* feat: add PDF analysis tool with native provider support
New `pdf` tool for analyzing PDF documents with model-powered analysis.
Architecture:
- Native PDF path: sends raw PDF bytes directly to providers that support
inline document input (Anthropic via DocumentBlockParam, Google Gemini
via inlineData with application/pdf MIME type)
- Extraction fallback: for providers without native PDF support, extracts
text via pdfjs-dist and rasterizes pages to images via @napi-rs/canvas,
then sends through the standard vision/text completion path
Key features:
- Single PDF (`pdf` param) or multiple PDFs (`pdfs` array, up to 10)
- Page range selection (`pages` param, e.g. "1-5", "1,3,7-9")
- Model override (`model` param) and file size limits (`maxBytesMb`)
- Auto-detects provider capability and falls back gracefully
- Same security patterns as image tool (SSRF guards, sandbox support,
local path roots, workspace-only policy)
Config (agents.defaults):
- pdfModel: primary/fallbacks (defaults to imageModel, then session model)
- pdfMaxBytesMb: max PDF file size (default: 10)
- pdfMaxPages: max pages to process (default: 20)
Model catalog:
- Extended ModelInputType to include "document" alongside "text"/"image"
- Added modelSupportsDocument() capability check
Files:
- src/agents/tools/pdf-tool.ts - main tool factory
- src/agents/tools/pdf-tool.helpers.ts - helpers (page range, config, etc.)
- src/agents/tools/pdf-native-providers.ts - direct API calls for Anthropic/Google
- src/agents/tools/pdf-tool.test.ts - 43 tests covering all paths
- Modified: model-catalog.ts, openclaw-tools.ts, config schema/types/labels/help
* fix: prepare pdf tool for merge (#31319) (thanks @tyler6204)
* feat(agents): support `thinkingDefault: "adaptive"` for Anthropic models
Anthropic's Opus 4.6 and Sonnet 4.6 support adaptive thinking where the
model dynamically decides when and how much to think. This is now
Anthropic's recommended mode and `budget_tokens` is deprecated on these
models.
Add "adaptive" as a valid thinking level:
- Config: `agents.defaults.thinkingDefault: "adaptive"`
- CLI: `/think adaptive` or `/think auto`
- Pi SDK mapping: "adaptive" → "medium" effort at the pi-agent-core
layer, which the Anthropic provider translates to
`thinking.type: "adaptive"` with `output_config.effort: "medium"`
- Provider fallbacks: OpenRouter and Google map "adaptive" to their
respective "medium" equivalents
Closes#30880
Made-with: Cursor
* style(changelog): format changelog with oxfmt
* test(types): fix strict typing in runtime/plugin-context tests
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
When sessions_spawn is called without runTimeoutSeconds, subagents
previously defaulted to 0 (no timeout). This adds a config key at
agents.defaults.subagents.runTimeoutSeconds so operators can set a
global default timeout for all subagent runs.
The agent-provided value still takes precedence when explicitly passed.
When neither the agent nor the config specifies a timeout, behavior is
unchanged (0 = no timeout), preserving backwards compatibility.
Updated for the subagent-spawn.ts refactor (logic moved from
sessions-spawn-tool.ts to spawnSubagentDirect).
Closes#19288
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The global `agents.defaults.thinkingDefault` forces a single thinking
level for all models. Users running multiple models with different
reasoning capabilities (e.g. Claude with extended thinking, GPT-4o
without, Gemini Flash with lightweight reasoning) cannot optimise the
thinking level per model.
Add an optional `thinkingDefault` field to `AgentModelEntryConfig` so
each entry under `agents.defaults.models` can declare its own default.
Resolution priority: per-model → global → catalog auto-detect.
Example config:
"models": {
"anthropic/claude-sonnet-4-20250514": { "thinkingDefault": "high" },
"openai/gpt-4o": { "thinkingDefault": "off" }
}
Co-authored-by: Cursor <cursoragent@cursor.com>
* 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)
* fix(ollama): add streaming config and fix OLLAMA_API_KEY env var support
Adds configurable streaming parameter to model configuration and sets streaming
to false by default for Ollama models. This addresses the corrupted response
issue caused by upstream SDK bug badlogic/pi-mono#1205 where interleaved
content/reasoning deltas in streaming responses cause garbled output.
Changes:
- Add streaming param to AgentModelEntryConfig type
- Set streaming: false default for Ollama models
- Add OLLAMA_API_KEY to envMap (was missing, preventing env var auth)
- Document streaming configuration in Ollama provider docs
- Add tests for Ollama model configuration
Users can now configure streaming per-model and Ollama authentication
via OLLAMA_API_KEY environment variable works correctly.
Fixes#8839
Related: badlogic/pi-mono#1205
* docs(ollama): use gpt-oss:20b as primary example
Updates documentation to use gpt-oss:20b as the primary example model
since it supports tool calling. The model examples now show:
- gpt-oss:20b as the primary recommended model (tool-capable)
- llama3.3 and qwen2.5-coder:32b as additional options
This provides users with a clear, working example that supports
OpenClaw's tool calling features.
* chore: remove unused vi import from ollama test
* feat(heartbeat): add accountId config option for multi-agent routing
Add optional accountId field to heartbeat configuration, allowing
multi-agent setups to explicitly specify which Telegram account
should be used for heartbeat delivery.
Previously, heartbeat delivery would use the accountId from the
session's deliveryContext. When a session had no prior conversation
history, heartbeats would default to the first/primary account
instead of the agent's intended bot.
Changes:
- Add accountId to HeartbeatSchema (zod-schema.agent-runtime.ts)
- Use heartbeat.accountId with fallback to session accountId (targets.ts)
Backward compatible: if accountId is not specified, behavior is unchanged.
Closes#8695
* fix: improve heartbeat accountId routing (#8702) (thanks @lsh411)
* fix: harden heartbeat accountId routing (#8702) (thanks @lsh411)
* fix: expose heartbeat accountId in status (#8702) (thanks @lsh411)
* chore: format status + heartbeat tests (#8702) (thanks @lsh411)
---------
Co-authored-by: m1 16 512 <m116512@m1ui-MacBookAir-2.local>
Co-authored-by: Gustavo Madeira Santana <gumadeiras@gmail.com>
* feat(config): add subagent default thinking
* fix: accept config subagents.thinking + stabilize test mocks (#7372) (thanks @tyler6204)
* fix: use findLast instead of clearAllMocks in test (#7372)
* fix: correct test assertions for tool result structure (#7372)
* fix: remove unnecessary type assertion after rebase
Add Mattermost as a supported messaging channel with bot API and WebSocket integration. Includes channel state tracking (tint, summary, details), multi-account support, and delivery target routing. Update documentation and tests to include Mattermost alongside existing channels.
