* 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)
275 lines
11 KiB
TypeScript
275 lines
11 KiB
TypeScript
import type { ChannelId } from "../channels/plugins/types.js";
|
||
import type {
|
||
BlockStreamingChunkConfig,
|
||
BlockStreamingCoalesceConfig,
|
||
HumanDelayConfig,
|
||
TypingMode,
|
||
} from "./types.base.js";
|
||
import type {
|
||
SandboxBrowserSettings,
|
||
SandboxDockerSettings,
|
||
SandboxPruneSettings,
|
||
} from "./types.sandbox.js";
|
||
import type { MemorySearchConfig } from "./types.tools.js";
|
||
|
||
export type AgentModelEntryConfig = {
|
||
alias?: string;
|
||
/** Provider-specific API parameters (e.g., GLM-4.7 thinking mode). */
|
||
params?: Record<string, unknown>;
|
||
/** Enable streaming for this model (default: true, false for Ollama to avoid SDK issue #1205). */
|
||
streaming?: boolean;
|
||
};
|
||
|
||
export type AgentModelListConfig = {
|
||
primary?: string;
|
||
fallbacks?: string[];
|
||
};
|
||
|
||
export type AgentContextPruningConfig = {
|
||
mode?: "off" | "cache-ttl";
|
||
/** TTL to consider cache expired (duration string, default unit: minutes). */
|
||
ttl?: string;
|
||
keepLastAssistants?: number;
|
||
softTrimRatio?: number;
|
||
hardClearRatio?: number;
|
||
minPrunableToolChars?: number;
|
||
tools?: {
|
||
allow?: string[];
|
||
deny?: string[];
|
||
};
|
||
softTrim?: {
|
||
maxChars?: number;
|
||
headChars?: number;
|
||
tailChars?: number;
|
||
};
|
||
hardClear?: {
|
||
enabled?: boolean;
|
||
placeholder?: string;
|
||
};
|
||
};
|
||
|
||
export type CliBackendConfig = {
|
||
/** CLI command to execute (absolute path or on PATH). */
|
||
command: string;
|
||
/** Base args applied to every invocation. */
|
||
args?: string[];
|
||
/** Output parsing mode (default: json). */
|
||
output?: "json" | "text" | "jsonl";
|
||
/** Output parsing mode when resuming a CLI session. */
|
||
resumeOutput?: "json" | "text" | "jsonl";
|
||
/** Prompt input mode (default: arg). */
|
||
input?: "arg" | "stdin";
|
||
/** Max prompt length for arg mode (if exceeded, stdin is used). */
|
||
maxPromptArgChars?: number;
|
||
/** Extra env vars injected for this CLI. */
|
||
env?: Record<string, string>;
|
||
/** Env vars to remove before launching this CLI. */
|
||
clearEnv?: string[];
|
||
/** Flag used to pass model id (e.g. --model). */
|
||
modelArg?: string;
|
||
/** Model aliases mapping (config model id → CLI model id). */
|
||
modelAliases?: Record<string, string>;
|
||
/** Flag used to pass session id (e.g. --session-id). */
|
||
sessionArg?: string;
|
||
/** Extra args used when resuming a session (use {sessionId} placeholder). */
|
||
sessionArgs?: string[];
|
||
/** Alternate args to use when resuming a session (use {sessionId} placeholder). */
|
||
resumeArgs?: string[];
|
||
/** When to pass session ids. */
|
||
sessionMode?: "always" | "existing" | "none";
|
||
/** JSON fields to read session id from (in order). */
|
||
sessionIdFields?: string[];
|
||
/** Flag used to pass system prompt. */
|
||
systemPromptArg?: string;
|
||
/** System prompt behavior (append vs replace). */
|
||
systemPromptMode?: "append" | "replace";
|
||
/** When to send system prompt. */
|
||
systemPromptWhen?: "first" | "always" | "never";
|
||
/** Flag used to pass image paths. */
|
||
imageArg?: string;
|
||
/** How to pass multiple images. */
|
||
imageMode?: "repeat" | "list";
|
||
/** Serialize runs for this CLI. */
|
||
serialize?: boolean;
|
||
};
|
||
|
||
export type AgentDefaultsConfig = {
|
||
/** Primary model and fallbacks (provider/model). */
|
||
model?: AgentModelListConfig;
|
||
/** Optional image-capable model and fallbacks (provider/model). */
|
||
imageModel?: AgentModelListConfig;
|
||
/** Model catalog with optional aliases (full provider/model keys). */
|
||
models?: Record<string, AgentModelEntryConfig>;
|
||
/** Agent working directory (preferred). Used as the default cwd for agent runs. */
|
||
workspace?: string;
|
||
/** Optional repository root for system prompt runtime line (overrides auto-detect). */
|
||
repoRoot?: string;
|
||
/** Skip bootstrap (BOOTSTRAP.md creation, etc.) for pre-configured deployments. */
|
||
skipBootstrap?: boolean;
|
||
/** Max chars for injected bootstrap files before truncation (default: 20000). */
|
||
bootstrapMaxChars?: number;
|
||
/** Max total chars across all injected bootstrap files (default: 24000). */
|
||
bootstrapTotalMaxChars?: number;
|
||
/** Optional IANA timezone for the user (used in system prompt; defaults to host timezone). */
|
||
userTimezone?: string;
|
||
/** Time format in system prompt: auto (OS preference), 12-hour, or 24-hour. */
|
||
timeFormat?: "auto" | "12" | "24";
|
||
/**
|
||
* Envelope timestamp timezone: "utc" (default), "local", "user", or an IANA timezone string.
|
||
*/
|
||
envelopeTimezone?: string;
|
||
/**
|
||
* Include absolute timestamps in message envelopes ("on" | "off", default: "on").
|
||
*/
|
||
envelopeTimestamp?: "on" | "off";
|
||
/**
|
||
* Include elapsed time in message envelopes ("on" | "off", default: "on").
|
||
*/
|
||
envelopeElapsed?: "on" | "off";
|
||
/** Optional context window cap (used for runtime estimates + status %). */
|
||
contextTokens?: number;
|
||
/** Optional CLI backends for text-only fallback (claude-cli, etc.). */
|
||
cliBackends?: Record<string, CliBackendConfig>;
|
||
/** Opt-in: prune old tool results from the LLM context to reduce token usage. */
|
||
contextPruning?: AgentContextPruningConfig;
|
||
/** Compaction tuning and pre-compaction memory flush behavior. */
|
||
compaction?: AgentCompactionConfig;
|
||
/** Vector memory search configuration (per-agent overrides supported). */
|
||
memorySearch?: MemorySearchConfig;
|
||
/** Default thinking level when no /think directive is present. */
|
||
thinkingDefault?: "off" | "minimal" | "low" | "medium" | "high" | "xhigh";
|
||
/** Default verbose level when no /verbose directive is present. */
|
||
verboseDefault?: "off" | "on" | "full";
|
||
/** Default elevated level when no /elevated directive is present. */
|
||
elevatedDefault?: "off" | "on" | "ask" | "full";
|
||
/** Default block streaming level when no override is present. */
|
||
blockStreamingDefault?: "off" | "on";
|
||
/**
|
||
* Block streaming boundary:
|
||
* - "text_end": end of each assistant text content block (before tool calls)
|
||
* - "message_end": end of the whole assistant message (may include tool blocks)
|
||
*/
|
||
blockStreamingBreak?: "text_end" | "message_end";
|
||
/** Soft block chunking for streamed replies (min/max chars, prefer paragraph/newline). */
|
||
blockStreamingChunk?: BlockStreamingChunkConfig;
|
||
/**
|
||
* Block reply coalescing (merge streamed chunks before send).
|
||
* idleMs: wait time before flushing when idle.
|
||
*/
|
||
blockStreamingCoalesce?: BlockStreamingCoalesceConfig;
|
||
/** Human-like delay between block replies. */
|
||
humanDelay?: HumanDelayConfig;
|
||
timeoutSeconds?: number;
|
||
/** Max inbound media size in MB for agent-visible attachments (text note or future image attach). */
|
||
mediaMaxMb?: number;
|
||
typingIntervalSeconds?: number;
|
||
/** Typing indicator start mode (never|instant|thinking|message). */
|
||
typingMode?: TypingMode;
|
||
/** Periodic background heartbeat runs. */
|
||
heartbeat?: {
|
||
/** Heartbeat interval (duration string, default unit: minutes; default: 30m). */
|
||
every?: string;
|
||
/** Optional active-hours window (local time); heartbeats run only inside this window. */
|
||
activeHours?: {
|
||
/** Start time (24h, HH:MM). Inclusive. */
|
||
start?: string;
|
||
/** End time (24h, HH:MM). Exclusive. Use "24:00" for end-of-day. */
|
||
end?: string;
|
||
/** Timezone for the window ("user", "local", or IANA TZ id). Default: "user". */
|
||
timezone?: string;
|
||
};
|
||
/** Heartbeat model override (provider/model). */
|
||
model?: string;
|
||
/** Session key for heartbeat runs ("main" or explicit session key). */
|
||
session?: string;
|
||
/** Delivery target ("last", "none", or a channel id). */
|
||
target?: "last" | "none" | ChannelId;
|
||
/** Optional delivery override (E.164 for WhatsApp, chat id for Telegram). */
|
||
to?: string;
|
||
/** Optional account id for multi-account channels. */
|
||
accountId?: string;
|
||
/** Override the heartbeat prompt body (default: "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK."). */
|
||
prompt?: string;
|
||
/** Max chars allowed after HEARTBEAT_OK before delivery (default: 30). */
|
||
ackMaxChars?: number;
|
||
/**
|
||
* When enabled, deliver the model's reasoning payload for heartbeat runs (when available)
|
||
* as a separate message prefixed with `Reasoning:` (same as `/reasoning on`).
|
||
*
|
||
* Default: false (only the final heartbeat payload is delivered).
|
||
*/
|
||
includeReasoning?: boolean;
|
||
};
|
||
/** Max concurrent agent runs across all conversations. Default: 1 (sequential). */
|
||
maxConcurrent?: number;
|
||
/** Sub-agent defaults (spawned via sessions_spawn). */
|
||
subagents?: {
|
||
/** Max concurrent sub-agent runs (global lane: "subagent"). Default: 1. */
|
||
maxConcurrent?: number;
|
||
/** Maximum depth allowed for sessions_spawn chains. Default behavior: 1 (no nested spawns). */
|
||
maxSpawnDepth?: number;
|
||
/** Maximum active children a single requester session may spawn. Default behavior: 5. */
|
||
maxChildrenPerAgent?: number;
|
||
/** Auto-archive sub-agent sessions after N minutes (default: 60). */
|
||
archiveAfterMinutes?: number;
|
||
/** Default model selection for spawned sub-agents (string or {primary,fallbacks}). */
|
||
model?: string | { primary?: string; fallbacks?: string[] };
|
||
/** Default thinking level for spawned sub-agents (e.g. "off", "low", "medium", "high"). */
|
||
thinking?: string;
|
||
};
|
||
/** Optional sandbox settings for non-main sessions. */
|
||
sandbox?: {
|
||
/** Enable sandboxing for sessions. */
|
||
mode?: "off" | "non-main" | "all";
|
||
/**
|
||
* Agent workspace access inside the sandbox.
|
||
* - "none": do not mount the agent workspace into the container; use a sandbox workspace under workspaceRoot
|
||
* - "ro": mount the agent workspace read-only; disables write/edit tools
|
||
* - "rw": mount the agent workspace read/write; enables write/edit tools
|
||
*/
|
||
workspaceAccess?: "none" | "ro" | "rw";
|
||
/**
|
||
* Session tools visibility for sandboxed sessions.
|
||
* - "spawned": only allow session tools to target sessions spawned from this session (default)
|
||
* - "all": allow session tools to target any session
|
||
*/
|
||
sessionToolsVisibility?: "spawned" | "all";
|
||
/** Container/workspace scope for sandbox isolation. */
|
||
scope?: "session" | "agent" | "shared";
|
||
/** Legacy alias for scope ("session" when true, "shared" when false). */
|
||
perSession?: boolean;
|
||
/** Root directory for sandbox workspaces. */
|
||
workspaceRoot?: string;
|
||
/** Docker-specific sandbox settings. */
|
||
docker?: SandboxDockerSettings;
|
||
/** Optional sandboxed browser settings. */
|
||
browser?: SandboxBrowserSettings;
|
||
/** Auto-prune sandbox containers. */
|
||
prune?: SandboxPruneSettings;
|
||
};
|
||
};
|
||
|
||
export type AgentCompactionMode = "default" | "safeguard";
|
||
|
||
export type AgentCompactionConfig = {
|
||
/** Compaction summarization mode. */
|
||
mode?: AgentCompactionMode;
|
||
/** Minimum reserve tokens enforced for Pi compaction (0 disables the floor). */
|
||
reserveTokensFloor?: number;
|
||
/** Max share of context window for history during safeguard pruning (0.1–0.9, default 0.5). */
|
||
maxHistoryShare?: number;
|
||
/** Pre-compaction memory flush (agentic turn). Default: enabled. */
|
||
memoryFlush?: AgentCompactionMemoryFlushConfig;
|
||
};
|
||
|
||
export type AgentCompactionMemoryFlushConfig = {
|
||
/** Enable the pre-compaction memory flush (default: true). */
|
||
enabled?: boolean;
|
||
/** Run the memory flush when context is within this many tokens of the compaction threshold. */
|
||
softThresholdTokens?: number;
|
||
/** User prompt used for the memory flush turn (NO_REPLY is enforced if missing). */
|
||
prompt?: string;
|
||
/** System prompt appended for the memory flush turn. */
|
||
systemPrompt?: string;
|
||
};
|