
|
|
|
|
|
).toBeUndefined();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("returns undefined for provider-prefixed model ids", () => {
|
|
|
|
|
const cfg = {
|
|
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
models: {
|
|
|
|
|
"anthropic/claude-sonnet-4-6": {},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
} as OpenClawConfig;
|
|
|
|
|
|
|
|
|
|
expect(
|
|
|
|
|
inferUniqueProviderFromConfiguredModels({
|
|
|
|
|
cfg,
|
|
|
|
|
model: "anthropic/claude-sonnet-4-6",
|
|
|
|
|
}),
|
|
|
|
|
).toBeUndefined();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("infers provider for slash-containing model id when allowlist match is unique", () => {
|
|
|
|
|
const cfg = {
|
|
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
models: {
|
|
|
|
|
"vercel-ai-gateway/anthropic/claude-sonnet-4-6": {},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
} as OpenClawConfig;
|
|
|
|
|
|
|
|
|
|
expect(
|
|
|
|
|
inferUniqueProviderFromConfiguredModels({
|
|
|
|
|
cfg,
|
|
|
|
|
model: "anthropic/claude-sonnet-4-6",
|
|
|
|
|
}),
|
|
|
|
|
).toBe("vercel-ai-gateway");
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
describe("buildModelAliasIndex", () => {
|
|
|
|
|
it("should build alias index from config", () => {
|
2026-01-30 03:15:10 +01:00
|
|
|
const cfg: Partial<OpenClawConfig> = {
|
2026-01-25 14:54:48 +02:00
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
models: {
|
|
|
|
|
"anthropic/claude-3-5-sonnet": { alias: "fast" },
|
|
|
|
|
"openai/gpt-4o": { alias: "smart" },
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
};
|
2026-01-09 19:59:45 +01:00
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
const index = buildModelAliasIndex({
|
2026-01-30 03:15:10 +01:00
|
|
|
cfg: cfg as OpenClawConfig,
|
2026-01-25 14:54:48 +02:00
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
});
|
2026-01-09 19:59:45 +01:00
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
expect(index.byAlias.get("fast")?.ref).toEqual({
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
model: "claude-3-5-sonnet",
|
|
|
|
|
});
|
|
|
|
|
expect(index.byAlias.get("smart")?.ref).toEqual({ provider: "openai", model: "gpt-4o" });
|
|
|
|
|
expect(index.byKey.get(modelKey("anthropic", "claude-3-5-sonnet"))).toEqual(["fast"]);
|
2026-01-09 19:59:45 +01:00
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-02-24 19:07:56 -05:00
|
|
|
describe("buildAllowedModelSet", () => {
|
|
|
|
|
it("keeps explicitly allowlisted models even when missing from bundled catalog", () => {
|
|
|
|
|
const result = buildAllowedModelSet({
|
2026-03-02 06:40:42 +00:00
|
|
|
cfg: EXPLICIT_ALLOWLIST_CONFIG,
|
|
|
|
|
catalog: BUNDLED_ALLOWLIST_CATALOG,
|
2026-02-24 19:07:56 -05:00
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(result.allowAny).toBe(false);
|
|
|
|
|
expect(result.allowedKeys.has("anthropic/claude-sonnet-4-6")).toBe(true);
|
|
|
|
|
expect(result.allowedCatalog).toEqual([
|
|
|
|
|
{ provider: "anthropic", id: "claude-sonnet-4-6", name: "claude-sonnet-4-6" },
|
|
|
|
|
]);
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe("resolveAllowedModelRef", () => {
|
|
|
|
|
it("accepts explicit allowlist refs absent from bundled catalog", () => {
|
|
|
|
|
const result = resolveAllowedModelRef({
|
2026-03-02 06:40:42 +00:00
|
|
|
cfg: EXPLICIT_ALLOWLIST_CONFIG,
|
|
|
|
|
catalog: BUNDLED_ALLOWLIST_CATALOG,
|
2026-02-24 19:07:56 -05:00
|
|
|
raw: "anthropic/claude-sonnet-4-6",
|
|
|
|
|
defaultProvider: "openai",
|
|
|
|
|
defaultModel: "gpt-5.2",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(result).toEqual({
|
|
|
|
|
key: "anthropic/claude-sonnet-4-6",
|
|
|
|
|
ref: { provider: "anthropic", model: "claude-sonnet-4-6" },
|
|
|
|
|
});
|
|
|
|
|
});
|
2026-02-26 14:31:57 +01:00
|
|
|
|
|
|
|
|
it("strips trailing auth profile suffix before allowlist matching", () => {
|
|
|
|
|
const cfg: OpenClawConfig = {
|
|
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
models: {
|
|
|
|
|
"openai/@cf/openai/gpt-oss-20b": {},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
} as OpenClawConfig;
|
|
|
|
|
|
|
|
|
|
const result = resolveAllowedModelRef({
|
|
|
|
|
cfg,
|
|
|
|
|
catalog: [],
|
|
|
|
|
raw: "openai/@cf/openai/gpt-oss-20b@cf:default",
|
|
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(result).toEqual({
|
|
|
|
|
key: "openai/@cf/openai/gpt-oss-20b",
|
|
|
|
|
ref: { provider: "openai", model: "@cf/openai/gpt-oss-20b" },
|
|
|
|
|
});
|
|
|
|
|
});
|
2026-02-24 19:07:56 -05:00
|
|
|
});
|
|
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
describe("resolveModelRefFromString", () => {
|
|
|
|
|
it("should resolve from string with alias", () => {
|
|
|
|
|
const index = {
|
|
|
|
|
byAlias: new Map([
|
|
|
|
|
["fast", { alias: "fast", ref: { provider: "anthropic", model: "sonnet" } }],
|
|
|
|
|
]),
|
|
|
|
|
byKey: new Map(),
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const resolved = resolveModelRefFromString({
|
|
|
|
|
raw: "fast",
|
|
|
|
|
defaultProvider: "openai",
|
|
|
|
|
aliasIndex: index,
|
|
|
|
|
});
|
2026-01-09 19:59:45 +01:00
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
expect(resolved?.ref).toEqual({ provider: "anthropic", model: "sonnet" });
|
|
|
|
|
expect(resolved?.alias).toBe("fast");
|
2026-01-09 19:59:45 +01:00
|
|
|
});
|
|
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
it("should resolve direct ref if no alias match", () => {
|
|
|
|
|
const resolved = resolveModelRefFromString({
|
|
|
|
|
raw: "openai/gpt-4",
|
|
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
});
|
|
|
|
|
expect(resolved?.ref).toEqual({ provider: "openai", model: "gpt-4" });
|
2026-01-09 19:59:45 +01:00
|
|
|
});
|
2026-02-26 14:31:57 +01:00
|
|
|
|
|
|
|
|
it("strips trailing profile suffix for simple model refs", () => {
|
|
|
|
|
const resolved = resolveModelRefFromString({
|
|
|
|
|
raw: "gpt-5@myprofile",
|
|
|
|
|
defaultProvider: "openai",
|
|
|
|
|
});
|
|
|
|
|
expect(resolved?.ref).toEqual({ provider: "openai", model: "gpt-5" });
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("strips trailing profile suffix for provider/model refs", () => {
|
|
|
|
|
const resolved = resolveModelRefFromString({
|
|
|
|
|
raw: "google/gemini-flash-latest@google:bevfresh",
|
|
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
});
|
|
|
|
|
expect(resolved?.ref).toEqual({
|
|
|
|
|
provider: "google",
|
|
|
|
|
model: "gemini-flash-latest",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("preserves Cloudflare @cf model segments", () => {
|
|
|
|
|
const resolved = resolveModelRefFromString({
|
|
|
|
|
raw: "openai/@cf/openai/gpt-oss-20b",
|
|
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
});
|
|
|
|
|
expect(resolved?.ref).toEqual({
|
|
|
|
|
provider: "openai",
|
|
|
|
|
model: "@cf/openai/gpt-oss-20b",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("preserves OpenRouter @preset model segments", () => {
|
|
|
|
|
const resolved = resolveModelRefFromString({
|
|
|
|
|
raw: "openrouter/@preset/kimi-2-5",
|
|
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
});
|
|
|
|
|
expect(resolved?.ref).toEqual({
|
|
|
|
|
provider: "openrouter",
|
|
|
|
|
model: "@preset/kimi-2-5",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("splits trailing profile suffix after OpenRouter preset paths", () => {
|
|
|
|
|
const resolved = resolveModelRefFromString({
|
|
|
|
|
raw: "openrouter/@preset/kimi-2-5@work",
|
|
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
});
|
|
|
|
|
expect(resolved?.ref).toEqual({
|
|
|
|
|
provider: "openrouter",
|
|
|
|
|
model: "@preset/kimi-2-5",
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("strips profile suffix before alias resolution", () => {
|
|
|
|
|
const index = {
|
|
|
|
|
byAlias: new Map([
|
|
|
|
|
["kimi", { alias: "kimi", ref: { provider: "nvidia", model: "moonshotai/kimi-k2.5" } }],
|
|
|
|
|
]),
|
|
|
|
|
byKey: new Map(),
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const resolved = resolveModelRefFromString({
|
|
|
|
|
raw: "kimi@nvidia:default",
|
|
|
|
|
defaultProvider: "openai",
|
|
|
|
|
aliasIndex: index,
|
|
|
|
|
});
|
|
|
|
|
expect(resolved?.ref).toEqual({
|
|
|
|
|
provider: "nvidia",
|
|
|
|
|
model: "moonshotai/kimi-k2.5",
|
|
|
|
|
});
|
|
|
|
|
expect(resolved?.alias).toBe("kimi");
|
|
|
|
|
});
|
2026-01-09 19:59:45 +01:00
|
|
|
});
|
2026-01-09 20:07:20 +01:00
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
describe("resolveConfiguredModelRef", () => {
|
|
|
|
|
it("should fall back to anthropic and warn if provider is missing for non-alias", () => {
|
2026-02-21 17:21:48 -05:00
|
|
|
setLoggerOverride({ level: "silent", consoleLevel: "warn" });
|
2026-01-25 14:54:48 +02:00
|
|
|
const warnSpy = vi.spyOn(console, "warn").mockImplementation(() => {});
|
2026-02-21 17:21:48 -05:00
|
|
|
try {
|
|
|
|
|
const cfg: Partial<OpenClawConfig> = {
|
|
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
model: { primary: "claude-3-5-sonnet" },
|
|
|
|
|
},
|
2026-01-09 20:07:20 +01:00
|
|
|
},
|
2026-02-21 17:21:48 -05:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const result = resolveConfiguredModelRef({
|
|
|
|
|
cfg: cfg as OpenClawConfig,
|
|
|
|
|
defaultProvider: "google",
|
|
|
|
|
defaultModel: "gemini-pro",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(result).toEqual({ provider: "anthropic", model: "claude-3-5-sonnet" });
|
|
|
|
|
expect(warnSpy).toHaveBeenCalledWith(
|
|
|
|
|
expect.stringContaining('Falling back to "anthropic/claude-3-5-sonnet"'),
|
|
|
|
|
);
|
|
|
|
|
} finally {
|
|
|
|
|
setLoggerOverride(null);
|
|
|
|
|
resetLogger();
|
|
|
|
|
}
|
2026-01-09 20:07:20 +01:00
|
|
|
});
|
2026-01-25 14:54:48 +02:00
|
|
|
|
2026-03-07 23:07:06 +00:00
|
|
|
it("sanitizes control characters in providerless-model warnings", () => {
|
|
|
|
|
setLoggerOverride({ level: "silent", consoleLevel: "warn" });
|
|
|
|
|
const warnSpy = vi.spyOn(console, "warn").mockImplementation(() => {});
|
|
|
|
|
try {
|
|
|
|
|
const cfg: Partial<OpenClawConfig> = {
|
|
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
model: { primary: "\u001B[31mclaude-3-5-sonnet\nspoof" },
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const result = resolveConfiguredModelRef({
|
|
|
|
|
cfg: cfg as OpenClawConfig,
|
|
|
|
|
defaultProvider: "google",
|
|
|
|
|
defaultModel: "gemini-pro",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(result).toEqual({
|
|
|
|
|
provider: "anthropic",
|
|
|
|
|
model: "\u001B[31mclaude-3-5-sonnet\nspoof",
|
|
|
|
|
});
|
|
|
|
|
const warning = warnSpy.mock.calls[0]?.[0] as string;
|
|
|
|
|
expect(warning).toContain('Falling back to "anthropic/claude-3-5-sonnet"');
|
|
|
|
|
expect(warning).not.toContain("\u001B");
|
|
|
|
|
expect(warning).not.toContain("\n");
|
|
|
|
|
} finally {
|
|
|
|
|
warnSpy.mockRestore();
|
|
|
|
|
setLoggerOverride(null);
|
|
|
|
|
resetLogger();
|
|
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
|
2026-01-25 14:54:48 +02:00
|
|
|
it("should use default provider/model if config is empty", () => {
|
2026-01-30 03:15:10 +01:00
|
|
|
const cfg: Partial<OpenClawConfig> = {};
|
2026-01-25 14:54:48 +02:00
|
|
|
const result = resolveConfiguredModelRef({
|
2026-01-30 03:15:10 +01:00
|
|
|
cfg: cfg as OpenClawConfig,
|
2026-01-25 14:54:48 +02:00
|
|
|
defaultProvider: "openai",
|
|
|
|
|
defaultModel: "gpt-4",
|
|
|
|
|
});
|
|
|
|
|
expect(result).toEqual({ provider: "openai", model: "gpt-4" });
|
2026-03-02 12:00:02 +08:00
|
|
|
});
|
2026-03-07 18:54:12 +00:00
|
|
|
|
|
|
|
|
it("should prefer configured custom provider when default provider is not in models.providers", () => {
|
|
|
|
|
const cfg: Partial<OpenClawConfig> = {
|
|
|
|
|
models: {
|
|
|
|
|
providers: {
|
|
|
|
|
n1n: {
|
|
|
|
|
baseUrl: "https://n1n.example.com",
|
|
|
|
|
models: [
|
|
|
|
|
{
|
|
|
|
|
id: "gpt-5.4",
|
|
|
|
|
name: "GPT 5.4",
|
|
|
|
|
reasoning: false,
|
|
|
|
|
input: ["text"],
|
|
|
|
|
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
|
|
|
|
contextWindow: 128000,
|
|
|
|
|
maxTokens: 4096,
|
|
|
|
|
},
|
|
|
|
|
],
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
const result = resolveConfiguredModelRef({
|
|
|
|
|
cfg: cfg as OpenClawConfig,
|
|
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
defaultModel: "claude-opus-4-6",
|
|
|
|
|
});
|
|
|
|
|
expect(result).toEqual({ provider: "n1n", model: "gpt-5.4" });
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("should keep default provider when it is in models.providers", () => {
|
|
|
|
|
const cfg: Partial<OpenClawConfig> = {
|
|
|
|
|
models: {
|
|
|
|
|
providers: {
|
|
|
|
|
anthropic: {
|
|
|
|
|
baseUrl: "https://api.anthropic.com",
|
|
|
|
|
models: [
|
|
|
|
|
{
|
|
|
|
|
id: "claude-opus-4-6",
|
|
|
|
|
name: "Claude Opus 4.6",
|
|
|
|
|
reasoning: true,
|
|
|
|
|
input: ["text", "image"],
|
|
|
|
|
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
|
|
|
|
contextWindow: 200000,
|
|
|
|
|
maxTokens: 4096,
|
|
|
|
|
},
|
|
|
|
|
],
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
const result = resolveConfiguredModelRef({
|
|
|
|
|
cfg: cfg as OpenClawConfig,
|
|
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
defaultModel: "claude-opus-4-6",
|
|
|
|
|
});
|
|
|
|
|
expect(result).toEqual({ provider: "anthropic", model: "claude-opus-4-6" });
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("should fall back to hardcoded default when no custom providers have models", () => {
|
|
|
|
|
const cfg: Partial<OpenClawConfig> = {
|
|
|
|
|
models: {
|
|
|
|
|
providers: {
|
|
|
|
|
"empty-provider": {
|
|
|
|
|
baseUrl: "https://example.com",
|
|
|
|
|
models: [],
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
const result = resolveConfiguredModelRef({
|
|
|
|
|
cfg: cfg as OpenClawConfig,
|
|
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
defaultModel: "claude-opus-4-6",
|
|
|
|
|
});
|
|
|
|
|
expect(result).toEqual({ provider: "anthropic", model: "claude-opus-4-6" });
|
|
|
|
|
});
|
2026-03-07 22:50:27 +00:00
|
|
|
|
|
|
|
|
it("should warn when specified model cannot be resolved and falls back to default", () => {
|
|
|
|
|
setLoggerOverride({ level: "silent", consoleLevel: "warn" });
|
|
|
|
|
const warnSpy = vi.spyOn(console, "warn").mockImplementation(() => {});
|
|
|
|
|
try {
|
|
|
|
|
const cfg: Partial<OpenClawConfig> = {
|
|
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
model: { primary: "openai/" },
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const result = resolveConfiguredModelRef({
|
|
|
|
|
cfg: cfg as OpenClawConfig,
|
|
|
|
|
defaultProvider: "anthropic",
|
|
|
|
|
defaultModel: "claude-opus-4-6",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(result).toEqual({ provider: "anthropic", model: "claude-opus-4-6" });
|
|
|
|
|
expect(warnSpy).toHaveBeenCalledWith(
|
|
|
|
|
expect.stringContaining('Falling back to default "anthropic/claude-opus-4-6"'),
|
|
|
|
|
);
|
|
|
|
|
} finally {
|
|
|
|
|
warnSpy.mockRestore();
|
|
|
|
|
setLoggerOverride(null);
|
|
|
|
|
resetLogger();
|
|
|
|
|
}
|
|
|
|
|
});
|
2026-03-02 12:00:02 +08:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe("resolveThinkingDefault", () => {
|
|
|
|
|
it("prefers per-model params.thinking over global thinkingDefault", () => {
|
|
|
|
|
const cfg = {
|
|
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
thinkingDefault: "low",
|
|
|
|
|
models: {
|
|
|
|
|
"anthropic/claude-opus-4-6": {
|
|
|
|
|
params: { thinking: "high" },
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
} as OpenClawConfig;
|
|
|
|
|
|
2026-03-02 06:40:42 +00:00
|
|
|
expect(resolveAnthropicOpusThinking(cfg)).toBe("high");
|
2026-03-02 04:27:26 +00:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("accepts per-model params.thinking=adaptive", () => {
|
|
|
|
|
const cfg = {
|
|
|
|
|
agents: {
|
|
|
|
|
defaults: {
|
|
|
|
|
models: {
|
|
|
|
|
"anthropic/claude-opus-4-6": {
|
|
|
|
|
params: { thinking: "adaptive" },
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
} as OpenClawConfig;
|
|
|
|
|
|
2026-03-02 06:40:42 +00:00
|
|
|
expect(resolveAnthropicOpusThinking(cfg)).toBe("adaptive");
|
2026-03-02 04:27:26 +00:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("defaults Anthropic Claude 4.6 models to adaptive", () => {
|
|
|
|
|
const cfg = {} as OpenClawConfig;
|
|
|
|
|
|
2026-03-02 06:40:42 +00:00
|
|
|
expect(resolveAnthropicOpusThinking(cfg)).toBe("adaptive");
|
2026-03-02 04:27:26 +00:00
|
|
|
|
|
|
|
|
expect(
|
|
|
|
|
resolveThinkingDefault({
|
|
|
|
|
cfg,
|
|
|
|
|
provider: "amazon-bedrock",
|
|
|
|
|
model: "us.anthropic.claude-sonnet-4-6-v1:0",
|
|
|
|
|
catalog: [
|
|
|
|
|
{
|
|
|
|
|
provider: "amazon-bedrock",
|
|
|
|
|
id: "us.anthropic.claude-sonnet-4-6-v1:0",
|
|
|
|
|
name: "Claude Sonnet 4.6",
|
|
|
|
|
reasoning: true,
|
|
|
|
|
},
|
|
|
|
|
],
|
|
|
|
|
}),
|
|
|
|
|
).toBe("adaptive");
|
2026-01-09 20:07:20 +01:00
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
});
|
2026-03-01 19:24:09 +05:30
|
|
|
|
|
|
|
|
describe("normalizeModelSelection", () => {
|
|
|
|
|
it("returns trimmed string for string input", () => {
|
|
|
|
|
expect(normalizeModelSelection("ollama/llama3.2:3b")).toBe("ollama/llama3.2:3b");
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("returns undefined for empty/whitespace string", () => {
|
|
|
|
|
expect(normalizeModelSelection("")).toBeUndefined();
|
|
|
|
|
expect(normalizeModelSelection(" ")).toBeUndefined();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("extracts primary from object", () => {
|
|
|
|
|
expect(normalizeModelSelection({ primary: "google/gemini-2.5-flash" })).toBe(
|
|
|
|
|
"google/gemini-2.5-flash",
|
|
|
|
|
);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("returns undefined for object without primary", () => {
|
|
|
|
|
expect(normalizeModelSelection({ fallbacks: ["a"] })).toBeUndefined();
|
|
|
|
|
expect(normalizeModelSelection({})).toBeUndefined();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("returns undefined for null/undefined/number", () => {
|
|
|
|
|
expect(normalizeModelSelection(undefined)).toBeUndefined();
|
|
|
|
|
expect(normalizeModelSelection(null)).toBeUndefined();
|
|
|
|
|
expect(normalizeModelSelection(42)).toBeUndefined();
|
|
|
|
|
});
|
|
|
|
|
});
|