* feat: add before_compaction and before_reset plugin hooks with session context
- Pass session messages to before_compaction hook
- Add before_reset plugin hook for /new and /reset commands
- Add sessionId to plugin hook agent context
* feat: extraBootstrapFiles config with glob pattern support
Add extraBootstrapFiles to agent defaults config, allowing glob patterns
(e.g. "projects/*/TOOLS.md") to auto-load project-level bootstrap files
into agent context every turn. Missing files silently skipped.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(status): show custom memory plugins as enabled, not unavailable
The status command probes memory availability using the built-in
memory-core manager. Custom memory plugins (e.g. via plugin slot)
can't be probed this way, so they incorrectly showed "unavailable".
Now they show "enabled (plugin X)" without the misleading label.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use async fs.glob and capture pre-compaction messages
- Replace globSync (node:fs) with fs.glob (node:fs/promises) to match
codebase conventions for async file operations
- Capture session.messages BEFORE replaceMessages(limited) so
before_compaction hook receives the full conversation history,
not the already-truncated list
* fix: resolve lint errors from CI (oxlint strict mode)
- Add void to fire-and-forget IIFE (no-floating-promises)
- Use String() for unknown catch params in template literals
- Add curly braces to single-statement if (curly rule)
* fix: resolve remaining CI lint errors in workspace.ts
- Remove `| string` from WorkspaceBootstrapFileName union (made all
typeof members redundant per no-redundant-type-constituents)
- Use type assertion for extra bootstrap file names
- Drop redundant await on fs.glob() AsyncIterable (await-thenable)
* fix: address Greptile review — path traversal guard + fs/promises import
- workspace.ts: use path.resolve() + traversal check in loadExtraBootstrapFiles()
- commands-core.ts: import fs from node:fs/promises, drop fs.promises prefix
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: resolve symlinks before workspace boundary check
Greptile correctly identified that symlinks inside the workspace could
point to files outside it, bypassing the path prefix check. Now uses
fs.realpath() to resolve symlinks before verifying the real path stays
within the workspace boundary.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address Greptile review — hook reliability and type safety
1. before_compaction: add compactingCount field so plugins know both
the full pre-compaction message count and the truncated count being
fed to the compaction LLM. Clarify semantics in comment.
2. loadExtraBootstrapFiles: use path.basename() for the name field
so "projects/quaid/TOOLS.md" maps to the known "TOOLS.md" type
instead of an invalid WorkspaceBootstrapFileName cast.
3. before_reset: fire the hook even when no session file exists.
Previously, short sessions without a persisted file would silently
skip the hook. Now fires with empty messages array so plugins
always know a reset occurred.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: validate bootstrap filenames and add compaction hook timeout
- Only load extra bootstrap files whose basename matches a recognized
workspace filename (AGENTS.md, TOOLS.md, etc.), preventing arbitrary
files from being injected into agent context.
- Wrap before_compaction hook in a 30-second Promise.race timeout so
misbehaving plugins cannot stall the compaction pipeline.
- Clarify hook comments: before_compaction is intentionally awaited
(plugins need messages before they're discarded) but bounded.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: make before_compaction non-blocking, add sessionFile to after_compaction
- before_compaction is now true fire-and-forget — no await, no timeout.
Plugins that need full conversation data should persist it themselves
and return quickly, or use after_compaction for async processing.
- after_compaction now includes sessionFile path so plugins can read
the full JSONL transcript asynchronously. All pre-compaction messages
are preserved on disk, eliminating the need to block compaction.
- Removes Promise.race timeout pattern that didn't actually cancel
slow hooks (just raced past them while they continued running).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add sessionFile to before_compaction for parallel processing
The session JSONL already has all messages on disk before compaction
starts. By providing sessionFile in before_compaction, plugins can
read and extract data in parallel with the compaction LLM call rather
than waiting for after_compaction. This is the optimal path for memory
plugins that need the full conversation history.
sessionFile is also kept on after_compaction for plugins that only
need to act after compaction completes (analytics, cleanup, etc.).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: move bootstrap extras into bundled hook
---------
Co-authored-by: Solomon Steadman <solstead@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Clawdbot <clawdbot@alfie.local>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* fix: defer gateway restart until all replies are sent
Fixes a race condition where gateway config changes (e.g., enabling
plugins via iMessage) trigger an immediate SIGUSR1 restart, killing the
iMessage RPC connection before replies are delivered.
Both restart paths (config watcher and RPC-triggered) now defer until
all queued operations, pending replies, and embedded agent runs complete
(polling every 500ms, 30s timeout). A shared emitGatewayRestart() guard
prevents double SIGUSR1 when both paths fire simultaneously.
Key changes:
- Dispatcher registry tracks active reply dispatchers globally
- markComplete() called in finally block for guaranteed cleanup
- Pre-restart deferral hook registered at gateway startup
- Centralized extractDeliveryInfo() for session key parsing
- Post-restart sentinel messages delivered directly (not via agent)
- config-patch distinguished from config-apply in sentinel kind
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: single-source gateway restart authorization
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* fix(agents): wait for agent idle before flushing pending tool results
When pi-agent-core's auto-retry mechanism handles overloaded/rate-limit
errors, it resolves waitForRetry() on assistant message receipt — before
tool execution completes in the retried agent loop. This causes the
attempt's finally block to call flushPendingToolResults() while tools
are still executing, inserting synthetic 'missing tool result' errors
and causing silent agent failures.
The fix adds a waitForIdle() call before the flush to ensure the agent's
retry loop (including tool execution) has fully completed.
Evidence from real session: tool call and synthetic error were only 53ms
apart — the tool never had a chance to execute before being flushed.
Root cause is in pi-agent-core's _resolveRetry() firing on message_end
instead of agent_end, but this workaround in OpenClaw prevents the
symptom without requiring an upstream fix.
Fixes#8643Fixes#13351
Refs #6682, #12595
* test: add tests for tool result flush race condition
Validates that:
- Real tool results are not replaced by synthetic errors when they arrive in time
- Flush correctly inserts synthetic errors for genuinely orphaned tool calls
- Flush is a no-op after real tool results have already been received
Refs #8643, #13748
* fix(agents): add waitForIdle to all flushPendingToolResults call sites
The original fix only covered the main run finally block, but there are
two additional call sites that can trigger flushPendingToolResults while
tools are still executing:
1. The catch block in attempt.ts (session setup error handler)
2. The finally block in compact.ts (compaction teardown)
Both now await agent.waitForIdle() with a 30s timeout before flushing,
matching the pattern already applied to the main finally block.
Production testing on VPS with debug logging confirmed these additional
paths can fire during sub-agent runs, producing spurious synthetic
'missing tool result' errors.
* fix(agents): centralize idle-wait flush and clear timeout handle
---------
Co-authored-by: Renue Development <dev@renuebyscience.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* Agents: allow gpt-5.3-codex-spark in fallback and thinking
* Fix: model picker issue for openai-codex/gpt-5.3-codex-spark
Fixed an issue in the model picker.
The UsageAccumulator sums cacheRead/cacheWrite across all API calls
within a single turn. With Anthropic prompt caching, each call reports
cacheRead ≈ current_context_size, so after N tool-call round-trips the
accumulated total becomes N × actual_context, which gets clamped to
contextWindow (200k) by deriveSessionTotalTokens().
Fix: track the most recent API call's cache fields separately and use
them in toNormalizedUsage() for context-size reporting. This makes
/status Context display accurate while preserving accumulated output
token counts.
Fixes#13698Fixes#13782
Co-authored-by: akari-musubi <259925157+akari-musubi@users.noreply.github.com>
Two fixes for Google Antigravity (Cloud Code Assist) reliability:
1. Forward-compat model fallback: pi-ai's model registry doesn't include
claude-opus-4-6-thinking. Add resolveAntigravityOpus46ForwardCompatModel()
that clones the opus-4-5 template so the correct api ("google-gemini-cli")
and baseUrl are preserved. Fixes#13765.
2. Fix thinking.signature rejection: The API returns Claude thinking blocks
without signatures, then rejects them on replay. The existing sanitizer
strips unsigned blocks, but the orphaned-user-message path in attempt.ts
bypassed it by reading directly from disk. Now applies
sanitizeAntigravityThinkingBlocks at that code path.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Move appendCacheTtlTimestamp() to after prompt + compaction retry
completes instead of before. The previous placement inserted a custom
entry (openclaw.cache-ttl) between compaction and the next prompt,
which broke pi-coding-agent's prepareCompaction() guard — the guard
only checks if the last entry is type 'compaction', and the cache-ttl
custom entry made it type 'custom', allowing an immediate second
compaction at very low token counts (e.g. 5,545 tokens) that nuked
all preserved context.
Fixes#9282
Relates to #12170
* fix: suggest /reset in context overflow error message
When the context window overflows, the error message now suggests
using /reset to clear session history, giving users an actionable
recovery path instead of a dead-end error.
Closes#12940
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: suggest /reset in context overflow error message (#12973) (thanks @RamiNoodle733)
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Rami Abdelrazzaq <RamiNoodle733@users.noreply.github.com>
* fix: use .js extension for ESM imports of RoutePeerKind
The imports incorrectly used .ts extension which doesn't resolve
with moduleResolution: NodeNext. Changed to .js and added 'type'
import modifier.
* fix tsconfig
* refactor: unify peer kind to ChatType, rename dm to direct
- Replace RoutePeerKind with ChatType throughout codebase
- Change 'dm' literal values to 'direct' in routing/session keys
- Keep backward compat: normalizeChatType accepts 'dm' -> 'direct'
- Add ChatType export to plugin-sdk, deprecate RoutePeerKind
- Update session key parsing to accept both 'dm' and 'direct' markers
- Update all channel monitors and extensions to use ChatType
BREAKING CHANGE: Session keys now use 'direct' instead of 'dm'.
Existing 'dm' keys still work via backward compat layer.
* fix tests
* test: update session key expectations for dmdirect migration
- Fix test expectations to expect :direct: in generated output
- Add explicit backward compat test for normalizeChatType('dm')
- Keep input test data with :dm: keys to verify backward compat
* fix: accept legacy 'dm' in session key parsing for backward compat
getDmHistoryLimitFromSessionKey now accepts both :dm: and :direct:
to ensure old session keys continue to work correctly.
* test: add explicit backward compat tests for dmdirect migration
- session-key.test.ts: verify both :dm: and :direct: keys are valid
- getDmHistoryLimitFromSessionKey: verify both formats work
* feat: backward compat for resetByType.dm config key
* test: skip unix-path Nix tests on Windows
* initial commit
* feat: implement deriveSessionTotalTokens function and update usage tests
* Added deriveSessionTotalTokens function to calculate total tokens based on usage and context tokens.
* Updated usage tests to include cases for derived session total tokens.
* Refactored session usage calculations in multiple files to utilize the new function for improved accuracy.
* fix: restore overflow truncation fallback + changelog/test hardening (#11551) (thanks @tyler6204)
* fix: gracefully handle oversized tool results causing context overflow
When a subagent reads a very large file or gets a huge tool result (e.g.,
gh pr diff on a massive PR), it can exceed the model's context window in
a single prompt. Auto-compaction can't help because there's no older
history to compact — just one giant tool result.
This adds two layers of defense:
1. Pre-emptive: Hard cap on tool result size (400K chars ≈ 100K tokens)
applied in the session tool result guard before persistence. This
prevents extremely large tool results from being stored in full,
regardless of model context window size.
2. Recovery: When context overflow is detected and compaction fails,
scan session messages for oversized tool results relative to the
model's actual context window (30% max share). If found, truncate
them in the session via branching (creating a new branch with
truncated content) and retry the prompt.
The truncation preserves the beginning of the content (most useful for
understanding what was read) and appends a notice explaining the
truncation and suggesting offset/limit parameters for targeted reads.
Includes comprehensive tests for:
- Text truncation with newline-boundary awareness
- Context-window-proportional size calculation
- In-memory message truncation
- Oversized detection heuristics
- Guard-level size capping during persistence
* fix: prep fixes for tool result truncation PR (#11579) (thanks @tyler6204)
* fix(errors): return clear billing error message instead of cryptic raw error (#8136)
When an LLM API provider returns a credit/billing-related error (HTTP 402,
insufficient credits, low balance, etc.), OpenClaw now shows a clear,
actionable message instead of passing through the raw/cryptic error text:
⚠️ API provider returned a billing error — your API key has run out of
credits or has an insufficient balance. Check your provider's billing
dashboard and top up or switch to a different API key.
Changes:
- formatAssistantErrorText: detect billing errors via isBillingErrorMessage()
and return a user-friendly message (placed before the generic HTTP/JSON
error fallthrough)
- sanitizeUserFacingText: same billing detection for the sanitization path
- pi-embedded-runner/run.ts: add billingFailure detection in the profile
exhaustion fallback, so the FailoverError message is billing-specific
- Added 3 new tests for credit balance, HTTP 402, and insufficient credits
* fix: extract billing error message to shared constant
Previously, overflowCompactionAttempted was a boolean flag set once, preventing
recovery when a single compaction wasn't enough. Change to a counter allowing up
to 3 attempts before giving up. Also add diagnostic logging on overflow events to
help debug early-overflow issues.
Fixes sessions that hit context overflow during long agentic turns with many tool
calls, where one compaction round isn't sufficient to bring context below limits.
- Introduced new properties for explicit message targeting and message tool disabling in the EmbeddedRunAttemptParams type.
- Updated cron job tests to validate best-effort delivery behavior and handling of delivery failures.
- Added logic to clear delivery settings when switching session targets in cron jobs.
- Improved the resolution of delivery failures and best-effort logic in the isolated agent's run function.
This update enhances the flexibility and reliability of delivery mechanisms in isolated cron jobs, ensuring better handling of message delivery scenarios.
- Updated isolated cron jobs to support new delivery modes: `announce` and `none`, improving output management.
- Refactored job configuration to remove legacy fields and streamline delivery settings.
- Enhanced the `CronJobEditor` UI to reflect changes in delivery options, including a new segmented control for delivery mode selection.
- Updated documentation to clarify the new delivery configurations and their implications for job execution.
- Improved tests to validate the new delivery behavior and ensure backward compatibility with legacy settings.
This update provides users with greater flexibility in managing how isolated jobs deliver their outputs, enhancing overall usability and clarity in job configurations.
