Files
openclaw/src/gateway/sessions-patch.ts
Tyler Yust b8f66c260d 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

360 lines
11 KiB
TypeScript

import { randomUUID } from "node:crypto";
import type { ModelCatalogEntry } from "../agents/model-catalog.js";
import type { OpenClawConfig } from "../config/config.js";
import type { SessionEntry } from "../config/sessions.js";
import { resolveDefaultAgentId } from "../agents/agent-scope.js";
import { resolveAllowedModelRef, resolveDefaultModelForAgent } from "../agents/model-selection.js";
import { normalizeGroupActivation } from "../auto-reply/group-activation.js";
import {
formatThinkingLevels,
formatXHighModelHint,
normalizeElevatedLevel,
normalizeReasoningLevel,
normalizeThinkLevel,
normalizeUsageDisplay,
supportsXHighThinking,
} from "../auto-reply/thinking.js";
import {
isSubagentSessionKey,
normalizeAgentId,
parseAgentSessionKey,
} from "../routing/session-key.js";
import { applyVerboseOverride, parseVerboseOverride } from "../sessions/level-overrides.js";
import { applyModelOverrideToSessionEntry } from "../sessions/model-overrides.js";
import { normalizeSendPolicy } from "../sessions/send-policy.js";
import { parseSessionLabel } from "../sessions/session-label.js";
import {
ErrorCodes,
type ErrorShape,
errorShape,
type SessionsPatchParams,
} from "./protocol/index.js";
function invalid(message: string): { ok: false; error: ErrorShape } {
return { ok: false, error: errorShape(ErrorCodes.INVALID_REQUEST, message) };
}
function normalizeExecHost(raw: string): "sandbox" | "gateway" | "node" | undefined {
const normalized = raw.trim().toLowerCase();
if (normalized === "sandbox" || normalized === "gateway" || normalized === "node") {
return normalized;
}
return undefined;
}
function normalizeExecSecurity(raw: string): "deny" | "allowlist" | "full" | undefined {
const normalized = raw.trim().toLowerCase();
if (normalized === "deny" || normalized === "allowlist" || normalized === "full") {
return normalized;
}
return undefined;
}
function normalizeExecAsk(raw: string): "off" | "on-miss" | "always" | undefined {
const normalized = raw.trim().toLowerCase();
if (normalized === "off" || normalized === "on-miss" || normalized === "always") {
return normalized;
}
return undefined;
}
export async function applySessionsPatchToStore(params: {
cfg: OpenClawConfig;
store: Record<string, SessionEntry>;
storeKey: string;
patch: SessionsPatchParams;
loadGatewayModelCatalog?: () => Promise<ModelCatalogEntry[]>;
}): Promise<{ ok: true; entry: SessionEntry } | { ok: false; error: ErrorShape }> {
const { cfg, store, storeKey, patch } = params;
const now = Date.now();
const parsedAgent = parseAgentSessionKey(storeKey);
const sessionAgentId = normalizeAgentId(parsedAgent?.agentId ?? resolveDefaultAgentId(cfg));
const resolvedDefault = resolveDefaultModelForAgent({ cfg, agentId: sessionAgentId });
const existing = store[storeKey];
const next: SessionEntry = existing
? {
...existing,
updatedAt: Math.max(existing.updatedAt ?? 0, now),
}
: { sessionId: randomUUID(), updatedAt: now };
if ("spawnedBy" in patch) {
const raw = patch.spawnedBy;
if (raw === null) {
if (existing?.spawnedBy) {
return invalid("spawnedBy cannot be cleared once set");
}
} else if (raw !== undefined) {
const trimmed = String(raw).trim();
if (!trimmed) {
return invalid("invalid spawnedBy: empty");
}
if (!isSubagentSessionKey(storeKey)) {
return invalid("spawnedBy is only supported for subagent:* sessions");
}
if (existing?.spawnedBy && existing.spawnedBy !== trimmed) {
return invalid("spawnedBy cannot be changed once set");
}
next.spawnedBy = trimmed;
}
}
if ("spawnDepth" in patch) {
const raw = patch.spawnDepth;
if (raw === null) {
if (typeof existing?.spawnDepth === "number") {
return invalid("spawnDepth cannot be cleared once set");
}
} else if (raw !== undefined) {
if (!isSubagentSessionKey(storeKey)) {
return invalid("spawnDepth is only supported for subagent:* sessions");
}
const numeric = Number(raw);
if (!Number.isInteger(numeric) || numeric < 0) {
return invalid("invalid spawnDepth (use an integer >= 0)");
}
const normalized = numeric;
if (typeof existing?.spawnDepth === "number" && existing.spawnDepth !== normalized) {
return invalid("spawnDepth cannot be changed once set");
}
next.spawnDepth = normalized;
}
}
if ("label" in patch) {
const raw = patch.label;
if (raw === null) {
delete next.label;
} else if (raw !== undefined) {
const parsed = parseSessionLabel(raw);
if (!parsed.ok) {
return invalid(parsed.error);
}
for (const [key, entry] of Object.entries(store)) {
if (key === storeKey) {
continue;
}
if (entry?.label === parsed.label) {
return invalid(`label already in use: ${parsed.label}`);
}
}
next.label = parsed.label;
}
}
if ("thinkingLevel" in patch) {
const raw = patch.thinkingLevel;
if (raw === null) {
// Clear the override and fall back to model default
delete next.thinkingLevel;
} else if (raw !== undefined) {
const normalized = normalizeThinkLevel(String(raw));
if (!normalized) {
const hintProvider = existing?.providerOverride?.trim() || resolvedDefault.provider;
const hintModel = existing?.modelOverride?.trim() || resolvedDefault.model;
return invalid(
`invalid thinkingLevel (use ${formatThinkingLevels(hintProvider, hintModel, "|")})`,
);
}
next.thinkingLevel = normalized;
}
}
if ("verboseLevel" in patch) {
const raw = patch.verboseLevel;
const parsed = parseVerboseOverride(raw);
if (!parsed.ok) {
return invalid(parsed.error);
}
applyVerboseOverride(next, parsed.value);
}
if ("reasoningLevel" in patch) {
const raw = patch.reasoningLevel;
if (raw === null) {
delete next.reasoningLevel;
} else if (raw !== undefined) {
const normalized = normalizeReasoningLevel(String(raw));
if (!normalized) {
return invalid('invalid reasoningLevel (use "on"|"off"|"stream")');
}
if (normalized === "off") {
delete next.reasoningLevel;
} else {
next.reasoningLevel = normalized;
}
}
}
if ("responseUsage" in patch) {
const raw = patch.responseUsage;
if (raw === null) {
delete next.responseUsage;
} else if (raw !== undefined) {
const normalized = normalizeUsageDisplay(String(raw));
if (!normalized) {
return invalid('invalid responseUsage (use "off"|"tokens"|"full")');
}
if (normalized === "off") {
delete next.responseUsage;
} else {
next.responseUsage = normalized;
}
}
}
if ("elevatedLevel" in patch) {
const raw = patch.elevatedLevel;
if (raw === null) {
delete next.elevatedLevel;
} else if (raw !== undefined) {
const normalized = normalizeElevatedLevel(String(raw));
if (!normalized) {
return invalid('invalid elevatedLevel (use "on"|"off"|"ask"|"full")');
}
// Persist "off" explicitly so patches can override defaults.
next.elevatedLevel = normalized;
}
}
if ("execHost" in patch) {
const raw = patch.execHost;
if (raw === null) {
delete next.execHost;
} else if (raw !== undefined) {
const normalized = normalizeExecHost(String(raw));
if (!normalized) {
return invalid('invalid execHost (use "sandbox"|"gateway"|"node")');
}
next.execHost = normalized;
}
}
if ("execSecurity" in patch) {
const raw = patch.execSecurity;
if (raw === null) {
delete next.execSecurity;
} else if (raw !== undefined) {
const normalized = normalizeExecSecurity(String(raw));
if (!normalized) {
return invalid('invalid execSecurity (use "deny"|"allowlist"|"full")');
}
next.execSecurity = normalized;
}
}
if ("execAsk" in patch) {
const raw = patch.execAsk;
if (raw === null) {
delete next.execAsk;
} else if (raw !== undefined) {
const normalized = normalizeExecAsk(String(raw));
if (!normalized) {
return invalid('invalid execAsk (use "off"|"on-miss"|"always")');
}
next.execAsk = normalized;
}
}
if ("execNode" in patch) {
const raw = patch.execNode;
if (raw === null) {
delete next.execNode;
} else if (raw !== undefined) {
const trimmed = String(raw).trim();
if (!trimmed) {
return invalid("invalid execNode: empty");
}
next.execNode = trimmed;
}
}
if ("model" in patch) {
const raw = patch.model;
if (raw === null) {
applyModelOverrideToSessionEntry({
entry: next,
selection: {
provider: resolvedDefault.provider,
model: resolvedDefault.model,
isDefault: true,
},
});
} else if (raw !== undefined) {
const trimmed = String(raw).trim();
if (!trimmed) {
return invalid("invalid model: empty");
}
if (!params.loadGatewayModelCatalog) {
return {
ok: false,
error: errorShape(ErrorCodes.UNAVAILABLE, "model catalog unavailable"),
};
}
const catalog = await params.loadGatewayModelCatalog();
const resolved = resolveAllowedModelRef({
cfg,
catalog,
raw: trimmed,
defaultProvider: resolvedDefault.provider,
defaultModel: resolvedDefault.model,
});
if ("error" in resolved) {
return invalid(resolved.error);
}
const isDefault =
resolved.ref.provider === resolvedDefault.provider &&
resolved.ref.model === resolvedDefault.model;
applyModelOverrideToSessionEntry({
entry: next,
selection: {
provider: resolved.ref.provider,
model: resolved.ref.model,
isDefault,
},
});
}
}
if (next.thinkingLevel === "xhigh") {
const effectiveProvider = next.providerOverride ?? resolvedDefault.provider;
const effectiveModel = next.modelOverride ?? resolvedDefault.model;
if (!supportsXHighThinking(effectiveProvider, effectiveModel)) {
if ("thinkingLevel" in patch) {
return invalid(`thinkingLevel "xhigh" is only supported for ${formatXHighModelHint()}`);
}
next.thinkingLevel = "high";
}
}
if ("sendPolicy" in patch) {
const raw = patch.sendPolicy;
if (raw === null) {
delete next.sendPolicy;
} else if (raw !== undefined) {
const normalized = normalizeSendPolicy(String(raw));
if (!normalized) {
return invalid('invalid sendPolicy (use "allow"|"deny")');
}
next.sendPolicy = normalized;
}
}
if ("groupActivation" in patch) {
const raw = patch.groupActivation;
if (raw === null) {
delete next.groupActivation;
} else if (raw !== undefined) {
const normalized = normalizeGroupActivation(String(raw));
if (!normalized) {
return invalid('invalid groupActivation (use "mention"|"always")');
}
next.groupActivation = normalized;
}
}
store[storeKey] = next;
return { ok: true, entry: next };
}