fix(subagent): harden read-tool overflow guards and sticky reply threading by tyler6204 · Pull Request #19508 · openclaw/openclaw

tyler6204 · 2026-02-17T22:04:06Z

Summary

Improve subagent reliability under heavy tool output and keep chunked replies threaded consistently across channels.

Changes

Prevent premature agent.wait completion by deferring transient lifecycle error snapshots with a short grace window in gateway agent-job tracking.
Add PI-embedded pre-call tool-result context guarding that compacts oldest tool results first, truncates oversized tool results, and preserves legacy role: "tool" support.
Account for tool-result metadata (details) in context budgeting and clear details on compacted tool results so compaction actually frees context.
Strip duplicated read truncation payloads (details.truncation.content) from read tool results before persistence/LLM context use.
Make read auto-page across chunks when no explicit limit is provided, and scale read output budget from model contextWindow.
Keep reply IDs/reply tags sticky across streamed/chunked assistant output so all chunks stay attached to the same parent message.
Propagate replyToId through shared outbound delivery and channel adapters for consistent behavior across Discord, Telegram, iMessage, Matrix, and BlueBubbles.
Normalize leading [[reply_to:<id>]] tags on iMessage outbound text so native replies target the intended message.
Extend system prompt guidance so subagents recover from compacted/truncated tool output by re-reading smaller sections instead of full-file reads.
Improve session display-name formatting to avoid duplicate prefixes in UI.
Update pre-commit hook behavior to avoid Bash mapfile portability issues.
Add/update changelog entries for all user-visible behavior changes (including thanks to @tyler6204).

Testing

Added/updated unit/integration/e2e coverage for tool-result context guarding and compaction behavior (including oversized details payloads).
Added/updated coverage for read-tool auto-paging, capped continuation hints, and context-window-aware read budgeting.
Added/updated coverage for sticky reply threading and reply-tag propagation across chunked sends.
Validated overflow repro paths with repeated large read/exec scenarios to confirm guard behavior differences and fixes.

Greptile Summary

This PR significantly improves subagent reliability under heavy tool output and ensures reply threading consistency across all messaging channels. The implementation introduces three major improvements: (1) pre-call tool-result context guarding that compacts oldest results first and strips oversized details payloads to prevent context overflow, (2) adaptive read-tool paging that automatically chunks large files based on model context windows, and (3) sticky reply threading that maintains replyToId across all chunks in Discord, Telegram, iMessage, Matrix, and BlueBubbles.

Key changes:

New tool-result-context-guard.ts implements context budgeting with oldest-first compaction and per-result size limits
Read tool strips duplicated truncation content from details and auto-pages when no explicit limit is provided
Reply IDs now propagate through all outbound delivery paths via overrides parameter
Agent lifecycle adds 15s grace window for transient error events before marking runs as failed
System prompt updated to guide recovery from compacted tool results
Pre-commit hook refactored to avoid Bash mapfile for macOS compatibility

Testing: Comprehensive test coverage added for context guard behavior, read-tool adaptive paging, and sticky reply threading across channels.

Confidence Score: 4/5

This PR is safe to merge with thorough testing recommended for the reply threading changes
Score reflects solid implementation with comprehensive test coverage. The tool-result context guard logic is well-designed with proper oldest-first compaction. Read-tool auto-paging correctly handles adaptive budgets. Reply threading changes are consistent across all channels. Minor concerns about error handling in Telegram sticky replies and the 15s grace window potentially masking real errors, but these are mitigated by existing tests and careful implementation.
Pay close attention to src/telegram/bot/delivery.ts for sticky reply behavior under partial failures, and src/gateway/server-methods/agent-job.ts to ensure the 15s error grace window doesn't mask legitimate failures

_{Last reviewed commit: 71fd991}

greptile-apps

_{34 files reviewed, 1 comment}

_{Edit Code Review Agent Settings | Greptile}

greptile-apps · 2026-02-17T22:12:02Z

src/telegram/bot/delivery.ts

+    const replyToMessageIdForPayload =
+      replyToId && (replyToMode === "all" || !hasReplied) ? replyToId : undefined;


check that this sticky reply behavior works correctly if some chunks succeed and others fail - replyToMessageIdForPayload is computed once and won't change even if an error occurs mid-loop

Prompt To Fix With AI

This is a comment left during a code review. Path: src/telegram/bot/delivery.ts Line: 107:108 Comment: check that this sticky reply behavior works correctly if some chunks succeed and others fail - `replyToMessageIdForPayload` is computed once and won't change even if an error occurs mid-loop How can I resolve this? If you propose a fix, please make it concise.

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 71fd991552

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-02-17T22:12:50Z

src/agents/pi-tools.read.ts

+    if (aggregatedText && aggregatedBytes + nextBytes > params.maxBytes) {
+      capped = true;
+      continuationOffset = nextOffset;
+      break;


Enforce read cap before appending first oversized page

The adaptive paging cap only triggers when aggregatedText is already non-empty, so an oversized first page is always appended. In large files where page 1 alone exceeds maxBytes, this returns far more than the configured budget (and can still add a "capped" notice), which undermines the overflow protection this change is meant to provide.

Useful? React with 👍 / 👎.

chatgpt-codex-connector · 2026-02-17T22:12:50Z

src/agents/pi-embedded-runner/tool-result-context-guard.ts

+  if (msg.role === "assistant") {
+    let chars = 0;
+    const content = (msg as { content?: unknown }).content;
+    if (Array.isArray(content)) {


Count assistant string content in context estimates

estimateMessageChars only accounts for assistant content when it is an array of blocks; assistant messages with string content are treated as zero length. That causes underestimation of prompt size, so the new guard may skip compaction/truncation even when context is actually over budget.

Useful? React with 👍 / 👎.

…tyler6204

…tyler6204)

…T_ID The run.skill-filter test was mocking ../../routing/session-key.js with only buildAgentMainSessionKey and normalizeAgentId, but the module also exports DEFAULT_ACCOUNT_ID which is required transitively by src/web/auth-store.ts. Switch to importOriginal pattern so all real exports are preserved alongside the mocked functions.

…l outputs and improving character estimation for message truncation. This includes a new function to create legacy tool results and updates to existing functions to better manage context overflow scenarios.

…ns and tests. This includes modifications to prepend or rewrite reply tags based on provided replyToId, ensuring proper message formatting for replies.

…cky reply context for chunked messages. This includes preserving reply references in Discord, Telegram, and iMessage, ensuring that follow-up messages maintain their intended reply targets. Additionally, improve handling of reply tags in system prompts and tests to support consistent reply behavior.

…unks when no explicit limit is provided, scaling output budget based on model context window. Additionally, add tests for adaptive reading behavior and capped continuation guidance for large outputs. Update related functions to support these features.

…l details payloads during compaction, ensuring repeated read calls do not bypass context limits. Introduce new utility functions for handling truncation content and enhance character estimation for tool results. Add tests to validate the removal of excessive details in context overflow scenarios.

… flag to track if a text chunk was sent. This ensures that replies are only marked as delivered when a text chunk has been successfully sent, improving the accuracy of reply handling in both channels.

…tyler6204

…tyler6204)

@obviyus

* Revert "fix(gateway): set explicit chat timeouts for mesh gateway calls" This reverts commit c529e60. * Revert "fix: capture init script exit codes instead of swallowing via pipe" This reverts commit 8b14052. * Revert "feat(docker): add init script support via /openclaw-init.d/" This reverts commit 53af9f7. * Revert "Agents: improve Windows scaffold helpers for venture studio" This reverts commit b6d934c. * chore: Fix types in tests 1/N. * chore: Fix types in tests 2/N. * Revert "fix: remove stderr suppression so install failures are visible in build logs" This reverts commit 717caa9. * Revert "fix(docker): ensure memory-lancedb deps installed in Docker image" This reverts commit 2ab6313. * Revert "fix: add windowsHide: true to spawn in runCommandWithTimeout" This reverts commit 32c66af. * Revert "Onboarding: fix webchat URL loopback and canonical session" This reverts commit 59e0e7e. * Revert "feat(linq): add interactive onboarding adapter" This reverts commit b91e437. * Revert "feat: add Linq channel — real iMessage via API, no Mac required" This reverts commit d4a142f. * docs: clarify discord proxy scope for startup REST calls * Revert "fix: flatten remaining anyOf/oneOf in Gemini schema cleaning" This reverts commit 06b961b. * Revert "fix: session-memory hook finds previous session file after /new/reset" This reverts commit d6acd71. * Revert "fix: respect OPENCLAW_HOME for isolated gateway instances" This reverts commit 34b18ea. * fix(process): harden graceful kill-tree cancellation semantics * fix(slack): scope attachment extraction to forwarded shares * docs(changelog): note process kill-tree hotfix * docs(changelog): note slack forwarded attachment hotfix * fix(session-memory): harden reset transcript recovery * revert(telegram): undo accidental merge of PR #18601 * fix(ui): preserve locale bootstrap and trusted-proxy overview behavior * fix(scripts): harden Windows UI spawn behavior * fix(slack): validate interaction payloads and handle malformed actions * fix(mattermost): harden react remove flag parsing * docs(changelog): record PR 18608 fixups * fix(heartbeat): bound responsePrefix strip for ack detection * chore: Fix types in tests 3/N. * chore: chore: Fix types in tests 4/N. * chore: Fix types in tests 5/N. * chore: Fix types in tests 6/N. * chore: Format files. * chore: Fix types that were broken due to reverts. * chore: Cleanup unused vars that were leftover from the reverts. * fix(actions): layer per-account gate fallback * fix(subagents): pass group context in /subagents spawn * fix(failover): align abort timeout detection and regressions * fix(models): sync auth-profiles before availability checks * fix(ui): correct usage range totals and muted styles * Revert "feat: show transcript file size in session status" This reverts commit 15dd2cd. * revert(doctor): undo accidental merge of PR #18591 * fix(agents): align session lock hold budget with run timeouts * Revert "fix: resolve #12770 - update Antigravity default model and trim leading whitespace in BlueBubbles replies" This reverts commit e179d45. * revert(tools): undo accidental merge of PR #18584 * revert(tools): finish rollback of PR #18584 * chore: Fix Slack test. * revert: remove accidentally merged video-quote-finder skill (#18550) * revert: accidental merge of OC-09 sandbox env sanitization change * fix(doctor): move forced exit to top-level command * chore: Fix types in tests 7/N. * chore: Fix types in tests 8/N. * chore: Fix types in tests 9/N. * chore: Fix types in tests 10/N. * chore: Fix types in tests 11/N. * chore: chore: Fix types in tests 12/N. * chore: Fix type errors from reverts. * fix(gateway): remove watch-mode build/start race (#18782) * fix(doctor): repair googlechat open dm wildcard auto-fix * test(extensions): cast fetch mocks to satisfy tsgo * fix(gateway): harden channel health monitor recovery * fix(reply): track messaging media aliases for dedupe * refactor(plugins): split before-agent hooks by model and prompt phases * revert(telegram): undo accidental merge of PR #18564 * fix(agents): restore multi-image image tool schema contract * chore: Format files. * fix(ui): gate sessions refresh on successful delete * revert(docs): undo accidental merge of #18516 * revert(exec): undo accidental merge of PR #18521 * docs(cron): clarify webhook posting summary condition * fix(gateway): preserve chat.history context under hard caps * chore: Fix types in tests 13/N. * chore: Fix types in tests 14/N. * chore: Fix types in tests 15/N. * chore: Fix types in tests 16/N. * chore: Fix types in tests 17/N. * chore: Fix types in tests 18/N. * chore: Format files. * revert(sandbox): revert SHA-1 slug restoration * test(session): cover stale threadId fallback * test(status): cover token summary variants * test(telegram): cover getFile file-too-big errors * test(voice-call): cover stream disconnect auto-end * chore(format): fix test import order * test(agents): cover tool result media placeholders * chore: chore: Fix types in tests 19/N. * chore: Fix types in tests 20/N. * chore: Fix types in tests 21/N. * chore: Fix types in tests 22/N. * chore: Fix types in tests 23/N. * docs(voice-call): document stale call reaper config * fix(doctor): audit env-only gateway tokens * fix(sessions): purge deleted transcript archives * test(docker): cover browser install build arg * revert(gateway): restore loopback auth setup * revert(voice-call): undo cached greeting note * revert(voice-call): undo oxfmt formatting * revert(voice-call): undo oxfmt formatting pass * revert(voice-call): remove cached inbound greeting * test: stabilize infra tests * fix(subagents): harden announce retry guards * Revert "fix(whatsapp): allow per-message link preview override\n\nWhatsApp messages default to enabling link previews for URLs. This adds\nsupport for overriding this behavior per-message via the \nparameter (e.g. from tool options), consistent with Telegram.\n\nFix: Updated internal WhatsApp Web API layers to pass option\ndown to Baileys ." This reverts commit 1bef2fc. * fix(telegram): clear offsets on token change * test(agents): cover exec non-zero exits * CI: use self-hosted for labeler/automation * Revert "channels: migrate extension account listing to factory" This reverts commit d24340d. * chore(format) * chore: wtf. * chore: Fix types. * chore: Fix types in tests 24/N. * chore: Fix types in tests 25/N. * chore: Fix types in tests 26/N. * chore: Fix types in tests 27/N. * chore: Fix types in tests 28/N. * chore: Fix types in tests 29/N. * chore: Fix types in tests 30/N. * chore: Fix types in tests 31/N. * chore: Fix types in tests 32/N. * fix(telegram): add initial message debounce for better push notifications (#18147) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 5e2285b Co-authored-by: Marvae <[email protected]> Co-authored-by: obviyus <[email protected]> Reviewed-by: @obviyus * style(telegram): format dispatch files * chore: Fix types in tests 33/N. * chore: Fix types in tests 34/N. * chore: Fix types in tests 35/N. * chore: Fix types in tests 36/N. * chore: Fix types in tests 37/N. * chore: Fix types in tests 38/N. * chore: Fix types in tests 39/N. * chore: Fix types in tests 40/N. * chore: Fix types in tests 41/N. * chore: Fix types in tests 42/N. * chore: Fix types in tests 43/N. * chore: Fix types in tests 44/N. * chore: Fix types in tests 45/N. * chore: Typecheck tests. * chore: Fix broken test. * chore: Fix hanging test. * fix(telegram): avoid duplicate preview bubbles in partial stream mode (#18956) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: cf4eca7 Co-authored-by: obviyus <[email protected]> Co-authored-by: obviyus <[email protected]> Reviewed-by: @obviyus * fix: before_tool_call hook double-fires with abort signal (#16852) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 6269d61 Co-authored-by: sreuter <[email protected]> Co-authored-by: obviyus <[email protected]> Reviewed-by: @obviyus * Revert "Default Telegram polls to public" This reverts commit c43e95e. * Revert "Fix Telegram poll action wiring" This reverts commit 556b531. * Revert "Add Telegram polls action to config typing" This reverts commit 5cbfaf5. * Revert "fix(telegram): wire sendPollTelegram into channel action handler (#16977)" This reverts commit 7bb9a7d. * CI: remove formal models conformance workflow (#19007) * fix: preserve telegram dm topic thread ids * style: drop aidev-note prefix in telegram comments * test: pass extensionContext in abort dedupe e2e * fix: align tool execute arg parsing for hooks * test: type telegram action mock passthrough args * Configure: make model picker allowlist searchable * Configure: improve searchable model picker token matching * Docs: add screenshot showing model picker usability issue * fix: searchable model picker in configure (#19010) (thanks @bjesuiter) * fix(extensions): revert openai codex auth plugin (PR #18009) * feat(telegram): add channel_post support for bot-to-bot communication (#17857) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 27a343c Co-authored-by: theSamPadilla <[email protected]> Co-authored-by: obviyus <[email protected]> Reviewed-by: @obviyus * Revert "fix: handle forum/topics in Telegram DM thread routing (#17980)" This reverts commit e20b87f. * Revert: undo #17974 README change * voice-call: harden closed-loop turn loop and transcript routing (#19140) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 14a3edb Co-authored-by: mbelinky <[email protected]> Co-authored-by: mbelinky <[email protected]> Reviewed-by: @mbelinky * iOS onboarding: stop auth step-3 retry loop churn (#19153) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: a38ec42 Co-authored-by: mbelinky <[email protected]> Co-authored-by: mbelinky <[email protected]> Reviewed-by: @mbelinky * Revert: fully roll back #17974 zh-cn UI README * chore(subagents): add regression coverage and changelog * fix(daemon): scope token drift warnings * test(web): fix baileys mock typing * test(cron): cover webhook session rollover overrides * docs(changelog): note webhook session reuse fix * fix(discord): normalize command allowFrom prefixes * fix(cli): honor update restart overrides * fix(cron): add spin-loop regression coverage * test(gateway): cover trusted proxy trimming * test(discord): cover audioAsVoice replies * test(feishu): cover post mentions for other users * fix(discord): preserve DM lastRoute user target * Revert "fix(browser): track original port mapping for EADDRINUSE fallback" This reverts commit 8e55503. * Revert "fix(browser): handle EADDRINUSE with automatic port fallback" This reverts commit 0e6daa2. * test(discord): fix mock call arg typing * Revert: fully roll back #17986 templates * test: add fetch mock helper and reaction coverage * CLI: approve latest pending device request * docs(readme): remove Android install link * revert(agents): remove llms.txt discovery prompt (#19192) * fix(ui): revert PR #18093 directive tags (#19188) * test(discord): cover auto-thread skip types * test(update): cover restart gating * docs(zai): document tool_stream defaults * revert: per-model thinkingDefault override (#19195) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: fe2c59e Co-authored-by: sebslight <[email protected]> Co-authored-by: sebslight <[email protected]> Reviewed-by: @sebslight * fix(gateway): make stale token cleanup non-fatal * Agents: add before_message_write persistence regression tests * fix(mattermost): surface reactions support * Tests: fix fetch mock typings for type-aware checks * revert: fix models set catalog validation (#19194) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 7e3b2ff Co-authored-by: sebslight <[email protected]> Co-authored-by: sebslight <[email protected]> Reviewed-by: @sebslight * test: cover cron telemetry and typed fetch mocks * revert(agents): revert base64 image validation (#19221) * docs(cli): add components send example * test(sessions): add delivery info regression coverage * fix(daemon): guard preferred node selection * test(auto-reply): cover sender_id metadata * revert: PR 18288 accidental merge (#19224) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 3cda315 Co-authored-by: sebslight <[email protected]> Co-authored-by: sebslight <[email protected]> Reviewed-by: @sebslight * test(telegram): cover autoSelectFamily env precedence * test(cron): add model fallback regression coverage * test(release): add appcast regression coverage * docs(changelog): remove revert entries * docs: add maintainer application section * docs: refine maintainer application guidance * docs: add vision doc and link from README * docs: add community plugins guide * Update auto-response message for third-party extensions * update my contributing list * iOS: use operator session for ChatSheet RPCs (#19320) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 0753b3a Co-authored-by: mbelinky <[email protected]> Co-authored-by: mbelinky <[email protected]> Reviewed-by: @mbelinky * fix: sanitize native command names for Telegram API (#19257) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: b608be3 Co-authored-by: akramcodez <[email protected]> Co-authored-by: obviyus <[email protected]> Reviewed-by: @obviyus * docs(slack): add assistant:write requirement for typing status * chore: document sessions_spawn response note and subagent context prefix * feat(ios): auto-select local signing team (#18421) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: bbb9c3a Co-authored-by: ngutman <[email protected]> Co-authored-by: ngutman <[email protected]> Reviewed-by: @ngutman * fix(bluebubbles): recover outbound message IDs and include sender metadata * fix cron announce routing and timeout handling * changelog: add @tyler6204 credit for today's entries * feat: share to openclaw ios app (#19424) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 0a7ab85 Co-authored-by: mbelinky <[email protected]> Co-authored-by: mbelinky <[email protected]> Reviewed-by: @mbelinky * Docs: expand multi-agent routing * docs(changelog): add missing 2026.2.16 entries and reorder by user impact * chore(release): bump version to 2026.2.17 * fix(signal): canonicalize message targets in tool and inbound flows * docs: tighten contribution guidance and vision links * docs: tighten PR scope and review-size policy in vision * fix(gateway): block cross-session fallback in node event delivery * fix(gateway): make health monitor checks single-flight * fix(ios): harden share relay routing and delivery guards * fix(telegram): normalize topic-create targets and add regression tests * feat(cron): add default stagger controls for scheduled jobs * fix(cron): retry next-second schedule compute on undefined * docs(security): harden gateway security guidance * feat(models): support anthropic sonnet 4.6 * fix: wire agents.defaults.imageModel into media understanding auto-discovery resolveAutoEntries only checked a hardcoded list of providers (openai, anthropic, google, minimax) when looking for an image model. agents.defaults.imageModel was never consulted by the media understanding pipeline — it was only wired into the explicit `image` tool. Add resolveImageModelFromAgentDefaults that reads the imageModel config (primary + fallbacks) and inserts it into the auto-discovery chain before the hardcoded provider list. runProviderEntry already falls back to describeImageWithModel (via pi-ai) for providers not in the media understanding registry, so no additional provider registration is needed. Co-Authored-By: Claude Sonnet 4.5 <[email protected]> (cherry picked from commit b381029) * docs: update AGENTS instructions * fix(subagent): harden read-tool overflow guards and sticky reply threading (#19508) * fix(gateway): avoid premature agent.wait completion on transient errors * fix(agent): preemptively guard tool results against context overflow * fix: harden tool-result context guard and add message_id metadata * fix: use importOriginal in session-key mock to include DEFAULT_ACCOUNT_ID The run.skill-filter test was mocking ../../routing/session-key.js with only buildAgentMainSessionKey and normalizeAgentId, but the module also exports DEFAULT_ACCOUNT_ID which is required transitively by src/web/auth-store.ts. Switch to importOriginal pattern so all real exports are preserved alongside the mocked functions. * pi-runner: guard accumulated tool-result overflow in transformContext * PI runner: compact overflowing tool-result context * Subagent: harden tool-result context recovery * Enhance tool-result context handling by adding support for legacy tool outputs and improving character estimation for message truncation. This includes a new function to create legacy tool results and updates to existing functions to better manage context overflow scenarios. * Enhance iMessage handling by adding reply tag support in send functions and tests. This includes modifications to prepend or rewrite reply tags based on provided replyToId, ensuring proper message formatting for replies. * Enhance message delivery across multiple channels by implementing sticky reply context for chunked messages. This includes preserving reply references in Discord, Telegram, and iMessage, ensuring that follow-up messages maintain their intended reply targets. Additionally, improve handling of reply tags in system prompts and tests to support consistent reply behavior. * Enhance read tool functionality by implementing auto-paging across chunks when no explicit limit is provided, scaling output budget based on model context window. Additionally, add tests for adaptive reading behavior and capped continuation guidance for large outputs. Update related functions to support these features. * Refine tool-result context management by stripping oversized read-tool details payloads during compaction, ensuring repeated read calls do not bypass context limits. Introduce new utility functions for handling truncation content and enhance character estimation for tool results. Add tests to validate the removal of excessive details in context overflow scenarios. * Refine message delivery logic in Matrix and Telegram by introducing a flag to track if a text chunk was sent. This ensures that replies are only marked as delivered when a text chunk has been successfully sent, improving the accuracy of reply handling in both channels. * fix: tighten reply threading coverage and prep fixes (#19508) (thanks @tyler6204) * fix(hooks): backport internal message hook bridge with safe delivery semantics * fix(subagent): update SUBAGENT_SPAWN_ACCEPTED_NOTE for clarity on auto-announcement behavior * fix: follow-up slack streaming routing/tests (#9972) (thanks @natedenh) * fix: reduce default image dimension from 2000px to 1200px Large images (2000px) consume excessive context tokens when sent to LLMs. 1200px provides sufficient detail for most use cases while significantly reducing token usage. The 5MB byte limit remains unchanged as JPEG compression at 1200px naturally produces smaller files. (cherry picked from commit 4018212) * fix(agents): make image sanitization dimension configurable * docs(tokens): document image dimension token tradeoffs * Whatsapp/add resolve outbound target tests (#19345) * test(whatsapp): add resolveWhatsAppOutboundTarget test suite * style: auto-format files * fix(test): correct mock order for invalid allowList entry test * feat(skills): Add 'Use when / Don't use when' routing blocks (#14521) * feat(skills): add 'Use when / Don't use when' blocks to skill descriptions Based on OpenAI's Shell + Skills + Compaction best practices article. Key changes: - Added clear routing logic to skill descriptions - Added negative examples to prevent misfires - Added templates/examples to github skill - Included Blake's specific setup notes for openhue Skills updated: - apple-reminders: Clarify vs Clawdbot cron - github: Clarify vs local git operations - imsg: Clarify vs other messaging channels - openhue: Add device inventory, room layout - tmux: Clarify vs exec tool - weather: Add location defaults, format codes Reference: https://developers.openai.com/blog/skills-shell-tips * fix(skills): restore metadata and generic CLI examples --------- Co-authored-by: Peter Steinberger <[email protected]> * feat(agents): add generic provider api key rotation (#19587) * feat(skills): improve descriptions with routing logic (#14577) * feat(skills): improve descriptions with routing logic Apply OpenAI's recommended pattern for skill descriptions: - Add 'Use when' conditions for clear triggering - Add 'NOT for' negative examples to reduce misfires - Make descriptions act as routing logic, not marketing copy Based on: https://developers.openai.com/blog/skills-shell-tips/ Skills updated: - coding-agent: clarify when to delegate vs direct edit - github: add boundaries vs browser/scripting - weather: add scope limitations Glean reported 20% drop in skill triggering without negative examples, recovering after adding them. This change brings Clawdbot skills in line with that pattern. * docs(skills): clarify routing boundaries (#14577) (thanks @DylanWoodAkers) * docs(changelog): add PR 14577 release note (#14577) (thanks @DylanWoodAkers) --------- Co-authored-by: ClawdBotWolf <[email protected]> Co-authored-by: Peter Steinberger <[email protected]> * Add frontend-design skill * feat(telegram): add forum topic creation support (#10427) Add `topic-create` action to the Telegram message adapter, enabling programmatic creation of forum topics in supergroups. Changes: - Add `createForumTopicTelegram()` to `src/telegram/send.ts` - Add `createForumTopic` handler in `telegram-actions.ts` - Wire `topic-create` action in Telegram adapter - Register `topic-create` in message action names and spec The bot requires `can_manage_topics` permission in the target group. Supports optional `iconColor` and `iconCustomEmojiId` parameters. Closes #10427 * chore: fix formatting in frontend-design SKILL.md * fix: add action gate check and config type for createForumTopic Address review feedback: - Add isActionEnabled() gate in telegram-actions.ts - Add gate() check in telegram adapter listActions - Add createForumTopic to TelegramActionConfig type * fix(telegram): normalize topic-create targets and add regression tests --------- Co-authored-by: Peter Steinberger <[email protected]> Co-authored-by: Gustavo Madeira Santana <[email protected]> Co-authored-by: cpojer <[email protected]> Co-authored-by: Sebastian <[email protected]> Co-authored-by: Josh Avant <[email protected]> Co-authored-by: Shadow <[email protected]> Co-authored-by: Hongwei Ma <[email protected]> Co-authored-by: Marvae <[email protected]> Co-authored-by: obviyus <[email protected]> Co-authored-by: Ayaan Zaidi <[email protected]> Co-authored-by: Ayaan Zaidi <[email protected]> Co-authored-by: Sascha Reuter <[email protected]> Co-authored-by: sreuter <[email protected]> Co-authored-by: Nimrod Gutman <[email protected]> Co-authored-by: Vignesh <[email protected]> Co-authored-by: Benjamin Jesuiter <[email protected]> Co-authored-by: Sam Padilla <[email protected]> Co-authored-by: Muhammed Mukhthar CM <[email protected]> Co-authored-by: Mariano <[email protected]> Co-authored-by: Shakker <[email protected]> Co-authored-by: Mariano Belinky <[email protected]> Co-authored-by: Shadow <[email protected]> Co-authored-by: Sk Akram <[email protected]> Co-authored-by: akramcodez <[email protected]> Co-authored-by: Onur <[email protected]> Co-authored-by: Tyler Yust <[email protected]> Co-authored-by: ngutman <[email protected]> Co-authored-by: Pablo Nunez <[email protected]> Co-authored-by: Claude Sonnet 4.5 <[email protected]> Co-authored-by: Tyler Yust <[email protected]> Co-authored-by: Han Xiao <[email protected]> Co-authored-by: Verite Igiraneza <[email protected]> Co-authored-by: Blakeshannon <[email protected]> Co-authored-by: Peter Steinberger <[email protected]> Co-authored-by: DylanWoodAkers <[email protected]> Co-authored-by: ClawdBotWolf <[email protected]> Co-authored-by: Claw <[email protected]>

@tyler6204

…ading (openclaw#19508) * fix(gateway): avoid premature agent.wait completion on transient errors * fix(agent): preemptively guard tool results against context overflow * fix: harden tool-result context guard and add message_id metadata * fix: use importOriginal in session-key mock to include DEFAULT_ACCOUNT_ID The run.skill-filter test was mocking ../../routing/session-key.js with only buildAgentMainSessionKey and normalizeAgentId, but the module also exports DEFAULT_ACCOUNT_ID which is required transitively by src/web/auth-store.ts. Switch to importOriginal pattern so all real exports are preserved alongside the mocked functions. * pi-runner: guard accumulated tool-result overflow in transformContext * PI runner: compact overflowing tool-result context * Subagent: harden tool-result context recovery * Enhance tool-result context handling by adding support for legacy tool outputs and improving character estimation for message truncation. This includes a new function to create legacy tool results and updates to existing functions to better manage context overflow scenarios. * Enhance iMessage handling by adding reply tag support in send functions and tests. This includes modifications to prepend or rewrite reply tags based on provided replyToId, ensuring proper message formatting for replies. * Enhance message delivery across multiple channels by implementing sticky reply context for chunked messages. This includes preserving reply references in Discord, Telegram, and iMessage, ensuring that follow-up messages maintain their intended reply targets. Additionally, improve handling of reply tags in system prompts and tests to support consistent reply behavior. * Enhance read tool functionality by implementing auto-paging across chunks when no explicit limit is provided, scaling output budget based on model context window. Additionally, add tests for adaptive reading behavior and capped continuation guidance for large outputs. Update related functions to support these features. * Refine tool-result context management by stripping oversized read-tool details payloads during compaction, ensuring repeated read calls do not bypass context limits. Introduce new utility functions for handling truncation content and enhance character estimation for tool results. Add tests to validate the removal of excessive details in context overflow scenarios. * Refine message delivery logic in Matrix and Telegram by introducing a flag to track if a text chunk was sent. This ensures that replies are only marked as delivered when a text chunk has been successfully sent, improving the accuracy of reply handling in both channels. * fix: tighten reply threading coverage and prep fixes (openclaw#19508) (thanks @tyler6204)

…ading (openclaw#19508) Cherry-picked from upstream 087dca8 with fork adaptations.

@tyler6204

…ading (openclaw#19508) * fix(gateway): avoid premature agent.wait completion on transient errors * fix(agent): preemptively guard tool results against context overflow * fix: harden tool-result context guard and add message_id metadata * fix: use importOriginal in session-key mock to include DEFAULT_ACCOUNT_ID The run.skill-filter test was mocking ../../routing/session-key.js with only buildAgentMainSessionKey and normalizeAgentId, but the module also exports DEFAULT_ACCOUNT_ID which is required transitively by src/web/auth-store.ts. Switch to importOriginal pattern so all real exports are preserved alongside the mocked functions. * pi-runner: guard accumulated tool-result overflow in transformContext * PI runner: compact overflowing tool-result context * Subagent: harden tool-result context recovery * Enhance tool-result context handling by adding support for legacy tool outputs and improving character estimation for message truncation. This includes a new function to create legacy tool results and updates to existing functions to better manage context overflow scenarios. * Enhance iMessage handling by adding reply tag support in send functions and tests. This includes modifications to prepend or rewrite reply tags based on provided replyToId, ensuring proper message formatting for replies. * Enhance message delivery across multiple channels by implementing sticky reply context for chunked messages. This includes preserving reply references in Discord, Telegram, and iMessage, ensuring that follow-up messages maintain their intended reply targets. Additionally, improve handling of reply tags in system prompts and tests to support consistent reply behavior. * Enhance read tool functionality by implementing auto-paging across chunks when no explicit limit is provided, scaling output budget based on model context window. Additionally, add tests for adaptive reading behavior and capped continuation guidance for large outputs. Update related functions to support these features. * Refine tool-result context management by stripping oversized read-tool details payloads during compaction, ensuring repeated read calls do not bypass context limits. Introduce new utility functions for handling truncation content and enhance character estimation for tool results. Add tests to validate the removal of excessive details in context overflow scenarios. * Refine message delivery logic in Matrix and Telegram by introducing a flag to track if a text chunk was sent. This ensures that replies are only marked as delivered when a text chunk has been successfully sent, improving the accuracy of reply handling in both channels. * fix: tighten reply threading coverage and prep fixes (openclaw#19508) (thanks @tyler6204)

@obviyus

* Revert "fix(gateway): set explicit chat timeouts for mesh gateway calls" This reverts commit c529e60. * Revert "fix: capture init script exit codes instead of swallowing via pipe" This reverts commit 8b14052. * Revert "feat(docker): add init script support via /openclaw-init.d/" This reverts commit 53af9f7. * Revert "Agents: improve Windows scaffold helpers for venture studio" This reverts commit b6d934c. * chore: Fix types in tests 1/N. * chore: Fix types in tests 2/N. * Revert "fix: remove stderr suppression so install failures are visible in build logs" This reverts commit 717caa9. * Revert "fix(docker): ensure memory-lancedb deps installed in Docker image" This reverts commit 2ab6313. * Revert "fix: add windowsHide: true to spawn in runCommandWithTimeout" This reverts commit 32c66af. * Revert "Onboarding: fix webchat URL loopback and canonical session" This reverts commit 59e0e7e. * Revert "feat(linq): add interactive onboarding adapter" This reverts commit b91e437. * Revert "feat: add Linq channel — real iMessage via API, no Mac required" This reverts commit d4a142f. * docs: clarify discord proxy scope for startup REST calls * Revert "fix: flatten remaining anyOf/oneOf in Gemini schema cleaning" This reverts commit 06b961b. * Revert "fix: session-memory hook finds previous session file after /new/reset" This reverts commit d6acd71. * Revert "fix: respect OPENCLAW_HOME for isolated gateway instances" This reverts commit 34b18ea. * fix(process): harden graceful kill-tree cancellation semantics * fix(slack): scope attachment extraction to forwarded shares * docs(changelog): note process kill-tree hotfix * docs(changelog): note slack forwarded attachment hotfix * fix(session-memory): harden reset transcript recovery * revert(telegram): undo accidental merge of PR openclaw#18601 * fix(ui): preserve locale bootstrap and trusted-proxy overview behavior * fix(scripts): harden Windows UI spawn behavior * fix(slack): validate interaction payloads and handle malformed actions * fix(mattermost): harden react remove flag parsing * docs(changelog): record PR 18608 fixups * fix(heartbeat): bound responsePrefix strip for ack detection * chore: Fix types in tests 3/N. * chore: chore: Fix types in tests 4/N. * chore: Fix types in tests 5/N. * chore: Fix types in tests 6/N. * chore: Format files. * chore: Fix types that were broken due to reverts. * chore: Cleanup unused vars that were leftover from the reverts. * fix(actions): layer per-account gate fallback * fix(subagents): pass group context in /subagents spawn * fix(failover): align abort timeout detection and regressions * fix(models): sync auth-profiles before availability checks * fix(ui): correct usage range totals and muted styles * Revert "feat: show transcript file size in session status" This reverts commit 15dd2cd. * revert(doctor): undo accidental merge of PR openclaw#18591 * fix(agents): align session lock hold budget with run timeouts * Revert "fix: resolve openclaw#12770 - update Antigravity default model and trim leading whitespace in BlueBubbles replies" This reverts commit e179d45. * revert(tools): undo accidental merge of PR openclaw#18584 * revert(tools): finish rollback of PR openclaw#18584 * chore: Fix Slack test. * revert: remove accidentally merged video-quote-finder skill (openclaw#18550) * revert: accidental merge of OC-09 sandbox env sanitization change * fix(doctor): move forced exit to top-level command * chore: Fix types in tests 7/N. * chore: Fix types in tests 8/N. * chore: Fix types in tests 9/N. * chore: Fix types in tests 10/N. * chore: Fix types in tests 11/N. * chore: chore: Fix types in tests 12/N. * chore: Fix type errors from reverts. * fix(gateway): remove watch-mode build/start race (openclaw#18782) * fix(doctor): repair googlechat open dm wildcard auto-fix * test(extensions): cast fetch mocks to satisfy tsgo * fix(gateway): harden channel health monitor recovery * fix(reply): track messaging media aliases for dedupe * refactor(plugins): split before-agent hooks by model and prompt phases * revert(telegram): undo accidental merge of PR openclaw#18564 * fix(agents): restore multi-image image tool schema contract * chore: Format files. * fix(ui): gate sessions refresh on successful delete * revert(docs): undo accidental merge of openclaw#18516 * revert(exec): undo accidental merge of PR openclaw#18521 * docs(cron): clarify webhook posting summary condition * fix(gateway): preserve chat.history context under hard caps * chore: Fix types in tests 13/N. * chore: Fix types in tests 14/N. * chore: Fix types in tests 15/N. * chore: Fix types in tests 16/N. * chore: Fix types in tests 17/N. * chore: Fix types in tests 18/N. * chore: Format files. * revert(sandbox): revert SHA-1 slug restoration * test(session): cover stale threadId fallback * test(status): cover token summary variants * test(telegram): cover getFile file-too-big errors * test(voice-call): cover stream disconnect auto-end * chore(format): fix test import order * test(agents): cover tool result media placeholders * chore: chore: Fix types in tests 19/N. * chore: Fix types in tests 20/N. * chore: Fix types in tests 21/N. * chore: Fix types in tests 22/N. * chore: Fix types in tests 23/N. * docs(voice-call): document stale call reaper config * fix(doctor): audit env-only gateway tokens * fix(sessions): purge deleted transcript archives * test(docker): cover browser install build arg * revert(gateway): restore loopback auth setup * revert(voice-call): undo cached greeting note * revert(voice-call): undo oxfmt formatting * revert(voice-call): undo oxfmt formatting pass * revert(voice-call): remove cached inbound greeting * test: stabilize infra tests * fix(subagents): harden announce retry guards * Revert "fix(whatsapp): allow per-message link preview override\n\nWhatsApp messages default to enabling link previews for URLs. This adds\nsupport for overriding this behavior per-message via the \nparameter (e.g. from tool options), consistent with Telegram.\n\nFix: Updated internal WhatsApp Web API layers to pass option\ndown to Baileys ." This reverts commit 1bef2fc. * fix(telegram): clear offsets on token change * test(agents): cover exec non-zero exits * CI: use self-hosted for labeler/automation * Revert "channels: migrate extension account listing to factory" This reverts commit d24340d. * chore(format) * chore: wtf. * chore: Fix types. * chore: Fix types in tests 24/N. * chore: Fix types in tests 25/N. * chore: Fix types in tests 26/N. * chore: Fix types in tests 27/N. * chore: Fix types in tests 28/N. * chore: Fix types in tests 29/N. * chore: Fix types in tests 30/N. * chore: Fix types in tests 31/N. * chore: Fix types in tests 32/N. * fix(telegram): add initial message debounce for better push notifications (openclaw#18147) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 5e2285b Co-authored-by: Marvae <[email protected]> Co-authored-by: obviyus <[email protected]> Reviewed-by: @obviyus * style(telegram): format dispatch files * chore: Fix types in tests 33/N. * chore: Fix types in tests 34/N. * chore: Fix types in tests 35/N. * chore: Fix types in tests 36/N. * chore: Fix types in tests 37/N. * chore: Fix types in tests 38/N. * chore: Fix types in tests 39/N. * chore: Fix types in tests 40/N. * chore: Fix types in tests 41/N. * chore: Fix types in tests 42/N. * chore: Fix types in tests 43/N. * chore: Fix types in tests 44/N. * chore: Fix types in tests 45/N. * chore: Typecheck tests. * chore: Fix broken test. * chore: Fix hanging test. * fix(telegram): avoid duplicate preview bubbles in partial stream mode (openclaw#18956) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: cf4eca7 Co-authored-by: obviyus <[email protected]> Co-authored-by: obviyus <[email protected]> Reviewed-by: @obviyus * fix: before_tool_call hook double-fires with abort signal (openclaw#16852) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 6269d61 Co-authored-by: sreuter <[email protected]> Co-authored-by: obviyus <[email protected]> Reviewed-by: @obviyus * Revert "Default Telegram polls to public" This reverts commit c43e95e. * Revert "Fix Telegram poll action wiring" This reverts commit 556b531. * Revert "Add Telegram polls action to config typing" This reverts commit 5cbfaf5. * Revert "fix(telegram): wire sendPollTelegram into channel action handler (openclaw#16977)" This reverts commit 7bb9a7d. * CI: remove formal models conformance workflow (openclaw#19007) * fix: preserve telegram dm topic thread ids * style: drop aidev-note prefix in telegram comments * test: pass extensionContext in abort dedupe e2e * fix: align tool execute arg parsing for hooks * test: type telegram action mock passthrough args * Configure: make model picker allowlist searchable * Configure: improve searchable model picker token matching * Docs: add screenshot showing model picker usability issue * fix: searchable model picker in configure (openclaw#19010) (thanks @bjesuiter) * fix(extensions): revert openai codex auth plugin (PR openclaw#18009) * feat(telegram): add channel_post support for bot-to-bot communication (openclaw#17857) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 27a343c Co-authored-by: theSamPadilla <[email protected]> Co-authored-by: obviyus <[email protected]> Reviewed-by: @obviyus * Revert "fix: handle forum/topics in Telegram DM thread routing (openclaw#17980)" This reverts commit e20b87f. * Revert: undo openclaw#17974 README change * voice-call: harden closed-loop turn loop and transcript routing (openclaw#19140) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 14a3edb Co-authored-by: mbelinky <[email protected]> Co-authored-by: mbelinky <[email protected]> Reviewed-by: @mbelinky * iOS onboarding: stop auth step-3 retry loop churn (openclaw#19153) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: a38ec42 Co-authored-by: mbelinky <[email protected]> Co-authored-by: mbelinky <[email protected]> Reviewed-by: @mbelinky * Revert: fully roll back openclaw#17974 zh-cn UI README * chore(subagents): add regression coverage and changelog * fix(daemon): scope token drift warnings * test(web): fix baileys mock typing * test(cron): cover webhook session rollover overrides * docs(changelog): note webhook session reuse fix * fix(discord): normalize command allowFrom prefixes * fix(cli): honor update restart overrides * fix(cron): add spin-loop regression coverage * test(gateway): cover trusted proxy trimming * test(discord): cover audioAsVoice replies * test(feishu): cover post mentions for other users * fix(discord): preserve DM lastRoute user target * Revert "fix(browser): track original port mapping for EADDRINUSE fallback" This reverts commit 8e55503. * Revert "fix(browser): handle EADDRINUSE with automatic port fallback" This reverts commit 0e6daa2. * test(discord): fix mock call arg typing * Revert: fully roll back openclaw#17986 templates * test: add fetch mock helper and reaction coverage * CLI: approve latest pending device request * docs(readme): remove Android install link * revert(agents): remove llms.txt discovery prompt (openclaw#19192) * fix(ui): revert PR openclaw#18093 directive tags (openclaw#19188) * test(discord): cover auto-thread skip types * test(update): cover restart gating * docs(zai): document tool_stream defaults * revert: per-model thinkingDefault override (openclaw#19195) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: fe2c59e Co-authored-by: sebslight <[email protected]> Co-authored-by: sebslight <[email protected]> Reviewed-by: @sebslight * fix(gateway): make stale token cleanup non-fatal * Agents: add before_message_write persistence regression tests * fix(mattermost): surface reactions support * Tests: fix fetch mock typings for type-aware checks * revert: fix models set catalog validation (openclaw#19194) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 7e3b2ff Co-authored-by: sebslight <[email protected]> Co-authored-by: sebslight <[email protected]> Reviewed-by: @sebslight * test: cover cron telemetry and typed fetch mocks * revert(agents): revert base64 image validation (openclaw#19221) * docs(cli): add components send example * test(sessions): add delivery info regression coverage * fix(daemon): guard preferred node selection * test(auto-reply): cover sender_id metadata * revert: PR 18288 accidental merge (openclaw#19224) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 3cda315 Co-authored-by: sebslight <[email protected]> Co-authored-by: sebslight <[email protected]> Reviewed-by: @sebslight * test(telegram): cover autoSelectFamily env precedence * test(cron): add model fallback regression coverage * test(release): add appcast regression coverage * docs(changelog): remove revert entries * docs: add maintainer application section * docs: refine maintainer application guidance * docs: add vision doc and link from README * docs: add community plugins guide * Update auto-response message for third-party extensions * update my contributing list * iOS: use operator session for ChatSheet RPCs (openclaw#19320) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 0753b3a Co-authored-by: mbelinky <[email protected]> Co-authored-by: mbelinky <[email protected]> Reviewed-by: @mbelinky * fix: sanitize native command names for Telegram API (openclaw#19257) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: b608be3 Co-authored-by: akramcodez <[email protected]> Co-authored-by: obviyus <[email protected]> Reviewed-by: @obviyus * docs(slack): add assistant:write requirement for typing status * chore: document sessions_spawn response note and subagent context prefix * feat(ios): auto-select local signing team (openclaw#18421) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: bbb9c3a Co-authored-by: ngutman <[email protected]> Co-authored-by: ngutman <[email protected]> Reviewed-by: @ngutman * fix(bluebubbles): recover outbound message IDs and include sender metadata * fix cron announce routing and timeout handling * changelog: add @tyler6204 credit for today's entries * feat: share to openclaw ios app (openclaw#19424) Merged via /review-pr -> /prepare-pr -> /merge-pr. Prepared head SHA: 0a7ab85 Co-authored-by: mbelinky <[email protected]> Co-authored-by: mbelinky <[email protected]> Reviewed-by: @mbelinky * Docs: expand multi-agent routing * docs(changelog): add missing 2026.2.16 entries and reorder by user impact * chore(release): bump version to 2026.2.17 * fix(signal): canonicalize message targets in tool and inbound flows * docs: tighten contribution guidance and vision links * docs: tighten PR scope and review-size policy in vision * fix(gateway): block cross-session fallback in node event delivery * fix(gateway): make health monitor checks single-flight * fix(ios): harden share relay routing and delivery guards * fix(telegram): normalize topic-create targets and add regression tests * feat(cron): add default stagger controls for scheduled jobs * fix(cron): retry next-second schedule compute on undefined * docs(security): harden gateway security guidance * feat(models): support anthropic sonnet 4.6 * fix: wire agents.defaults.imageModel into media understanding auto-discovery resolveAutoEntries only checked a hardcoded list of providers (openai, anthropic, google, minimax) when looking for an image model. agents.defaults.imageModel was never consulted by the media understanding pipeline — it was only wired into the explicit `image` tool. Add resolveImageModelFromAgentDefaults that reads the imageModel config (primary + fallbacks) and inserts it into the auto-discovery chain before the hardcoded provider list. runProviderEntry already falls back to describeImageWithModel (via pi-ai) for providers not in the media understanding registry, so no additional provider registration is needed. Co-Authored-By: Claude Sonnet 4.5 <[email protected]> (cherry picked from commit b381029) * docs: update AGENTS instructions * fix(subagent): harden read-tool overflow guards and sticky reply threading (openclaw#19508) * fix(gateway): avoid premature agent.wait completion on transient errors * fix(agent): preemptively guard tool results against context overflow * fix: harden tool-result context guard and add message_id metadata * fix: use importOriginal in session-key mock to include DEFAULT_ACCOUNT_ID The run.skill-filter test was mocking ../../routing/session-key.js with only buildAgentMainSessionKey and normalizeAgentId, but the module also exports DEFAULT_ACCOUNT_ID which is required transitively by src/web/auth-store.ts. Switch to importOriginal pattern so all real exports are preserved alongside the mocked functions. * pi-runner: guard accumulated tool-result overflow in transformContext * PI runner: compact overflowing tool-result context * Subagent: harden tool-result context recovery * Enhance tool-result context handling by adding support for legacy tool outputs and improving character estimation for message truncation. This includes a new function to create legacy tool results and updates to existing functions to better manage context overflow scenarios. * Enhance iMessage handling by adding reply tag support in send functions and tests. This includes modifications to prepend or rewrite reply tags based on provided replyToId, ensuring proper message formatting for replies. * Enhance message delivery across multiple channels by implementing sticky reply context for chunked messages. This includes preserving reply references in Discord, Telegram, and iMessage, ensuring that follow-up messages maintain their intended reply targets. Additionally, improve handling of reply tags in system prompts and tests to support consistent reply behavior. * Enhance read tool functionality by implementing auto-paging across chunks when no explicit limit is provided, scaling output budget based on model context window. Additionally, add tests for adaptive reading behavior and capped continuation guidance for large outputs. Update related functions to support these features. * Refine tool-result context management by stripping oversized read-tool details payloads during compaction, ensuring repeated read calls do not bypass context limits. Introduce new utility functions for handling truncation content and enhance character estimation for tool results. Add tests to validate the removal of excessive details in context overflow scenarios. * Refine message delivery logic in Matrix and Telegram by introducing a flag to track if a text chunk was sent. This ensures that replies are only marked as delivered when a text chunk has been successfully sent, improving the accuracy of reply handling in both channels. * fix: tighten reply threading coverage and prep fixes (openclaw#19508) (thanks @tyler6204) * fix(hooks): backport internal message hook bridge with safe delivery semantics * fix(subagent): update SUBAGENT_SPAWN_ACCEPTED_NOTE for clarity on auto-announcement behavior * fix: follow-up slack streaming routing/tests (openclaw#9972) (thanks @natedenh) * fix: reduce default image dimension from 2000px to 1200px Large images (2000px) consume excessive context tokens when sent to LLMs. 1200px provides sufficient detail for most use cases while significantly reducing token usage. The 5MB byte limit remains unchanged as JPEG compression at 1200px naturally produces smaller files. (cherry picked from commit 4018212) * fix(agents): make image sanitization dimension configurable * docs(tokens): document image dimension token tradeoffs * Whatsapp/add resolve outbound target tests (openclaw#19345) * test(whatsapp): add resolveWhatsAppOutboundTarget test suite * style: auto-format files * fix(test): correct mock order for invalid allowList entry test * feat(skills): Add 'Use when / Don't use when' routing blocks (openclaw#14521) * feat(skills): add 'Use when / Don't use when' blocks to skill descriptions Based on OpenAI's Shell + Skills + Compaction best practices article. Key changes: - Added clear routing logic to skill descriptions - Added negative examples to prevent misfires - Added templates/examples to github skill - Included Blake's specific setup notes for openhue Skills updated: - apple-reminders: Clarify vs Clawdbot cron - github: Clarify vs local git operations - imsg: Clarify vs other messaging channels - openhue: Add device inventory, room layout - tmux: Clarify vs exec tool - weather: Add location defaults, format codes Reference: https://developers.openai.com/blog/skills-shell-tips * fix(skills): restore metadata and generic CLI examples --------- Co-authored-by: Peter Steinberger <[email protected]> * feat(agents): add generic provider api key rotation (openclaw#19587) * feat(skills): improve descriptions with routing logic (openclaw#14577) * feat(skills): improve descriptions with routing logic Apply OpenAI's recommended pattern for skill descriptions: - Add 'Use when' conditions for clear triggering - Add 'NOT for' negative examples to reduce misfires - Make descriptions act as routing logic, not marketing copy Based on: https://developers.openai.com/blog/skills-shell-tips/ Skills updated: - coding-agent: clarify when to delegate vs direct edit - github: add boundaries vs browser/scripting - weather: add scope limitations Glean reported 20% drop in skill triggering without negative examples, recovering after adding them. This change brings Clawdbot skills in line with that pattern. * docs(skills): clarify routing boundaries (openclaw#14577) (thanks @DylanWoodAkers) * docs(changelog): add PR 14577 release note (openclaw#14577) (thanks @DylanWoodAkers) --------- Co-authored-by: ClawdBotWolf <[email protected]> Co-authored-by: Peter Steinberger <[email protected]> * Add frontend-design skill * feat(telegram): add forum topic creation support (openclaw#10427) Add `topic-create` action to the Telegram message adapter, enabling programmatic creation of forum topics in supergroups. Changes: - Add `createForumTopicTelegram()` to `src/telegram/send.ts` - Add `createForumTopic` handler in `telegram-actions.ts` - Wire `topic-create` action in Telegram adapter - Register `topic-create` in message action names and spec The bot requires `can_manage_topics` permission in the target group. Supports optional `iconColor` and `iconCustomEmojiId` parameters. Closes openclaw#10427 * chore: fix formatting in frontend-design SKILL.md * fix: add action gate check and config type for createForumTopic Address review feedback: - Add isActionEnabled() gate in telegram-actions.ts - Add gate() check in telegram adapter listActions - Add createForumTopic to TelegramActionConfig type * fix(telegram): normalize topic-create targets and add regression tests --------- Co-authored-by: Peter Steinberger <[email protected]> Co-authored-by: Gustavo Madeira Santana <[email protected]> Co-authored-by: cpojer <[email protected]> Co-authored-by: Sebastian <[email protected]> Co-authored-by: Josh Avant <[email protected]> Co-authored-by: Shadow <[email protected]> Co-authored-by: Hongwei Ma <[email protected]> Co-authored-by: Marvae <[email protected]> Co-authored-by: obviyus <[email protected]> Co-authored-by: Ayaan Zaidi <[email protected]> Co-authored-by: Ayaan Zaidi <[email protected]> Co-authored-by: Sascha Reuter <[email protected]> Co-authored-by: sreuter <[email protected]> Co-authored-by: Nimrod Gutman <[email protected]> Co-authored-by: Vignesh <[email protected]> Co-authored-by: Benjamin Jesuiter <[email protected]> Co-authored-by: Sam Padilla <[email protected]> Co-authored-by: Muhammed Mukhthar CM <[email protected]> Co-authored-by: Mariano <[email protected]> Co-authored-by: Shakker <[email protected]> Co-authored-by: Mariano Belinky <[email protected]> Co-authored-by: Shadow <[email protected]> Co-authored-by: Sk Akram <[email protected]> Co-authored-by: akramcodez <[email protected]> Co-authored-by: Onur <[email protected]> Co-authored-by: Tyler Yust <[email protected]> Co-authored-by: ngutman <[email protected]> Co-authored-by: Pablo Nunez <[email protected]> Co-authored-by: Claude Sonnet 4.5 <[email protected]> Co-authored-by: Tyler Yust <[email protected]> Co-authored-by: Han Xiao <[email protected]> Co-authored-by: Verite Igiraneza <[email protected]> Co-authored-by: Blakeshannon <[email protected]> Co-authored-by: Peter Steinberger <[email protected]> Co-authored-by: DylanWoodAkers <[email protected]> Co-authored-by: ClawdBotWolf <[email protected]> Co-authored-by: Claw <[email protected]>

tyler6204 self-assigned this Feb 17, 2026

greptile-apps bot reviewed Feb 17, 2026

View reviewed changes

chatgpt-codex-connector bot reviewed Feb 17, 2026

View reviewed changes

tyler6204 added a commit that referenced this pull request Feb 17, 2026

fix: tighten reply threading coverage and prep fixes (#19508) (thanks @…

9290f96

…tyler6204)

tyler6204 added 14 commits February 17, 2026 15:29

fix(gateway): avoid premature agent.wait completion on transient errors

181c00e

fix(agent): preemptively guard tool results against context overflow

10c9e9c

fix: harden tool-result context guard and add message_id metadata

d30457d

pi-runner: guard accumulated tool-result overflow in transformContext

9a2aa3b

PI runner: compact overflowing tool-result context

9c61a66

Subagent: harden tool-result context recovery

d3f7f4d

Enhance tool-result context handling by adding support for legacy too…

98a53f1

…l outputs and improving character estimation for message truncation. This includes a new function to create legacy tool results and updates to existing functions to better manage context overflow scenarios.

Enhance iMessage handling by adding reply tag support in send functio…

5f3049f

…ns and tests. This includes modifications to prepend or rewrite reply tags based on provided replyToId, ensuring proper message formatting for replies.

Refine message delivery logic in Matrix and Telegram by introducing a…

0277086

… flag to track if a text chunk was sent. This ensures that replies are only marked as delivered when a text chunk has been successfully sent, improving the accuracy of reply handling in both channels.

fix: tighten reply threading coverage and prep fixes (#19508) (thanks @…

dcbf23d

…tyler6204)

tyler6204 force-pushed the fix/subagent-reliability branch from 9290f96 to dcbf23d Compare February 17, 2026 23:32

tyler6204 merged commit 087dca8 into main Feb 17, 2026
11 of 12 checks passed

tyler6204 deleted the fix/subagent-reliability branch February 17, 2026 23:32

tyler6204 mentioned this pull request Feb 17, 2026

feat(models): add Claude Sonnet 4.6 support #19397

Closed

davidstosik mentioned this pull request Feb 18, 2026

feat: add Claude Sonnet 4.6 support #19371

Closed

This was referenced Feb 18, 2026

📡 Upstream Digest — 2026-02-18 01:24 UTC curtismercier/openclaw-mods#55

Open

上游更新: v2026.2.17 — 16 P0 + 67 P1 待合并 jiulingyun/openclaw-cn#160

Open

jiulingyun mentioned this pull request Feb 18, 2026

upstream(subagent): 移植 3 个冲突 commit (P1) — v2026.2.15→v2026.2.17 jiulingyun/openclaw-cn#196

Open

6 tasks

Copilot AI mentioned this pull request Feb 18, 2026

[WIP] Migrate 3 conflicting commits from upstream jiulingyun/openclaw-cn#199

Draft

danielheyman mentioned this pull request Feb 18, 2026

Read auto-paging in 2026.2.17 causes significant token usage increase for cron/worker sessions #20324

Closed

jun-planfit added a commit to planfit/openclaw that referenced this pull request Feb 19, 2026

fix(subagent): harden read-tool overflow guards and sticky reply thre…

f4460e5

…ading (openclaw#19508) Cherry-picked from upstream 087dca8 with fork adaptations.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(subagent): harden read-tool overflow guards and sticky reply threading#19508

fix(subagent): harden read-tool overflow guards and sticky reply threading#19508
tyler6204 merged 14 commits intomainfrom
fix/subagent-reliability

tyler6204 commented Feb 17, 2026 •

edited by greptile-apps bot

Loading

Uh oh!

greptile-apps bot left a comment

Uh oh!

greptile-apps bot Feb 17, 2026

Uh oh!

chatgpt-codex-connector bot left a comment

Uh oh!

chatgpt-codex-connector bot Feb 17, 2026

Uh oh!

chatgpt-codex-connector bot Feb 17, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Comments

		const replyToMessageIdForPayload =
		replyToId && (replyToMode === "all" \|\| !hasReplied) ? replyToId : undefined;

Uh oh!

Conversation

tyler6204 commented Feb 17, 2026 • edited by greptile-apps bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Changes

Testing

Greptile Summary

Confidence Score: 4/5

Uh oh!

greptile-apps bot left a comment

Choose a reason for hiding this comment

Uh oh!

greptile-apps bot Feb 17, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector bot Feb 17, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector bot Feb 17, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Comments

tyler6204 commented Feb 17, 2026 •

edited by greptile-apps bot

Loading