Files
openclaw/src/agents/model-selection.test.ts

732 lines
22 KiB
TypeScript
Raw Normal View History

import { describe, it, expect, vi } from "vitest";
import type { OpenClawConfig } from "../config/config.js";
import { resetLogger, setLoggerOverride } from "../logging/logger.js";
2026-01-09 05:27:54 +00:00
import {
buildAllowedModelSet,
inferUniqueProviderFromConfiguredModels,
2026-01-09 05:27:54 +00:00
parseModelRef,
buildModelAliasIndex,
normalizeModelSelection,
normalizeProviderId,
normalizeProviderIdForAuth,
modelKey,
resolveAllowedModelRef,
resolveConfiguredModelRef,
resolveThinkingDefault,
resolveModelRefFromString,
2026-01-09 05:27:54 +00:00
} from "./model-selection.js";
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,
});
}
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");
expect(normalizeProviderId("kimi-code")).toBe("kimi-coding");
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
});
});
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");
});
});
describe("parseModelRef", () => {
it("should parse full model refs", () => {
expect(parseModelRef("anthropic/claude-3-5-sonnet", "openai")).toEqual({
provider: "anthropic",
model: "claude-3-5-sonnet",
});
});
it("preserves nested model ids after provider prefix", () => {
expect(parseModelRef("nvidia/moonshotai/kimi-k2.5", "anthropic")).toEqual({
provider: "nvidia",
model: "moonshotai/kimi-k2.5",
});
});
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",
});
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",
});
});
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
});
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",
});
});
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({
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({
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({
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",
});
});
it("should return null for empty strings", () => {
expect(parseModelRef("", "anthropic")).toBeNull();
expect(parseModelRef(" ", "anthropic")).toBeNull();
2026-01-09 05:07:16 +00:00
});
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",
});
});
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",
});
});
it("should handle invalid slash usage", () => {
expect(parseModelRef("/", "anthropic")).toBeNull();
expect(parseModelRef("anthropic/", "anthropic")).toBeNull();
expect(parseModelRef("/model", "anthropic")).toBeNull();
});
});
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");
});
});
describe("buildModelAliasIndex", () => {
it("should build alias index from config", () => {
2026-01-30 03:15:10 +01:00
const cfg: Partial<OpenClawConfig> = {
agents: {
defaults: {
models: {
"anthropic/claude-3-5-sonnet": { alias: "fast" },
"openai/gpt-4o": { alias: "smart" },
},
},
},
};
const index = buildModelAliasIndex({
2026-01-30 03:15:10 +01:00
cfg: cfg as OpenClawConfig,
defaultProvider: "anthropic",
});
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"]);
});
});
describe("buildAllowedModelSet", () => {
it("keeps explicitly allowlisted models even when missing from bundled catalog", () => {
const result = buildAllowedModelSet({
cfg: EXPLICIT_ALLOWLIST_CONFIG,
catalog: BUNDLED_ALLOWLIST_CATALOG,
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({
cfg: EXPLICIT_ALLOWLIST_CONFIG,
catalog: BUNDLED_ALLOWLIST_CATALOG,
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" },
});
});
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" },
});
});
});
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,
});
expect(resolved?.ref).toEqual({ provider: "anthropic", model: "sonnet" });
expect(resolved?.alias).toBe("fast");
});
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" });
});
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");
});
});
describe("resolveConfiguredModelRef", () => {
it("should fall back to anthropic and warn if provider is missing for non-alias", () => {
setLoggerOverride({ level: "silent", consoleLevel: "warn" });
const warnSpy = vi.spyOn(console, "warn").mockImplementation(() => {});
try {
const cfg: Partial<OpenClawConfig> = {
agents: {
defaults: {
model: { primary: "claude-3-5-sonnet" },
},
},
};
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();
}
});
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();
}
});
it("should use default provider/model if config is empty", () => {
2026-01-30 03:15:10 +01:00
const cfg: Partial<OpenClawConfig> = {};
const result = resolveConfiguredModelRef({
2026-01-30 03:15:10 +01:00
cfg: cfg as OpenClawConfig,
defaultProvider: "openai",
defaultModel: "gpt-4",
});
expect(result).toEqual({ provider: "openai", model: "gpt-4" });
});
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" });
});
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();
}
});
});
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;
expect(resolveAnthropicOpusThinking(cfg)).toBe("high");
});
it("accepts per-model params.thinking=adaptive", () => {
const cfg = {
agents: {
defaults: {
models: {
"anthropic/claude-opus-4-6": {
params: { thinking: "adaptive" },
},
},
},
},
} as OpenClawConfig;
expect(resolveAnthropicOpusThinking(cfg)).toBe("adaptive");
});
it("defaults Anthropic Claude 4.6 models to adaptive", () => {
const cfg = {} as OpenClawConfig;
expect(resolveAnthropicOpusThinking(cfg)).toBe("adaptive");
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");
});
});
});
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();
});
});