🦞 ClawReview Report

openclaw/openclaw · 3434 open PRs analyzed · 2026-02-17 03:49 UTC
Models: meta-llama/llama-3.1-70b-instruct, mistralai/mistral-large-latest, google/gemini-2.0-flash-001
3434
PRs Analyzed
283
Duplicate Clusters
688
Duplicate PRs
54
Vision Drift Flags

🔀 Duplicate Clusters

PRs grouped by semantic intent. Within each cluster, PRs are ranked by quality score — #1 is the recommended merge candidate.

Fixes a bug where Slack bot replies in DMs would incorrectly be forced into a thread created by the typing indicator, ignoring the user's `replyToMode` setting.

17 duplicates bugfix area: Slack integration · confidence: 78.0%
Rank
Pull Request
Quality
Review
⭐#1
#14720 fix(slack): pass threadId in plugin read action (#14706)
@lailoo
9.4/10
✓ Consensus
#2
#11194 fix(slack): queue drain drops string thread_ts — replies leak to main channel instead of thread
@Lukavyi
9.3/10
✓ Consensus
#3
#16113 fix(slack): respect replyToMode=off for inline directive reply tags
@zerone0x
9.3/10
✓ Consensus
#4
#8764 fix(slack): respect replyToMode=off for threading
@aithne-z
9.1/10
✓ Consensus
#5
#5098 fix(slack): forward threadId for message.read
@galligan
9.1/10
✓ Consensus
#6
#12414 fix(slack): do not cache API failures in thread_ts resolver
@Yida-Dev
9.1/10
✓ Consensus
#7
#13438 fix(slack): pass threadId through to readSlackMessages in extension plugin
@sandieman2
9.1/10
✓ Consensus
#8
#16143 fix: Slack reply tags bypass replyToMode=off (#16080)
@echoVic
9.1/10
✓ Consensus
#9
#16982 fix(slack): don't create thread via status indicator when replyToMode is off
@arosstale
9.1/10
✓ Consensus
#10
#5514 Slack: fix threadId ignored on read + thread_broadcast dropped
@SanderHelgesen
9.0/10
✓ Consensus
#11
#18036 fix(slack): honour replyToMode off for typing indicator
@theoseo
8.9/10
✓ Consensus
#12
#6509 fix(slack): pass threadId param in read action
@morningstar-daemon
8.9/10
✓ Consensus
#13
#11934 fix(slack): preserve thread_ts in queue drain and deliveryContext
@sandieman2
8.8/10
✓ Consensus
#14
#17969 fix(slack): pass threadId in extension read action
@dostu
8.4/10
⚠ Human Review
#15
#12244 fix(slack): preserve thread context for DM thread replies
@junhoyeo
8.0/10
✓ Consensus
#16
#2917 Slack: fix thread context + prevent reply spillover
@SocialNerd42069
7.6/10
✓ Consensus
#17
#16871 fix(slack): respect replyToMode=off in statusThreadTs
@Limitless2023
5.7/10
⚠ Human Review

Fixes an issue where Telegram Premium users' DM topic replies were incorrectly sent to the top-level chat instead of the intended thread by removing an unnecessary guard that prevented the `message_thread_id` parameter from being included in DM requests.

14 duplicates bugfix area: telegram · confidence: 80.0%
Rank
Pull Request
Quality
Review
⭐#1
#12758 fix(telegram): drop message_thread_id=1 for DM chats
@yukihamada
9.4/10
✓ Consensus
#2
#18214 fix(telegram): preserve DM topic thread params for Premium users
@BinHPdev
9.3/10
✓ Consensus
#3
#17952 fix(telegram): support message_thread_id for DM topics
@timbrinded
9.3/10
✓ Consensus
#4
#12864 fix(telegram): omit thread_id=1 for DMs to prevent cron delivery fail…
@divol89
9.2/10
✓ Consensus
#5
#14443 fix(telegram): skip General topic thread ID for all chat types (#14383)
@lailoo
9.2/10
✓ Consensus
#6
#17433 fix(telegram): omit message_thread_id for private chats to prevent silent message drops
@widingmarcus-cyber
9.0/10
✓ Consensus
#7
#12936 fix(telegram): omit message_thread_id for private DM chats
@omair445
8.9/10
✓ Consensus
#8
#11653 fix(telegram): retry without message_thread_id on stale forum thread error
@liuxiaopai-ai
8.8/10
✓ Consensus
#9
#7261 fix(telegram): preserve DM topic thread id for outbound media
@ViffyGwaanl
8.4/10
✓ Consensus
#10
#7261 fix(telegram): preserve DM topic thread id for outbound media
@ViffyGwaanl
8.4/10
✓ Consensus
#11
#18001 fix(telegram): restore message_thread_id for DM reply-threads
@thebtf
8.3/10
⚠ Human Review
#12
#16882 fix(telegram): ensure sendWithThreadFallback retries for auto-injected thread ID in DM (#16816)
@echoVic
7.9/10
✓ Consensus
#13
#17252 fix: skip message_thread_id for Telegram private chats to prevent silent message drops
@Limitless2023
7.7/10
✓ Consensus
#14
#6192 Telegram: fix DM Topics thread routing
@ViffyGwaanl
6.8/10
✓ Consensus

Fixes a bug where cron jobs get permanently blocked after a timeout or crash by automatically clearing stale `runningAtMs` markers, allowing the job to resume scheduling after twice the job's timeout period.

8 duplicates bugfix area: cron · confidence: 76.0%
Rank
Pull Request
Quality
Review
⭐#1
#17949 fix: clear stale runningAtMs in cron.run() before already-running check (#17554)
@yasumorishima
9.3/10
✓ Consensus
#2
#12448 fix: prevent cron list/status from silently skipping due jobs
@Yida-Dev
9.1/10
✓ Consensus
#3
#5428 fix(Cron): prevent one-shot loop on skip
@imshrishk
8.9/10
✓ Consensus
#4
#12443 fix(cron): don't advance past-due jobs that haven't been executed
@rummangeminicode
8.9/10
✓ Consensus
#5
#17561 fix(cron): add runtime staleness guard for runningAtMs (#17554)
@robbyczgw-cla
8.5/10
✓ Consensus
#6
#17643 fix: clear stale runningAtMs in cron.run to allow manual triggers
@MisterGuy420
8.4/10
✓ Consensus
#7
#18192 fix(cron): auto-clear stale runningAtMs markers after timeout (#18120)
@BinHPdev
8.3/10
✓ Consensus
#8
#17664 fix(cron): detect and clear stale runningAtMs marker in manual run (#17554)
@echoVic
8.2/10
✓ Consensus

Fixes an issue where document messages sent via WhatsApp Web always had the filename 'file' regardless of the actual filename, by correctly passing the filename through the send pipeline.

7 duplicates bugfix area: WhatsApp Web · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#15650 fix(whatsapp): pass fileName to document sends instead of hardcoding 'file'
@whoknowsmann
9.1/10
✓ Consensus
#2
#6566 fix: thread fileName through WhatsApp document send path
@giannisanni
9.0/10
✓ Consensus
#3
#6566 fix: thread fileName through WhatsApp document send path
@giannisanni
9.0/10
✓ Consensus
#4
#10889 fix: pass fileName through WhatsApp document send path
@DeveshParagiri
9.0/10
✓ Consensus
#5
#16785 fix(whatsapp): preserve document filenames in outbound Baileys mode
@SahilSahu731
8.8/10
✓ Consensus
#6
#9606 fix: pass fileName to WhatsApp document messages
@AytuncYildizli
8.2/10
✓ Consensus
#7
#7458 fix: pass filename through to WhatsApp document sends (#7446)
@gavinbmoore
8.0/10
✓ Consensus

Fixes a bug where Signal group IDs were being lowercased during target normalization, causing allowlist matching to fail because Signal group IDs are Base64 encoded and case-sensitive.

7 duplicates bugfix area: signal · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#12793 fix(signal): preserve case-sensitivity for group IDs, UUIDs, and usernames
@wilmerdooley1-star
9.4/10
✓ Consensus
#2
#13640 fix(signal): preserve case-sensitive Base64 group IDs in target normalization
@Siauruk
9.4/10
✓ Consensus
#3
#14462 fix(messaging): preserve case in target normalization fallback (#14263)
@lailoo
9.4/10
✓ Consensus
#4
#10623 fix(signal): preserve case for Base64 group IDs in target normalization
@heyhudson
9.1/10
✓ Consensus
#5
#16562 fix(signal): preserve case for group and username targets
@akalypse
9.1/10
✓ Consensus
#6
#12698 Fix: preserve Signal group ID case during normalization
@hunsbea
9.0/10
✓ Consensus
#7
#4573 fixed the bug: signal group base64 forced to lowercase
@jdainireda03-pixel
7.6/10
✓ Consensus

Adds the `--ignore-scripts` flag to the `npm install` command during plugin installation to prevent supply chain attacks by preventing the execution of arbitrary lifecycle scripts from untrusted packages.

6 duplicates security area: plugins · confidence: 87.0%
Rank
Pull Request
Quality
Review
⭐#1
#8073 fix(plugins): add --ignore-scripts to npm install
@yubrew
9.4/10
✓ Consensus
#2
#8600 fix(update): add --ignore-scripts to prevent supply chain attacks
@yubrew
9.3/10
✓ Consensus
#3
#8075 fix(skills): add --ignore-scripts to all package managers
@yubrew
9.1/10
✓ Consensus
#4
#10528 security: add --ignore-scripts to plugin and hook dependency installation
@abdelsfane
9.0/10
✓ Consensus
#5
#11432 fix(security): add --ignore-scripts to npm install in hook and plugin installers
@coygeek
8.5/10
⚠ Human Review
#6
#13169 security: add --ignore-scripts to npm install during plugin/hook installation
@RamiNoodle733
8.5/10
✓ Consensus

Adds a periodic retry mechanism with bounded exponential backoff to ensure subagent announce messages are eventually delivered, even if initial attempts fail due to temporary issues like gateway unavailability or race conditions.

6 duplicates bugfix area: agents · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#16239 fix: retry on transient API errors (overloaded, rate-limit, timeout)
@zerone0x
9.1/10
✓ Consensus
#2
#9232 Fix: Add automatic retry for network errors in message runs
@vishaltandale00
8.9/10
✓ Consensus
#3
#18205 fix (agents): add periodic retry timer for failed subagent announces
@MegaPhoenix92
8.7/10
✓ Consensus
#4
#16200 fix: retry on transient API errors (overloaded, rate-limit, timeout)
@zerone0x
8.7/10
✓ Consensus
#5
#17001 fix: retry sub-agent announcements with backoff instead of silently dropping on timeout
@luisecab
8.3/10
✓ Consensus
#6
#17028 fix(subagent): retry announce on timeout
@Limitless2023
5.4/10
⚠ Human Review

Removes a false-positive billing error rewrite in `sanitizeUserFacingText` that was triggered on normal assistant responses discussing billing topics, affecting Telegram, Discord, and WhatsApp channels.

6 duplicates bugfix area: agents · confidence: 81.0%
Rank
Pull Request
Quality
Review
⭐#1
#17834 fix: remove false-positive billing error rewrite on normal assistant text
@niceysam
9.3/10
✓ Consensus
#2
#11680 Agents: guard billing error detection with length check (#11649)
@lailoo
9.3/10
✓ Consensus
#3
#12226 fix: remove billing error false-positive from sanitizeUserFacingText
@Yida-Dev
9.3/10
✓ Consensus
#4
#12777 fix: prevent false positive billing error detection in sanitizeUserFacingText
@jpaine
9.2/10
✓ Consensus
#5
#13467 fix(errors): prevent billing false positive in sanitizeUserFacingText
@lailoo
9.2/10
✓ Consensus
#6
#12720 fix: prevent sanitizeUserFacingText false-positives on 402 in normal text
@zerone0x
9.1/10
✓ Consensus

Fixes a race condition where sub-agent model overrides set via `sessions.patch` were sometimes ignored by the agent handler due to stale cached data, ensuring the handler uses the most up-to-date session information from the store.

5 duplicates bugfix area: gateway · confidence: 81.0%
Rank
Pull Request
Quality
Review
⭐#1
#8398 Fix: preserve modelOverride in agent handler (#5369)
@CodeReclaimers
9.1/10
✓ Consensus
#2
#8398 Fix: preserve modelOverride in agent handler (#5369)
@CodeReclaimers
9.1/10
✓ Consensus
#3
#16340 fix: load model catalog from agent-specific directory for sub-agents
@Limitless2023
8.8/10
✓ Consensus
#4
#16988 fix: always regenerate models.json from gateway config
@MisterGuy420
7.1/10
✓ Consensus
#5
#13376 fix: pass model directly to agent for sub-agent runs
@jrbobbyhansen-pixel
6.7/10
✓ Consensus

Fixes a bug where context token lookups could return incorrect context window sizes due to cross-provider model ID collisions by using only available models from configured providers.

5 duplicates bugfix area: agents · confidence: 80.0%
Rank
Pull Request
Quality
Review
⭐#1
#17604 fix(context): use getAvailable() to prevent cross-provider model ID collision in MODEL_CACHE
@aldoeliacim
9.1/10
✓ Consensus
#2
#17638 fix: lookupContextTokens() returns wrong contextWindow due to cross-provider model ID collision
@MisterGuy420
9.1/10
✓ Consensus
#3
#14744 fix(context): key MODEL_CACHE by provider/modelId to prevent collision (#14708)
@lailoo
8.9/10
✓ Consensus
#4
#17641 fix: use getAvailable() in lookupContextTokens to prevent cross-provider model ID collision (#17586)
@echoVic
7.7/10
✓ Consensus
#5
#15632 fix: use provider-qualified key in MODEL_CACHE for context window lookup
@linwebs
7.7/10
✓ Consensus

Adds the ability to route webhook requests to a specific agent by introducing an optional `agentId` parameter in the webhook payload.

4 duplicates feature area: gateway · confidence: 90.0%
Rank
Pull Request
Quality
Review
⭐#1
#7846 feat: add agentId param to webhook agent endpoint
@Bre77
8.8/10
✓ Consensus
#2
#9800 feat(hooks): allow webhook mappings to route to specific agents via a…
@bogdanClawdy
8.7/10
✓ Consensus
#3
#10383 feat(hooks): add agentId to hook mappings
@quentintou
8.1/10
✓ Consensus
#4
#10663 feat(hooks): add agentId support for webhook routing
@nityatrish
8.0/10
✓ Consensus

Filters HEARTBEAT_OK messages from the chat history in the Control UI when showOk is false, aligning history behavior with live chat broadcasts.

4 duplicates bugfix area: gateway · confidence: 91.0%
Rank
Pull Request
Quality
Review
⭐#1
#11647 fix(webchat): filter HEARTBEAT_OK messages from chat.history response
@liuxiaopai-ai
9.4/10
✓ Consensus
#2
#11889 fix(chat): filter HEARTBEAT_OK messages in chat.history when showOk is false
@bendyclaw
9.4/10
✓ Consensus
#3
#11859 fix: filter HEARTBEAT_OK messages from chat.history when showOk is false
@Zjianru
9.0/10
✓ Consensus
#4
#11661 fix: Filter HEARTBEAT_OK from chat.history when showOk is false
@veast
8.8/10
✓ Consensus

Fixes false positives in `sanitizeUserFacingText` by introducing an `errorContext` flag to ensure error-specific rewrites are only applied to actual error messages, preventing normal assistant replies from being incorrectly modified.

4 duplicates bugfix area: agents · confidence: 80.0%
Rank
Pull Request
Quality
Review
⭐#1
#11685 Agents: scope error rewrites in sanitizeUserFacingText behind errorContext flag (#11649)
@lailoo
9.1/10
✓ Consensus
#2
#12052 fix: scope error-detection heuristics to error source in sanitizeUserFacingText
@skylarkoo7
9.1/10
✓ Consensus
#3
#12702 fix: prevent sanitizeUserFacingText false-positives on assistant prose
@zerone0x
9.1/10
✓ Consensus
#4
#13318 fix(agents): prevent sanitizeUserFacingText from rewriting conversational context overflow mentions
@hleliofficiel
8.4/10
✓ Consensus

Fixes a bug in the cron scheduler where the timer callback would not fire for scheduled jobs due to incorrect timer clearing logic, and improves logging for debugging.

4 duplicates bugfix area: cron · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#12303 fix(cron): correct nextRunAtMs calculation and prevent timer stall
@colddonkey
9.0/10
✓ Consensus
#2
#12131 fix(cron): ensure timer callback fires for scheduled jobs
@divol89
8.9/10
✓ Consensus
#3
#12122 fix(cron): ensure timer callback fires for scheduled jobs
@divol89
8.8/10
✓ Consensus
#4
#12086 fix(cron): ensure timer callback fires for scheduled jobs
@divol89
6.5/10
✓ Consensus

Prevents the HEARTBEAT_OK token, an internal acknowledgement, from being incorrectly delivered to user channels, even when visibility.showOk is enabled.

4 duplicates bugfix area: heartbeat · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#16980 fix(heartbeat): strip HEARTBEAT_OK from streaming path for heartbeat runs
@aldoeliacim
9.2/10
✓ Consensus
#2
#12837 fix(heartbeat): suppress HEARTBEAT_OK token delivery
@JBrady
8.9/10
✓ Consensus
#3
#17009 fix(heartbeat): strip HEARTBEAT_OK from streaming during heartbeat runs
@arosstale
8.4/10
⚠ Human Review
#4
#17006 fix(heartbeat): skip delivery when showOk is false
@Limitless2023
7.3/10
✓ Consensus

Fixes a bug where `dangerouslyDisableDeviceAuth` did not properly bypass device identity checks and cleared operator scopes, preventing the Control UI from functioning correctly.

4 duplicates bugfix area: gateway · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#17572 fix: make dangerouslyDisableDeviceAuth bypass device identity checks
@gitwithuli
9.1/10
✓ Consensus
#2
#17844 fix: preserve scopes when dangerouslyDisableDeviceAuth is enabled
@Maxymvs
8.2/10
⚠ Human Review
#3
#17605 fix: preserve scopes when disableControlUiDeviceAuth is enabled
@MisterGuy420
7.9/10
✓ Consensus
#4
#17180 fix: preserve scopes when dangerouslyDisableDeviceAuth is enabled
@Limitless2023
6.6/10
⚠ Human Review

Skips the embedding provider check in `openclaw doctor` when the QMD memory backend is active, preventing a false positive warning.

4 duplicates bugfix area: doctor command · confidence: 90.0%
Rank
Pull Request
Quality
Review
⭐#1
#17295 fix(doctor): skip embedding provider check when QMD backend is active
@miloudbelarebia
9.4/10
✓ Consensus
#2
#17360 fix(doctor): skip embedding provider check when memory backend is QMD
@nikhil8182
9.4/10
✓ Consensus
#3
#17381 fix: skip embedding provider check in doctor when QMD backend is enabled
@Limitless2023
8.3/10
✓ Consensus
#4
#17660 fix: skip embedding provider check in doctor when QMD backend is configured (#17263)
@echoVic
7.9/10
✓ Consensus

Fixes a lost-update race condition in `updateSessionStoreEntry` and `updateLastRoute` by ensuring the session store is re-read from disk within the lock, preventing stale cached data from overwriting concurrent writes.

4 duplicates bugfix area: session store · confidence: 81.0%
Rank
Pull Request
Quality
Review
⭐#1
#10726 fix: re-read session store inside lock in updateLastRoute
@Yida-Dev
9.5/10
✓ Consensus
#2
#10725 fix: re-read session store inside lock in updateSessionStoreEntry
@Yida-Dev
9.4/10
✓ Consensus
#3
#16987 fix(config): add skipCache to updateSessionStoreEntry and updateLastRoute to prevent lost updates
@AI-Reviewer-QS
9.2/10
✓ Consensus
#4
#15882 fix: move session entry computation inside store lock to prevent race conditions
@cloorus
8.9/10
✓ Consensus

Prevents orphaned tool results by dropping assistant messages with a 'stopReason' of 'error' during transcript repair, which can occur when providers filter out errored assistant messages.

4 duplicates bugfix area: transcript repair · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#4844 fix(agents): skip error/aborted assistant messages in transcript repair
@lailoo
9.3/10
✓ Consensus
#2
#9416 fix: drop errored/aborted assistant tool pairs in transcript repair
@xandorklein
9.2/10
✓ Consensus
#3
#3880 fix: drop assistant messages with stopReason 'error' to avoid orphaning tool results (#3860)
@SalimBinYousuf1
6.9/10
✓ Consensus
#4
#3880 fix: drop assistant messages with stopReason 'error' to avoid orphaning tool results (#3860)
@SalimBinYousuf1
6.9/10
✓ Consensus

Enable Slack Block Kit functionality for plugin-level edit actions, allowing plugins to update messages with structured blocks instead of just plain text.

4 duplicates feature area: Slack integration · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#18262 feat(slack): support Block Kit blocks in editMessage
@Solvely-Colin
8.7/10
✓ Consensus
#2
#18257 feat(slack): support Block Kit blocks in sendMessage
@Solvely-Colin
8.7/10
✓ Consensus
#3
#18268 feat(slack): support blocks in plugin send action
@Solvely-Colin
7.8/10
⚠ Human Review
#4
#18278 feat(slack): support blocks in plugin edit action
@Solvely-Colin
7.4/10
✓ Consensus

Prevents a cron job from entering a tight spin loop and starving the event loop when its next execution time is in the past by enforcing a minimum timer delay.

3 duplicates bugfix area: cron · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#16861 fix(cron): add minimum timer delay floor to prevent spin loop
@echoVic
9.1/10
✓ Consensus
#2
#17370 fix(cron): prevent spin loop when timer delay resolves to 0ms
@BinHPdev
8.9/10
✓ Consensus
#3
#16878 fix(cron): prevent timer spin loop with minimum delay floor
@Limitless2023
7.9/10
✓ Consensus

Fixes a bug where WhatsApp media from group members was not downloaded when using groupPolicy: allowlist and the group was in the groups allowlist but the sender was not in groupAllowFrom, by allowing messages from all participants in groups that are explicitly in the groups allowlist.

3 duplicates bugfix area: WhatsApp inbound access control · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#6567 fix: include paired users in WhatsApp group sender allowlist
@giannisanni
9.2/10
✓ Consensus
#2
#6567 fix: include paired users in WhatsApp group sender allowlist
@giannisanni
9.2/10
✓ Consensus
#3
#4390 fix(whatsapp): allow media from allowlisted groups without groupAllow…
@Sarang19114
8.6/10
✓ Consensus

Fixes a bug where memory flush was not triggering before compaction because it was using the last turn's tokens instead of the cumulative context size for the threshold check.

3 duplicates bugfix area: memory management · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#12760 fix(memory-flush): fire on every compaction cycle instead of skipping alternate cycles (#12590)
@lailoo
9.3/10
✓ Consensus
#2
#15945 fix(memory-flush): only write memoryFlushCompactionCount when compaction succeeds
@aldoeliacim
9.3/10
✓ Consensus
#3
#4999 fix(memory-flush): use contextTokens instead of totalTokens for threshold check
@Farfadium
8.5/10
✓ Consensus

Fixes a bug where WhatsApp replies from LID JIDs were not correctly identified as replies to the bot, preventing implicit mentions from working as expected when requireMention is true.

3 duplicates bugfix area: whatsapp-web integration · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#11166 fix(whatsapp): detect LID @mentions in self-chat mode
@mcaxtr
9.3/10
✓ Consensus
#2
#17256 fix: allow text regex fallback when bot JID not in mentionedJids
@DarlingtonDeveloper
9.2/10
✓ Consensus
#3
#16655 fix(whatsapp): resolve reply-to sender E.164 for LID JIDs (have bot see replys without a mention even with "requireMention: true", like the Discord integration)
@mascarenhas
9.0/10
✓ Consensus

Add baseline HTTP security headers to all gateway responses to improve security posture.

3 duplicates security area: gateway · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#10526 security: add baseline security headers to gateway HTTP responses
@abdelsfane
8.8/10
✓ Consensus
#2
#6906 Add baseline HTTP security headers to gateway responses
@QuantumEdu
8.6/10
✓ Consensus
#3
#6906 Add baseline HTTP security headers to gateway responses
@QuantumEdu
8.6/10
✓ Consensus

Fixes a bug where inbound voice calls were not properly cleaned up when disconnected by using media stream disconnect as a fallback signal to mark the call as ended, preventing the exhaustion of the `maxConcurrentCalls` limit.

3 duplicates bugfix area: voice-call · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#9760 fix(voice-call): discard stale calls on plugin restart
@leszekszpunar
9.0/10
✓ Consensus
#2
#6702 fix(voice-call): mark calls as ended when media stream disconnects
@johngnip
7.5/10
✓ Consensus
#3
#6702 fix(voice-call): mark calls as ended when media stream disconnects
@johngnip
7.5/10
✓ Consensus

Integrate Ollama as a supported provider, enabling auto-discovery of local models and providing configuration options for custom Ollama instances.

3 duplicates feature area: onboarding, auth, providers · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#7278 feat(ollama): optimize local LLM support with auto-discovery and timeouts
@alltomatos
8.5/10
✓ Consensus
#2
#7278 feat(ollama): optimize local LLM support with auto-discovery and timeouts
@alltomatos
8.5/10
✓ Consensus
#3
#7432 Comprehensive Ollama Support PR
@charlieduzstuf
7.2/10
✓ Consensus

Wires up the `message_sending` plugin hook in the outbound delivery pipeline, allowing plugins to modify outgoing message content or cancel delivery before the channel adapter sends the message.

3 duplicates feature area: outbound delivery · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#8084 fix(plugins): wire up message_sending hook in outbound delivery
@lailoo
8.8/10
✓ Consensus
#2
#9906 feat: wire message_sending hook in outbound delivery
@teempai
8.8/10
✓ Consensus
#3
#10066 feat(plugins): wire message_sending hook in deliverOutboundPayloads
@davinci-ai
8.2/10
✓ Consensus

Adds the ability to configure the `thinkingDefault` setting on a per-model basis, allowing different models to have different default thinking levels.

3 duplicates feature area: agents · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#18152 feat: support per-model thinkingDefault override in models config
@wu-tian807
8.8/10
✓ Consensus
#2
#16899 feat(config): per-agent and per-model thinking defaults
@jh280722
8.5/10
✓ Consensus
#3
#15030 Agents: support per-agent thinking defaults
@sauerdaniel
7.8/10
⚠ Human Review

Fixes cron jobs created via the tool API not auto-firing because the `enabled` flag was not being defaulted to `true` when omitted, preventing the calculation of `nextRunAtMs`.

3 duplicates bugfix area: cron · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#8701 fix: default enabled to true for cron jobs created via tool API
@maximus-claw
9.4/10
✓ Consensus
#2
#9088 fix(cron): ensure nextRunAtMs is computed when enabled is undefined (#9056)
@divol89
8.9/10
✓ Consensus
#3
#9088 fix(cron): ensure nextRunAtMs is computed when enabled is undefined (#9056)
@divol89
8.9/10
✓ Consensus

Prevents unnecessary gateway restarts triggered by changes to the `meta.lastTouchedAt` field in the configuration by marking the `meta` section as non-actionable for config reloads.

3 duplicates bugfix area: gateway · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#11746 fix: treat meta config paths as no-op to prevent unnecessary gateway restarts
@QDenka
9.3/10
✓ Consensus
#2
#11280 fix(gateway): add meta prefix to reload rules to prevent double SIGUSR1
@cheenu1092-oss
9.2/10
✓ Consensus
#3
#8473 fix(gateway): prevent spurious restarts on meta.lastTouchedAt changes
@adam-smeth
8.9/10
✓ Consensus

Adds Mistral AI as a supported provider, including CLI onboarding, configuration, and documentation, enabling users to easily use Mistral's models within the application.

3 duplicates feature area: CLI onboarding wizard and provider configuration · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#16258 feat(models): add Mistral AI provider support
@joeVenner
8.3/10
✓ Consensus
#2
#9647 feat(providers): add Mistral AI as first-class provider
@Shimadakunn
7.4/10
⚠ Human Review
#3
#14730 Add Mistral AI as a model provider
@jaimegh-es
6.9/10
⚠ Human Review

Replaces direct console.warn calls in the compaction agent with the SubsystemLogger for consistent logging.

3 duplicates refactor area: agents · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#9425 refactor(agents): replace console.warn with SubsystemLogger in compaction.ts
@dinakars777
9.5/10
✓ Consensus
#2
#9990 refactor(agents): replace console.warn with SubsystemLogger in venice-models.tsrefactor(agents): replace console.warn with SubsystemLogger in venice…
@dinakars777
8.0/10
✓ Consensus
#3
#9974 refactor(agents): replace console.warn with SubsystemLogger in compaction-safeguard.ts
@dinakars777
5.3/10
⚠ Human Review

Fixes a bug where rate-limit errors from Anthropic were being incorrectly classified as context overflow errors by tightening the regex used for context overflow detection and adding guard clauses to exclude rate-limit and billing errors.

3 duplicates bugfix area: agents · confidence: 81.0%
Rank
Pull Request
Quality
Review
⭐#1
#10003 fix: stop misclassifying rate-limit errors as context overflow
@maxtongwang
9.1/10
✓ Consensus
#2
#10601 fix: prevent FailoverError (rate_limit/billing) from being misreported as context overflow
@DukeDeSouth
9.1/10
✓ Consensus
#3
#11174 Fix/fried chicken error
@jfgrissom
8.3/10
✓ Consensus

Fixes a false positive in the `openclaw doctor` command that incorrectly identified unrelated LaunchAgents as gateway-like services by adding a check to only consider services with labels starting with `ai.openclaw.` after detecting an 'openclaw' marker.

3 duplicates bugfix area: gateway · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#10182 fix: skip non-openclaw LaunchAgents in doctor gateway scan
@Yida-Dev
9.2/10
✓ Consensus
#2
#15908 fix: doctor falsely flags non-gateway services as 'gateway-like'
@echoVic
7.1/10
✓ Consensus
#3
#15903 fix(doctor): stricter gateway service detection to prevent false positives
@Shuai-DaiDai
5.5/10
⚠ Human Review

Fixes a bug where the Mattermost integration incorrectly required mentions in group channels even when the `chatmode` was set to `onmessage`, by ensuring the account-level mention preference is passed into group mention resolution as a fallback.

3 duplicates bugfix area: mattermost · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#10081 fix(mattermost): pass requireMentionOverride to core resolver
@manchmod
8.8/10
✓ Consensus
#2
#14995 fix(mattermost): honor chatmode mention fallback in group mention gating
@ninjaa
8.6/10
✓ Consensus
#3
#10587 fix(extensions/mattermost): pass requireMention override from chatmode config
@baku4
8.4/10
⚠ Human Review

Fixes a false positive warning message in the logs for the 'read' tool when the 'file_path' alias is used instead of 'path'.

3 duplicates bugfix area: agents · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#10938 fix(agents): normalize read tool params before path guard check
@wony2
9.4/10
✓ Consensus
#2
#10504 fix: check file_path alias in read tool path warning
@tamio0800
8.0/10
✓ Consensus
#3
#11564 fix(agents): support file_path alias in read tool monitoring
@janckerchen
7.7/10
✓ Consensus

Adds support for sending audio messages in Feishu, fixes a file upload bug, and enhances the reply dispatcher to handle media URLs.

3 duplicates feature area: Feishu extension · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#15351 feat(feishu): Add native audio message support (voice bubble)
@lovejing0306
7.9/10
⚠ Human Review
#2
#13669 feat(feishu): add audio message support
@AGI-XiaoBai-No1
7.8/10
⚠ Human Review
#3
#10675 feat(feishu): add audio message support and fix file upload
@YumoeZhung
7.5/10
✓ Consensus

Fixes a bug in bash completion generation where empty flags in command options would cause spurious completion matches.

3 duplicates bugfix area: cli · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#10710 fix(cli): filter empty flags in bash completion generation
@Yida-Dev
9.3/10
✓ Consensus
#2
#10723 fix(cli): filter empty flags in PowerShell completion generation
@Yida-Dev
9.2/10
✓ Consensus
#3
#11165 fix(cli): filter empty flags in zsh and PowerShell nested completion
@Yida-Dev
9.1/10
✓ Consensus

Hides assistant messages containing only tool call information when the 'Toggle assistant thinking/working output' button is off in the Control UI, preventing tool call blocks from being displayed when they should be hidden.

3 duplicates feature area: UI · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#10996 fix(control-ui): hide tool call blocks when thinking/working toggle is off
@Annaxiebot
8.5/10
✓ Consensus
#2
#11010 fix(control-ui): hide tool call cards when thinking toggle is off
@Annaxiebot
8.0/10
✓ Consensus
#3
#11526 fix(control-ui): hide tool-only assistant messages when thinking is off
@Annaxiebot
7.9/10
✓ Consensus

Adds support for the DeepSeek provider (DeepSeek-V3, DeepSeek-R1) to enable users to utilize DeepSeek models within the application.

3 duplicates feature area: onboarding · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#11151 feat: add DeepSeek provider support
@MackDing
8.4/10
✓ Consensus
#2
#14393 feat: add standalone DeepSeek provider support
@osoulmate
8.4/10
✓ Consensus
#3
#12503 feat: add DeepSeek provider suppor
@MackDing
8.2/10
✓ Consensus

Enforces a non-empty secret at runtime for Telegram webhook mode to prevent unauthenticated update injection, addressing a security vulnerability.

3 duplicates security area: Telegram webhook · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#13117 fix: Telegram webhook mode allows unauthenticated update injection when
@coygeek
9.5/10
✓ Consensus
#2
#13170 security: enforce webhookSecret at runtime for Telegram webhook mode
@RamiNoodle733
9.4/10
✓ Consensus
#3
#13521 telegram: require webhook secret in runtime webhook mode
@davidahmann
8.5/10
✓ Consensus

Adds support for Cloudflare's Markdown for Agents by modifying the Accept header in web-fetch to prefer markdown responses while maintaining backward compatibility with existing servers.

3 duplicates feature area: agents · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#15251 feat(web-fetch): send Accept: text/markdown header for Cloudflare Markdown for Agents
@wujieli0207
9.3/10
✓ Consensus
#2
#15242 feat(web-fetch): Add Accept header for Cloudflare Markdown for Agents [AI-assisted]
@drkraft
8.2/10
✓ Consensus
#3
#15414 feat(web-fetch): add Accept: text/markdown header for Cloudflare Markdown for Agents
@aldoeliacim
8.2/10
✓ Consensus

Adds comprehensive GraphQL documentation to the GitHub skill, including basic query and mutation examples, schema introspection commands, and guidance to prevent hallucination when working with GitHub Projects V2

3 duplicates docs area: skills/github · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#15894 docs: add GraphQL and schema introspection guidance to GitHub skill
@echoVic
9.0/10
⚠ Human Review
#2
#15810 feat(skill): add GraphQL guidance to GitHub skill
@brandonwise
8.6/10
⚠ Human Review
#3
#15803 fix(skills/github): add GraphQL introspection guidance
@rixau
7.8/10
⚠ Human Review

Implements lazy-loading of CLI commands to improve cold-start performance by deferring the import of command dependencies until the command is actually invoked.

3 duplicates performance area: CLI · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#15977 perf(cli): lazy-load core command infrastructure
@RocketMan234
7.8/10
✓ Consensus
#2
#15978 perf(cli): defer browser-cli and status command imports
@RocketMan234
7.8/10
✓ Consensus
#3
#15979 perf(cli): defer all sub-CLI imports and add help stubs
@RocketMan234
7.5/10
✓ Consensus

Fixes a bug where `resolveSessionFilePath` was defaulting to the main agent's session directory when called for other agents, leading to incorrect file path resolution and errors when accessing sessions for non-main agents, and also includes unrelated changes such as cross-gateway support, per-agent API key preservation, and CI/CD pipeline updates.

3 duplicates bugfix area: gateway · confidence: 81.0%
Rank
Pull Request
Quality
Review
⭐#1
#16325 fix: resolve agentId from sessionKey when not provided
@Limitless2023
8.4/10
✓ Consensus
#2
#15792 fix: pass agentId to resolveSessionFilePath in additional call sites
@MisterGuy420
7.3/10
✓ Consensus
#3
#15982 fix: pass agentId to resolveSessionFilePath in reply flow (NX-003)
@automagik-genie
4.6/10
✓ Consensus

Adds a new 'set_public_permission' action to the Feishu Doc tool, allowing users to programmatically set the public access level (read or edit) of a document.

3 duplicates feature area: feishu · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#16594 feat(feishu): add set_public_permission doc action
@ciberponk
9.0/10
✓ Consensus
#2
#16607 feat(feishu): add get_public_permission doc action
@ciberponk
9.0/10
✓ Consensus
#3
#16637 feat(feishu_doc): support optional public_access on create
@ciberponk
8.1/10
⚠ Human Review

Fixes a bug where clawdock helper commands were not including docker-compose.extra.yml, causing volume mounts defined there to be ignored.

3 duplicates bugfix area: clawdock · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#17094 fix(clawdock): include docker-compose.extra.yml in helper commands
@zerone0x
8.2/10
⚠ Human Review
#2
#17104 fix(clawdock): include docker-compose.extra.yml in compose commands
@Limitless2023
7.9/10
✓ Consensus
#3
#17097 fix(clawdock): include docker-compose.extra.yml in compose commands
@DhruvGarg111
7.9/10
✓ Consensus

Fixes a bug where inbound voice calls via Telnyx were being silently dropped by ensuring the `direction`, `from`, and `to` fields are passed through and the `direction` field is normalized from Telnyx's `incoming`/`outgoing` to `inbound`/`outbound`.

3 duplicates bugfix area: voice-call · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#16811 Fix Telnyx inbound calls silently dropped — normalizeEvent missing direction/from/to
@Clawborn
9.4/10
✓ Consensus
#2
#16651 fix(voice-call): pass direction, from, to fields in Telnyx call.initiated events
@brandonwise
9.3/10
✓ Consensus
#3
#16998 fix(voice-call): pass direction/from/to in Telnyx call.initiated events
@arosstale
9.2/10
✓ Consensus

Adds a foundational Chinese UI translation project to OpenClaw, including core translations and documentation, to improve accessibility for Chinese-speaking users.

3 duplicates feature area: UI · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#17974 feat: Add Chinese UI translation project
@durenzidu
7.6/10
✓ Consensus
#2
#10586 feat: Add Chinese (zh-CN) localization support
@Maxsong-0
7.6/10
⚠ Human Review
#3
#9490 Add Internationalization (i18n) Support
@luuman
7.3/10
⚠ Human Review

Enables the memory-lancedb plugin to support custom OpenAI-compatible endpoints (e.g., Ollama, vLLM) by allowing a configurable baseURL and custom vector dimensions.

3 duplicates feature area: memory-lancedb · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#17874 feat(memory-lancedb): Custom OpenAI BaseURL & Dimensions Support
@rish2jain
8.9/10
✓ Consensus
#2
#17566 memory-lancedb: support local OpenAI-compatible embeddings
@lumenradley
8.4/10
✓ Consensus
#3
#10064 feat(memory-lancedb): Support custom embedding providers (SiliconFlow, etc.)
@kckylechen1
7.8/10
✓ Consensus

Fixes a false positive in the `openclaw doctor` command that incorrectly reports permission warnings for symlinks pointing to the Nix store on NixOS systems.

3 duplicates bugfix area: doctor tool · confidence: 90.0%
Rank
Pull Request
Quality
Review
⭐#1
#11458 fix(doctor): skip config permission check on symlinks
@AnonO6
9.3/10
✓ Consensus
#2
#11408 Security: resolve symlink target permissions in safeStat; skip doctor config warning for symlinks (#11307)
@lailoo
8.9/10
✓ Consensus
#3
#16957 fix(doctor): skip false positive permission warnings for Nix store symlinks
@soumikbhatta
8.3/10
⚠ Human Review

Adds support for the DingTalk messaging platform as a new channel within OpenClaw, including inbound/outbound message handling, configuration, and documentation.

3 duplicates feature area: channels · confidence: 87.0%
Rank
Pull Request
Quality
Review
⭐#1
#9444 feat(channels): add DingTalk channel
@sm-yjr
7.7/10
✓ Consensus
#2
#13291 feat(ddingtalk): add DingTalk(ddingtalk) channel extension
@largezhou
7.1/10
✓ Consensus
#3
#10347 DingTalk: add channel support
@dimaginexus
6.7/10
⚠ Human Review

Fixes a bug where the `before_tool_call` hook was firing twice when an abort signal was present due to a Symbol property being dropped during object spreading.

3 duplicates bugfix area: agents · confidence: 91.0%
Rank
Pull Request
Quality
Review
⭐#1
#16978 fix(hooks): preserve before_tool_call marker across abort signal wrapping
@arosstale
9.6/10
✓ Consensus
#2
#16852 fix: before_tool_call hook double-fires with abort signal
@sreuter
9.4/10
✓ Consensus
#3
#16870 fix: before_tool_call hook double-fire with abort signal
@Limitless2023
4.5/10
✓ Consensus

Fixes an issue where session file paths from one agent are incorrectly validated against the main agent's sessions directory in multi-agent setups, causing errors when sub-agents with explicit agentDir configurations try to reference their own session files.

3 duplicates bugfix area: sessions · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#16249 fix(sessions): allow cross-agent session paths in multi-agent bindings
@0xbrak
9.1/10
✓ Consensus
#2
#15474 fix: validate session file paths against any agent sessions dir
@maximalmargin
8.9/10
✓ Consensus
#3
#16171 fix: trust absolute sessionFile paths in multi-agent setups
@iJaack
8.9/10
✓ Consensus

Improves the performance of shell completion generation by avoiding the loading of heavy plugins during the process, resulting in significantly faster completion script generation.

3 duplicates performance area: CLI · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#17680 perf(cli): skip plugin loading during completion generation
@mcrolly
9.4/10
✓ Consensus
#2
#13840 perf(cli): skip plugin loading during completion generation
@lailoo
9.1/10
✓ Consensus
#3
#9158 perf(completion): add fast path for cached completions
@gavinbmoore
7.8/10
✓ Consensus

Prevents the TUI from crashing when a rendered line exceeds the terminal width by truncating overwide lines.

3 duplicates bugfix area: TUI · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#17677 fix(tui): prevent crash when rendered line exceeds terminal width
@Phineas1500
9.3/10
✓ Consensus
#2
#12913 TUI: truncate lines to fit terminal width on narrow terminals
@kutayilmaaz
8.1/10
✓ Consensus
#3
#6260 fix(tui): prevent width overflow crashes from nested ANSI escape codes
@0xktn
7.5/10
✓ Consensus

Fixes an issue where auto-paired Dashboard/webchat devices were not receiving the full set of operator scopes after a gateway restart, preventing them from functioning correctly, and includes several other related fixes and improvements.

3 duplicates bugfix area: gateway · confidence: 87.0%
Rank
Pull Request
Quality
Review
⭐#1
#17205 fix: enforce full operator scopes for Control UI and Webchat auto-pairing
@Limitless2023
6.7/10
✓ Consensus
#2
#17205 fix: enforce full operator scopes for Control UI and Webchat auto-pairing
@Limitless2023
6.7/10
✓ Consensus
#3
#17201 fix: include full operator scopes for auto-paired Dashboard/webchat devices
@Limitless2023
5.3/10
✓ Consensus

Restores the correct priority of device tokens over config tokens for authentication, fixing a regression introduced in v2026.2.14 where config tokens were incorrectly prioritized.

3 duplicates bugfix area: gateway · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#17279 fix: restore device token priority over config token
@MisterGuy420
9.0/10
✓ Consensus
#2
#17336 fix(gateway): restore device token priority over passive config token
@milosm
8.4/10
⚠ Human Review
#3
#17379 fix: restore device token priority in device-auth mode
@Limitless2023
7.4/10
⚠ Human Review

Fixes a bug where WhatsApp Web QR login auto-retry fails to trigger for 515 "restart required" errors due to incorrect status code extraction from nested error structures.

3 duplicates bugfix area: WhatsApp Web · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#3071 fix: WhatsApp 515 error retry not triggering
@rabsef-bicrym
8.9/10
✓ Consensus
#2
#3071 fix: WhatsApp 515 error retry not triggering
@rabsef-bicrym
8.9/10
✓ Consensus
#3
#9515 fix(web): retry WhatsApp 515 restart up to 3 times with delay
@Sebachowa
7.6/10
✓ Consensus

Fixes a bug where the `pnpm ui:build` command fails on Windows when the pnpm executable path contains spaces due to incorrect handling by the shell.

3 duplicates bugfix area: UI · confidence: 96.0%
Rank
Pull Request
Quality
Review
⭐#1
#4295 fix: quote Windows paths with spaces in UI runner command
@Xieweikang123
6.8/10
✓ Consensus
#2
#4295 fix: quote Windows paths with spaces in UI runner command
@Xieweikang123
6.8/10
✓ Consensus
#3
#10051 CLI: fix ui build on Windows when pnpm path contains spaces
@jibrailinitdsg
6.5/10
⚠ Human Review

Enables autoSelectFamily by default for Node.js 22+ in the Telegram plugin to allow IPv4 fallback when IPv6 is configured but not properly routed, resolving issues with sending messages on certain networks.

2 duplicates bugfix area: telegram · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#18272 fix(telegram): enable autoSelectFamily by default for Node.js 22+
@nacho9900
9.2/10
✓ Consensus
#2
#10796 fix(telegram): use undici Agent with autoSelectFamily for Node 22+ IPv6 fix
@yashmakhija
8.7/10
✓ Consensus

Sanitize tool call IDs for Azure OpenAI to comply with the 40-character limit enforced by Azure OpenAI's API.

2 duplicates bugfix area: agents · confidence: 87.0%
Rank
Pull Request
Quality
Review
⭐#1
#8117 Agents: sanitize tool call ids for OpenAI
@TylonHH
7.4/10
✓ Consensus
#2
#4057 fix: sanitize tool call IDs for Azure OpenAI
@wangchuan3533
6.2/10
✓ Consensus

Fixes a bug where orphaned user messages, when rebuilt into the session context, bypass the sanitization pipeline, leading to mismatched tool_use/tool_result pairings and API errors.

2 duplicates bugfix area: agents · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#4009 fix(agent): sanitize messages after orphan user repair
@drag88
9.1/10
✓ Consensus
#2
#4009 fix(agent): sanitize messages after orphan user repair
@drag88
9.1/10
✓ Consensus

Converts Unicode emojis used in Slack ack reactions to Slack shortcodes to prevent `invalid_name` errors when interacting with the Slack API.

2 duplicates bugfix area: slack · confidence: 87.0%
Rank
Pull Request
Quality
Review
⭐#1
#4257 fix(slack): Convert Unicode emojis to Slack shortcodes for ack reactions
@rossshannon
8.0/10
✓ Consensus
#2
#4257 fix(slack): Convert Unicode emojis to Slack shortcodes for ack reactions
@rossshannon
8.0/10
✓ Consensus

Updates Antigravity integration to avoid recent gateway failures by bumping the hardcoded Antigravity User-Agent version and adding a transcript sanitizer to ensure tool-related blocks include a required input object

2 duplicates bugfix area: agents · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#4445 fix: resolve Antigravity "unsupported version" and tool_use schema validation errors
@harry2690
7.9/10
✓ Consensus
#2
#4445 fix: resolve Antigravity "unsupported version" and tool_use schema validation errors
@harry2690
7.9/10
✓ Consensus

Upgrades the Dockerfile's base image to Node.js 24 to leverage the latest Active LTS version for security, performance, and long-term support.

2 duplicates config area: Docker · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#4116 Update Dockerfile to node 24
@kotov228
7.1/10
⚠ Human Review
#2
#4116 Update Dockerfile to node 24
@kotov228
7.1/10
⚠ Human Review

Improve gateway stability by handling transient mDNS/Bonjour errors and providing a CLI flag to disable mDNS advertising.

2 duplicates bugfix area: gateway · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#4653 fix(gateway): improve crash resilience for mDNS and network errors
@AyedAlmudarra
8.2/10
✓ Consensus
#2
#4653 fix(gateway): improve crash resilience for mDNS and network errors
@AyedAlmudarra
8.2/10
✓ Consensus

Prevents outbound direct message sends from overwriting the main session's display name with the last recipient's name, while still updating delivery context for accurate routing.

2 duplicates bugfix area: outbound messaging · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#4693 fix: keep main session displayName on outbound sends
@ManojINaik
7.2/10
✓ Consensus
#2
#4693 fix: keep main session displayName on outbound sends
@ManojINaik
7.2/10
✓ Consensus

Adds proactive compaction to the embedded Pi agent runner to prevent context overflow by checking token usage before sending API requests and compacting if necessary.

2 duplicates feature area: agents · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#4042 agents: add proactive compaction before request
@freedomzt
8.6/10
✓ Consensus
#2
#4042 agents: add proactive compaction before request
@freedomzt
8.6/10
✓ Consensus

Adds a configuration option to store messages from non-allowlisted group members as context, allowing the agent to see all messages in a group even if some members are not allowed to trigger the agent.

2 duplicates feature area: WhatsApp group messaging · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#4402 fix: store group messages from non-allowlisted senders as pending context
@adam91holt
8.6/10
✓ Consensus
#2
#4402 fix: store group messages from non-allowlisted senders as pending context
@adam91holt
8.6/10
✓ Consensus

Adds validation to base64 encoded image data before sending it to the Anthropic API to prevent session corruption caused by invalid image data, replacing invalid images with descriptive text blocks.

2 duplicates bugfix area: agents · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#18263 fix: validate base64 image data before API submission
@sriram369
9.1/10
✓ Consensus
#2
#18219 fix: validate base64 image data before sending to LLM APIs
@Grynn
9.1/10
✓ Consensus

Reduces lock contention on the global sessions.json file by introducing per-session metadata files for frequent updates and a debounced background sync to keep the global file in sync.

2 duplicates performance area: session management · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#4664 fix: per-session metadata files to eliminate lock contention
@tsukhani
7.5/10
✓ Consensus
#2
#4664 fix: per-session metadata files to eliminate lock contention
@tsukhani
7.5/10
✓ Consensus

Corrects the workspace directory path reported to agents running in a sandbox to reflect the path inside the Docker container, ensuring tools execute in the correct location.

2 duplicates bugfix area: agents · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#3967 fix(sandbox): correct workspace prompt path
@sweepies
9.5/10
✓ Consensus
#2
#3967 fix(sandbox): correct workspace prompt path
@sweepies
9.5/10
✓ Consensus

Fixes a packaging issue on Windows by correcting the bin path in package.json and adds support for OpenAI vision models by extracting image data from data URIs in the OpenAI-compatible API and converting them to the internal agent command format.

2 duplicates bugfix area: gateway · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#4534 fix: packaging and OpenAI vision format conversion
@SalimBinYousuf1
6.5/10
✓ Consensus
#2
#4534 fix: packaging and OpenAI vision format conversion
@SalimBinYousuf1
6.5/10
✓ Consensus

Prevents the compaction safeguard extension from discarding conversation history in embedded mode by returning undefined when ctx.model or apiKey is unavailable, allowing the built-in compaction logic to handle summarization.

2 duplicates bugfix area: agents · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#4223 fix: compaction safeguard falls through when ctx.model is unavailable
@hanxiao
8.3/10
✓ Consensus
#2
#4223 fix: compaction safeguard falls through when ctx.model is unavailable
@hanxiao
8.3/10
✓ Consensus

Fixes a permission denied error in Docker containers by ensuring the 'node' user owns all files copied into the image.

2 duplicates bugfix area: Docker · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#11333 fix(docker): align host directory ownership with container user
@liuxiaopai-ai
8.1/10
✓ Consensus
#2
#5458 fix: set correct file ownership in Dockerfile (#5450)
@hakyonglee
7.7/10
⚠ Human Review

Prevents the Slack integration from attempting to process HTML login pages (returned due to authentication failures or expired URLs) as media files, improving error handling and visibility by logging a warning and skipping the file.

2 duplicates bugfix area: Slack media downloads · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#14847 fix(slack): preserve auth across Slack-hosted file redirects
@natashache
9.1/10
✓ Consensus
#2
#4665 fix(slack): reject HTML responses when downloading media
@tumf
9.0/10
✓ Consensus

Adds a BouncyCastle fallback for Ed25519 key generation and signing on Android devices where the system provider fails, and introduces a UI setting for users to input a gateway token for authentication.

2 duplicates feature area: Android app · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#5867 Android: Add BouncyCastle Ed25519 fallback and gateway token UI
@brandonpollack23
7.5/10
✓ Consensus
#2
#10597 fix(android): add BouncyCastle fallback for Ed25519 on Samsung devices
@bingluo-coder
6.4/10
⚠ Human Review

Changes the default browser profile to 'openclaw' when no profile is specified, preventing errors for users without the Chrome extension.

2 duplicates bugfix area: browser · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#14944 fix(browser): prefer openclaw profile in headless/noSandbox environments
@BenediktSchackenberg
9.1/10
✓ Consensus
#2
#6193 fix(browser): default to openclaw profile instead of chrome extension relay
@mikezaoldyeck
7.3/10
✓ Consensus

Fixes a potential hang in the embedded Pi runner teardown process by making the compaction wait abortable, ensuring that the teardown path proceeds even if compaction events are not received.

2 duplicates bugfix area: agents · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#13347 fix: wrap waitForCompactionRetry() in abortable() to prevent lane deadlock on timeout
@smartleos
9.2/10
✓ Consensus
#2
#5467 Fix: make embedded compaction wait abortable
@yoyooyooo
9.1/10
✓ Consensus

Fixes a bug where the session-memory hook reads from an empty current session file after a /new or /reset command, leading to loss of conversation history, by adding a fallback mechanism to read from the most recent .jsonl.reset.* file if the current session file is empty or too small.

2 duplicates bugfix area: memory/storage · confidence: 90.0%
Rank
Pull Request
Quality
Review
⭐#1
#18253 fix: session-memory hook reads from reset files when current file is …
@princeh23
7.7/10
✓ Consensus
#2
#18103 fix: session-memory hook reads reset file after /new or /reset
@MisterGuy420
6.7/10
✓ Consensus

Adds 'agent:turn_start' and 'agent:turn_end' lifecycle events to provide real-time agent activity signals for integrations like status dashboards.

2 duplicates feature area: hooks · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#6630 feat(hooks): add agent:turn_start and agent:turn_end lifecycle events
@drdigital13
6.4/10
✓ Consensus
#2
#6630 feat(hooks): add agent:turn_start and agent:turn_end lifecycle events
@drdigital13
6.4/10
✓ Consensus

Fixes a bug where cron jobs with `deliver: true` would silently fail to deliver the original message when the agent response was filtered as heartbeat-only, by substituting the original message as the delivery payload in such cases.

2 duplicates bugfix area: cron · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#6522 fix(cron): deliver original message when agent response is heartbeat-only
@sidmohan0
9.2/10
✓ Consensus
#2
#6522 fix(cron): deliver original message when agent response is heartbeat-only
@sidmohan0
9.2/10
✓ Consensus

Fixes a bug where messages sent via the Matrix channel without specifying an accountId were being sent from the wrong Matrix account due to incorrect account resolution.

2 duplicates bugfix area: matrix · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#6517 fix(matrix): pass accountId through outbound chain to resolveMatrixClient
@saxyguy81
8.5/10
✓ Consensus
#2
#6517 fix(matrix): pass accountId through outbound chain to resolveMatrixClient
@saxyguy81
8.5/10
✓ Consensus

Adds a new interactive HTML visualization for line balancing of a Double End M12 Cable Assembly, including multiple balancing algorithms, animated station merging, and performance metrics.

2 duplicates feature area: UI · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#7030 feat: add line balancing animation for Double End M12 Cable Assembly
@ceasarcapuno
6.8/10
✓ Consensus
#2
#7030 feat: add line balancing animation for Double End M12 Cable Assembly
@ceasarcapuno
6.8/10
✓ Consensus

Fixes a bug where compaction summarization fails in 'safeguard' mode due to missing model context, causing fallback to static summaries by passing the model through the runtime registry.

2 duplicates bugfix area: compaction-safeguard · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#6800 fix: pass model to compaction-safeguard via runtime for compact.js workflow
@earlook99
8.6/10
✓ Consensus
#2
#6800 fix: pass model to compaction-safeguard via runtime for compact.js workflow
@earlook99
8.6/10
✓ Consensus

Adds a configurable placeholder message to the Telegram channel while the agent is processing a request, updating it with tool usage information and deleting it upon completion.

2 duplicates feature area: Telegram · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#7046 feat(telegram): add placeholder message while processing
@shanemort1982
7.5/10
✓ Consensus
#2
#7046 feat(telegram): add placeholder message while processing
@shanemort1982
7.5/10
✓ Consensus

Updates the Hetzner VPS installation guide with improved instructions, including optional hcloud CLI provisioning, expanded Docker Compose examples, and a new section on configuring the gateway with first-run commands and validation/access flows.

2 duplicates docs area: installation guide · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#6994 Update Docs/hetzner
@0xE282B0
7.2/10
✓ Consensus
#2
#6994 Update Docs/hetzner
@0xE282B0
7.2/10
✓ Consensus

Fixes a bug where the TTS tool was not picking up runtime config changes for voice selection, requiring a gateway restart to apply changes.

2 duplicates bugfix area: TTS agent · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#6677 fix(tts): always load fresh config for voice selection
@Jinqiao
8.5/10
✓ Consensus
#2
#6677 fix(tts): always load fresh config for voice selection
@Jinqiao
8.5/10
✓ Consensus

Adds a persistent contact storage mechanism for the WhatsApp tool by creating a CONTACTS.md file in the workspace to store contact information, allowing the agent to remember previously used contacts across sessions.

2 duplicates feature area: agents · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#6965 feat: add CONTACTS.md for persistent WhatsApp contact storage
@negativenagesh
7.7/10
⚠ Human Review
#2
#6965 feat: add CONTACTS.md for persistent WhatsApp contact storage
@negativenagesh
7.7/10
⚠ Human Review

Adds IO Intelligence as a new inference provider in OpenClaw, allowing users to integrate IO Intelligence models with OpenClaw

2 duplicates feature area: inference providers · confidence: 92.0%
Rank
Pull Request
Quality
Review
⭐#1
#7051 Add io-intelligence model inference provider
@rajagurunath
6.8/10
✓ Consensus
#2
#7051 Add io-intelligence model inference provider
@rajagurunath
6.8/10
✓ Consensus

Updates the browser configuration examples in the documentation to use standard JSON format with quoted keys for better compatibility.

2 duplicates docs area: browser · confidence: 96.0%
Rank
Pull Request
Quality
Review
⭐#1
#6751 docs(browser): update JSON configuration format in documentation
@saltapp
8.2/10
⚠ Human Review
#2
#6751 docs(browser): update JSON configuration format in documentation
@saltapp
8.2/10
⚠ Human Review

Adds a `supportsStrictMode` option to the model configuration to allow disabling the `strict: true` parameter in tool/function definitions for OpenAI-compatible endpoints that do not support it.

2 duplicates feature area: config · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#6683 feat(config): add supportsStrictMode compat option for model definitions
@long-pham
9.2/10
✓ Consensus
#2
#6683 feat(config): add supportsStrictMode compat option for model definitions
@long-pham
9.2/10
✓ Consensus

Triggers internal hooks when a new session is created via the `sessions.reset` RPC, mirroring the behavior of the `/new` command when issued through a channel, to ensure features like session memory and command logging function correctly in TUI and webchat.

2 duplicates bugfix area: gateway · confidence: 93.0%
Rank
Pull Request
Quality
Review
⭐#1
#6853 fix: fire internal hooks on sessions.reset RPC (TUI/webchat /new)
@hamiltonchua
8.5/10
✓ Consensus
#2
#6853 fix: fire internal hooks on sessions.reset RPC (TUI/webchat /new)
@hamiltonchua
8.5/10
✓ Consensus

Adds a cleanup mechanism to remove orphaned temporary files created during cron store saves on application startup, preventing potential interference from incomplete writes.

2 duplicates bugfix area: cron store · confidence: 96.0%
Rank
Pull Request
Quality
Review
⭐#1
#6827 fix: cron scheduler cleanup orphaned .tmp files on startup
@fatelei
7.6/10
✓ Consensus
#2
#6827 fix: cron scheduler cleanup orphaned .tmp files on startup
@fatelei
7.6/10
✓ Consensus

Improves the user experience of the `/queue` and `/subagents` chat commands by reformatting their output to be more readable and informative.

2 duplicates feature area: auto-reply command handling · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#6690 UX: clearer /queue and /subagents output
@kamb5686
7.9/10
✓ Consensus
#2
#6690 UX: clearer /queue and /subagents output
@kamb5686
7.9/10
✓ Consensus

Fixes multiple path traversal vulnerabilities in archive extraction and transcript handling to prevent arbitrary file read/write outside intended directories.

2 duplicates security area: gateway · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#6729 fix(security): prevent path traversal in archive extraction (CWE-22)
@unisone
8.9/10
✓ Consensus
#2
#6729 fix(security): prevent path traversal in archive extraction (CWE-22)
@unisone
8.9/10
✓ Consensus

Addresses a crash on Android/Termux by wrapping calls to `os.networkInterfaces()` in try/catch blocks to gracefully handle the restricted `uv_interface_addresses` system call.

2 duplicates bugfix area: networking · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#7060 fix: handle uv_interface_addresses failure on Android/Termux
@kjoh94
8.3/10
✓ Consensus
#2
#7060 fix: handle uv_interface_addresses failure on Android/Termux
@kjoh94
8.3/10
✓ Consensus

Removes the workspace protocol dependency on openclaw from the feishu extension's package.json to resolve an npm install error related to unsupported workspace protocols during plugin installation.

2 duplicates bugfix area: integrations · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#11454 fix(plugins): remove workspace:* from extension dependencies
@AnonO6
8.6/10
⚠ Human Review
#2
#18209 fix(feishu): remove workspace protocol from devDependencies to fix in…
@zywj
7.8/10
✓ Consensus

Fixes a bug where messages sent via `sessions_send` were incorrectly routed to the webchat channel due to a hardcoded channel value, and introduces support for direct session key formats to correctly route messages to the intended channel.

2 duplicates bugfix area: agents · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#6850 fix: support direct channel:account:peer format in session key extraction
@toboto
8.6/10
✓ Consensus
#2
#6850 fix: support direct channel:account:peer format in session key extraction
@toboto
8.6/10
✓ Consensus

Modifies plugin installation to use the 'id' field from the plugin manifest file for the installation directory name, falling back to the npm package name if the manifest or ID is missing.

2 duplicates bugfix area: plugins · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#7090 fix: plugin install uses manifest ID for folder name (#2796)
@dial481
8.8/10
✓ Consensus
#2
#7090 fix: plugin install uses manifest ID for folder name (#2796)
@dial481
8.8/10
✓ Consensus

Adds a new 'camb-ai' extension to OpenClaw, providing agent tools and CLI commands for text-to-speech, speech-to-text, translation, voice cloning, and sound generation using the Camb AI platform.

2 duplicates feature area: agents · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#7088 feat: add Camb AI extension
@neilruaro-camb
7.4/10
✓ Consensus
#2
#7088 feat: add Camb AI extension
@neilruaro-camb
7.4/10
✓ Consensus

Strips malformed tool_use blocks from assistant messages to prevent permanent session corruption caused by interrupted tool calls, ensuring subsequent API requests do not fail due to unexpected or missing tool_use_id errors.

2 duplicates bugfix area: session transcript repair · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#16966 fix: strip tool_use blocks from aborted/errored assistant messages
@StressTestor
9.3/10
✓ Consensus
#2
#6687 fix(session-repair): strip malformed tool_use blocks to prevent permanent session corruption
@NSEvent
9.0/10
✓ Consensus

Adds regression tests to verify that the `sessions_spawn` tool correctly applies explicit model overrides, even when an `agentId` is provided, and that explicit models take precedence over global subagent model defaults.

2 duplicates tests area: gateway · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#6875 test: add coverage for sessions_spawn model + agentId (#6817)
@whoknowsmann
9.0/10
✓ Consensus
#2
#6875 test: add coverage for sessions_spawn model + agentId (#6817)
@whoknowsmann
9.0/10
✓ Consensus

Removes the unnecessary and failing 'restore control-ui' step in the update runner, which attempts to restore a gitignored directory, causing update failures despite successful builds.

2 duplicates bugfix area: update-runner · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#6786 [Prompt Request] fix: remove dead restore step for gitignored dist/control-ui/
@therealZpoint-bot
7.6/10
✓ Consensus
#2
#6786 [Prompt Request] fix: remove dead restore step for gitignored dist/control-ui/
@therealZpoint-bot
7.6/10
✓ Consensus

Clarify in the documentation and system prompt that the `/elevated on` command is an alias for `/elevated ask` to reduce user confusion.

2 duplicates docs area: agents · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#6857 docs: clarify that /elevated on is an alias for ask
@whoknowsmann
9.4/10
✓ Consensus
#2
#6857 docs: clarify that /elevated on is an alias for ask
@whoknowsmann
9.4/10
✓ Consensus

Fixes an issue where node pairing requests created via WebSocket connection were not being properly handled by the `node.pair.*` API handlers, leading to an inability to approve or reject pairing requests through the CLI or API.

2 duplicates bugfix area: gateway · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#6846 fix: bridge node.pair.* tools to device pairing store
@cortexuvula
8.4/10
✓ Consensus
#2
#6846 fix: bridge node.pair.* tools to device pairing store
@cortexuvula
8.4/10
✓ Consensus

Adds a new environment variable to configure volume mount options in docker-compose, primarily to support rootless Podman and SELinux environments by allowing users to specify mount flags like `:U` or `:Z`.

2 duplicates feature area: docker · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#7061 Add additional variable to the docker-compose file (default off) to make it work with rootless podman
@aupeachmo
7.4/10
✓ Consensus
#2
#7061 Add additional variable to the docker-compose file (default off) to make it work with rootless podman
@aupeachmo
7.4/10
✓ Consensus

Increase the maximum WebSocket payload size to accommodate larger attachments sent from node clients, specifically addressing the issue of silently dropped payloads when sending base64-encoded images.

2 duplicates bugfix area: gateway · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#6805 fix: increase WebSocket MAX_PAYLOAD_BYTES to 6MB for attachments
@cortexuvula
8.8/10
✓ Consensus
#2
#6805 fix: increase WebSocket MAX_PAYLOAD_BYTES to 6MB for attachments
@cortexuvula
8.8/10
✓ Consensus

Removes MiniMax from the list of reasoning tag providers to fix an issue where MiniMax responses were not displayed in the TUI due to the absence of ``/`` tags.

2 duplicates bugfix area: providers · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#10430 fix: remove Minimax from isReasoningTagProvider
@echoedinvoker
9.1/10
✓ Consensus
#2
#18053 fix(providers): remove MiniMax from reasoning tag providers
@MarcBickel
8.1/10
⚠ Human Review

Updates Twitter URLs to X URLs in the Chinese documentation to maintain consistency with the English documentation.

2 duplicates docs area: docs/zh-CN · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#7171 docs(zh-CN): update Twitter URLs to X for consistency
@RamiNoodle733
8.9/10
⚠ Human Review
#2
#7210 docs: cleanup citation artifacts and update twitter URLs to X
@hongxuWei
8.7/10
⚠ Human Review

Adds a new Text-to-Speech provider, Inworld AI, to the application, allowing users to generate speech from text using Inworld AI's voices and models.

2 duplicates feature area: TTS · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#7258 feat(tts): add Inworld AI TTS provider
@willsinghwilson
7.8/10
⚠ Human Review
#2
#7258 feat(tts): add Inworld AI TTS provider
@willsinghwilson
7.8/10
⚠ Human Review

Updates openclaw to properly update externally installed npm plugins during the update process

2 duplicates bugfix area: cli · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#7106 fix: openclaw update includes external npm-installed plugins
@dial481
8.0/10
⚠ Human Review
#2
#7106 fix: openclaw update includes external npm-installed plugins
@dial481
8.0/10
⚠ Human Review

Adds internationalization (i18n) infrastructure to the project, including support for English and Simplified Chinese, to enable future localization efforts.

2 duplicates feature area: i18n · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#7130 [AI-Assisted] Add i18n infrastructure with Chinese (zh-CN) support
@01luyicheng
8.6/10
✓ Consensus
#2
#7130 [AI-Assisted] Add i18n infrastructure with Chinese (zh-CN) support
@01luyicheng
8.6/10
✓ Consensus

Ensures that the `resolveSoulEvilConfigFromHook` function prioritizes environment variables defined within the `env` block of a hook configuration, preventing accidental access to top-level configuration properties when an `env` block is present.

2 duplicates refactor area: soul-evil hook handler · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#7036 Fix evil soul hooks by enforcing env properties
@richard-chau
8.4/10
✓ Consensus
#2
#7036 Fix evil soul hooks by enforcing env properties
@richard-chau
8.4/10
✓ Consensus

Adds support for the CommonStack AI provider, including onboarding, model scanning, and integration with the CLI, allowing users to access and manage models through the CommonStack platform.

2 duplicates feature area: providers · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#7113 feat(providers): add CommonStack provider support
@flhoildy
7.4/10
✓ Consensus
#2
#7113 feat(providers): add CommonStack provider support
@flhoildy
7.4/10
✓ Consensus

Adds documentation to address the 'stranger problem' in agents, proposing a lighter approach to continuity with a self-check ritual and memory hierarchy, and provides a practical template for agents to use in their workspaces.

2 duplicates docs area: agent architecture and continuity · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#7196 docs: Agent continuity - the 'stranger problem' and lighter approach
@sincere-arjun
7.7/10
✓ Consensus
#2
#7196 docs: Agent continuity - the 'stranger problem' and lighter approach
@sincere-arjun
7.7/10
✓ Consensus

Improves the reliability of agentic loops by adding resilience to transient network errors, including automatic retries and proper classification of network-related failures, preventing silent failures and ensuring continuous operation.

2 duplicates bugfix area: agents · confidence: 95.0%
Rank
Pull Request
Quality
Review
⭐#1
#7229 fix: add network error resilience to agentic loop failover
@ai-fanatic
9.0/10
✓ Consensus
#2
#7229 fix: add network error resilience to agentic loop failover
@ai-fanatic
9.0/10
✓ Consensus

Changes the `openclaw gateway stop` command to use `launchctl kill SIGTERM` instead of `launchctl bootout` so that the LaunchAgent remains loaded and can be restarted without requiring a reinstall.

2 duplicates bugfix area: gateway · confidence: 87.0%
Rank
Pull Request
Quality
Review
⭐#1
#16845 fix(daemon): gateway auto-restart on SIGTERM + agent restart guidelines
@kiminbean
8.8/10
✓ Consensus
#2
#7155 fix(gateway): use kill SIGTERM instead of bootout for stop
@rafaelreis-r
8.5/10
✓ Consensus

Adds a 'gateway:shutdown' internal hook to allow internal hooks to perform cleanup, logging, or other shutdown tasks when the gateway stops, and consolidates plugin lifecycle hook firing to prevent duplicates.

2 duplicates feature area: gateway · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#12582 feat(hooks): emit gateway shutdown lifecycle events
@vincentkoc
9.2/10
✓ Consensus
#2
#15425 Gateway: add gateway:shutdown internal hook for lifecycle cleanup
@a-anand-91119
9.0/10
✓ Consensus

Adds support for detecting mentions in Matrix messages from Element clients by parsing the `formatted_body` field for `matrix.to` links, as Element does not use the `m.mentions` field.

2 duplicates feature area: Matrix integration · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#16941 fix(matrix): detect mentions in formatted_body matrix.to links
@zerone0x
9.5/10
✓ Consensus
#2
#7842 Fix Matrix mention detection for Element client (formatted_body links)
@emadomedher
7.9/10
✓ Consensus

Adds a new hook event type 'message:received' that fires before a message is processed by the agent, enabling custom logic on incoming messages and context injection

2 duplicates feature area: hooks · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#11597 feat(hooks): implement message:received hook
@gnufoo
8.8/10
✓ Consensus
#2
#7545 feat(hooks): add message:received hook for pre-turn automation
@wangtian24
8.6/10
✓ Consensus

Integrate Speechify as a new Text-to-Speech provider, including API integration, configuration schema updates, gateway RPC exposure, CLI command adjustments, and documentation.

2 duplicates feature area: tts · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#7965 feat(tts): add Speechify as TTS provider
@chaerla
7.3/10
⚠ Human Review
#2
#7965 feat(tts): add Speechify as TTS provider
@chaerla
7.3/10
⚠ Human Review

Improves OpenClaw's memory management by standardizing on a WM/STM-friendly workspace layout, automatically creating and maintaining STM.md, and allowing memory tools to search/read STM and LTM (when opted in) out of the box, enhancing personalization and continuity without requiring extra configuration.

2 duplicates feature area: memory · confidence: 95.0%
Rank
Pull Request
Quality
Review
⭐#1
#7894 Memory improvements: Give OpenClaw better memory + REM sleep
@bornio
8.1/10
✓ Consensus
#2
#7894 Memory improvements: Give OpenClaw better memory + REM sleep
@bornio
8.1/10
✓ Consensus

Implements a new `before_model_select` plugin hook that allows plugins to intercept and modify the model selection process before it's finalized, enabling intelligent model routing based on prompt content.

2 duplicates feature area: model selection · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8022 feat: implement before_model_select plugin hook
@dead-pool-aka-wilson
8.7/10
✓ Consensus
#2
#8022 feat: implement before_model_select plugin hook
@dead-pool-aka-wilson
8.7/10
✓ Consensus

Adds documentation on how to use Docker Hardened Images (DHI) with OpenClaw to improve security by reducing the attack surface and vulnerabilities.

2 duplicates docs area: docker · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#7920 docs: Add Docker Hardened Images (DHI) guide
@thiago4go
8.4/10
⚠ Human Review
#2
#7920 docs: Add Docker Hardened Images (DHI) guide
@thiago4go
8.4/10
⚠ Human Review

Fixes a bug where Slack channel and user names were incorrectly treated as IDs, preventing directory lookup and causing `channel_not_found` errors in cross-account messaging scenarios.

2 duplicates bugfix area: Slack integration · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8024 fix(slack): resolve channel names via directory for cross-account messaging
@emma-digital-assistant
9.1/10
✓ Consensus
#2
#8024 fix(slack): resolve channel names via directory for cross-account messaging
@emma-digital-assistant
9.1/10
✓ Consensus

Integrate Atlas browser capabilities for web search and fetch, reducing API usage by prioritizing in-browser ChatGPT tasks and falling back to existing providers when Atlas is unavailable, while also adding Atlas profile auto-detection and per-profile executable path support.

2 duplicates feature area: gateway · confidence: 92.0%
Rank
Pull Request
Quality
Review
⭐#1
#7982 Save API Usage: Use Atlas Browser ChatGPT Capabilities
@yaoshengwang
6.3/10
⚠ Human Review
#2
#7982 Save API Usage: Use Atlas Browser ChatGPT Capabilities
@yaoshengwang
6.3/10
⚠ Human Review

Fixes a bug where one-shot cron jobs scheduled during gateway downtime are not executed after the gateway restarts by ensuring the timer is armed immediately for past-due jobs.

2 duplicates bugfix area: cron · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#8034 fix(cron): run past-due one-shot jobs immediately on startup
@FelixFoster
8.4/10
✓ Consensus
#2
#10918 fix(cron): add tolerance for timer precision and skip due jobs in recompute
@Cherwayway
8.1/10
✓ Consensus

Adds a new CLI tool, openclaw-env, to generate hardened Docker Compose sandboxes for running OpenClaw, enforcing least-privilege defaults and supporting restricted network access via an egress proxy with domain allowlisting.

2 duplicates feature area: OpenClaw sandboxing · confidence: 98.0%
Rank
Pull Request
Quality
Review
⭐#1
#8137 feat: openclaw-env hardened sandbox generator (MVP)
@krahimov
7.7/10
✓ Consensus
#2
#8137 feat: openclaw-env hardened sandbox generator (MVP)
@krahimov
7.7/10
✓ Consensus

Persist the webchat message queue to localStorage to prevent message loss on browser refresh, ensuring messages queued while the agent is busy are retained across sessions.

2 duplicates feature area: web-ui · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#8344 fix: persist webchat message queue to localStorage across browser refresh
@vishaltandale00
7.4/10
✓ Consensus
#2
#8344 fix: persist webchat message queue to localStorage across browser refresh
@vishaltandale00
7.4/10
✓ Consensus

Adds the ability to configure context pruning settings on a per-cron-job basis, overriding the global defaults, to reduce unnecessary token costs associated with caching context for simple cron jobs.

2 duplicates feature area: cron jobs and gateway · confidence: 96.0%
Rank
Pull Request
Quality
Review
⭐#1
#8341 feat: add per-job cache control for cron jobs
@vishaltandale00
8.1/10
✓ Consensus
#2
#8341 feat: add per-job cache control for cron jobs
@vishaltandale00
8.1/10
✓ Consensus

Fixes a bug where the browser bridge server was unreachable from inside Docker containers by binding to 127.0.0.1 instead of 0.0.0.0 when running in sandbox mode, and advertising the Docker bridge IP.

2 duplicates bugfix area: browser · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8296 fix(browser): bind sandbox browser bridge to 0.0.0.0 for container access
@gavinbmoore
8.3/10
✓ Consensus
#2
#8296 fix(browser): bind sandbox browser bridge to 0.0.0.0 for container access
@gavinbmoore
8.3/10
✓ Consensus

Enables browser downloads when connecting via Chrome DevTools Protocol (CDP) by calling the `Browser.setDownloadBehavior` method.

2 duplicates bugfix area: browser · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8303 fix(browser): enable downloads via CDP Browser.setDownloadBehavior
@gavinbmoore
8.5/10
✓ Consensus
#2
#8303 fix(browser): enable downloads via CDP Browser.setDownloadBehavior
@gavinbmoore
8.5/10
✓ Consensus

Adds clickable state filter chips to the skills page, allowing users to filter skills based on their state (Ready, Disabled, Missing Dependencies, Blocked).

2 duplicates feature area: UI · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8279 feat(ui): add clickable state filter chips to /skills page
@gildo
7.2/10
✓ Consensus
#2
#8279 feat(ui): add clickable state filter chips to /skills page
@gildo
7.2/10
✓ Consensus

Adds internal hook events before and after session compaction to allow hooks to capture session content before it's summarized.

2 duplicates feature area: agents · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#13861 feat(hooks): add session:compaction hook event
@lailoo
8.5/10
✓ Consensus
#2
#8244 feat(hooks): add session:before_compact and session:after_compact internal hook events
@kephail
7.9/10
✓ Consensus

Adds the ability to configure per-skill thinking level and model selection via the skills.entries configuration, allowing overrides of session defaults when invoking specific skills.

2 duplicates feature area: skills · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8455 feat: add thinking/model config to skills.entries
@tsukhani
7.6/10
✓ Consensus
#2
#8455 feat: add thinking/model config to skills.entries
@tsukhani
7.6/10
✓ Consensus

Filters out 'NO_REPLY' messages from chat history in the webchat interface to prevent them from being displayed to the user.

2 duplicates bugfix area: gateway · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#8334 fix(webchat): Filter NO_REPLY messages from chat history
@vishaltandale00
8.5/10
✓ Consensus
#2
#8334 fix(webchat): Filter NO_REPLY messages from chat history
@vishaltandale00
8.5/10
✓ Consensus

Implements a per-tool-call timeout to prevent agent hangs caused by indefinitely running tool calls, returning an error result to the model instead of hanging, and fixes a memory leak related to abort listeners.

2 duplicates feature area: agents · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#8332 fix: add per-tool-call timeout to prevent agent hangs (v2 - fixes memory leak)
@vishaltandale00
8.9/10
✓ Consensus
#2
#8332 fix: add per-tool-call timeout to prevent agent hangs (v2 - fixes memory leak)
@vishaltandale00
8.9/10
✓ Consensus

Adds a configuration option to customize the user's display name in the webchat interface, allowing users to replace the default "You" label with a custom name.

2 duplicates feature area: webchat · confidence: 91.0%
Rank
Pull Request
Quality
Review
⭐#1
#8318 feat(webchat): Add configurable user display name
@vishaltandale00
8.7/10
✓ Consensus
#2
#8318 feat(webchat): Add configurable user display name
@vishaltandale00
8.7/10
✓ Consensus

Adds a 'none' option to the postToMainMode setting for isolated cron jobs to prevent duplicate messages by skipping posting to the main session.

2 duplicates feature area: cron · confidence: 98.0%
Rank
Pull Request
Quality
Review
⭐#1
#8315 fix(cron): Add 'none' option to postToMainMode to prevent duplicate messages
@vishaltandale00
8.8/10
✓ Consensus
#2
#8315 fix(cron): Add 'none' option to postToMainMode to prevent duplicate messages
@vishaltandale00
8.8/10
✓ Consensus

Adds optional auto-compaction support for spawned subagent sessions to prevent context limits and allow long-running tasks to continue

2 duplicates feature area: agents · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#8313 feat: auto-compaction support for spawned subagent sessions
@vishaltandale00
7.4/10
✓ Consensus
#2
#8313 feat: auto-compaction support for spawned subagent sessions
@vishaltandale00
7.4/10
✓ Consensus

Adds the ability to configure whether bot messages are allowed to trigger replies in Telegram groups, providing feature parity with Discord and Slack.

2 duplicates feature area: Telegram · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#8310 feat(telegram): Add allowBots support for groups (parity with Discord/Slack)
@vishaltandale00
8.6/10
✓ Consensus
#2
#8310 feat(telegram): Add allowBots support for groups (parity with Discord/Slack)
@vishaltandale00
8.6/10
✓ Consensus

Adds an 'emb_' prefix to the custom_id field in batch embedding requests to comply with OpenAI's API pattern requirements and prevent HTTP 400 errors.

2 duplicates bugfix area: memory search · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8309 fix: add emb_ prefix to batch embedding custom_id for OpenAI compliance
@vishaltandale00
8.5/10
⚠ Human Review
#2
#8309 fix: add emb_ prefix to batch embedding custom_id for OpenAI compliance
@vishaltandale00
8.5/10
⚠ Human Review

Adds support for SambaNova as a new model provider with an OpenAI-compatible API, including onboarding, authentication, and configuration.

2 duplicates feature area: gateway · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8216 Feat: Add sambanova provider
@luisfucros
5.5/10
✓ Consensus
#2
#8216 Feat: Add sambanova provider
@luisfucros
5.5/10
✓ Consensus

Fixes outbound voice calls failing due to the Twilio webhook returning empty TwiML for calls that are not yet in 'in-progress' status, by ensuring valid TwiML (streaming or pause) is always returned.

2 duplicates bugfix area: voice-call · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8297 fix(voice-call): prevent empty TwiML for non-in-progress outbound calls
@vishaltandale00
8.0/10
⚠ Human Review
#2
#8297 fix(voice-call): prevent empty TwiML for non-in-progress outbound calls
@vishaltandale00
8.0/10
⚠ Human Review

Prevents file descriptor exhaustion by adding Python virtual environment and cache directories to the skills file watcher's ignore list.

2 duplicates bugfix area: agents · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8291 Fix: Add Python virtual environment ignore patterns to skills watcher
@vishaltandale00
8.4/10
⚠ Human Review
#2
#8291 Fix: Add Python virtual environment ignore patterns to skills watcher
@vishaltandale00
8.4/10
⚠ Human Review

Adds support for configuring the base URL of the Brave Search provider, allowing users to use local proxies, audit logs, or corporate network policies.

2 duplicates feature area: web-search · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#18167 feat(web-search): add baseUrl support for Brave Search provider
@jkoprax
9.2/10
✓ Consensus
#2
#13843 feat(web-search): allow overriding Brave Search base URL
@strelov1
8.1/10
✓ Consensus

Fixes a bug where images pasted into webchat disappeared after sending because they were being sent with the full data URL instead of just the base64 content.

2 duplicates bugfix area: webchat · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#8284 Fix: Webchat images now persist after sending
@vishaltandale00
7.5/10
✓ Consensus
#2
#8284 Fix: Webchat images now persist after sending
@vishaltandale00
7.5/10
✓ Consensus

Enables file downloads in the OpenClaw Chrome profile by calling the CDP Browser.setDownloadBehavior command after browser launch, configuring the download path to the user's default Downloads directory.

2 duplicates feature area: browser · confidence: 96.0%
Rank
Pull Request
Quality
Review
⭐#1
#8282 Fix: Enable browser downloads via CDP Browser.setDownloadBehavior
@vishaltandale00
7.0/10
✓ Consensus
#2
#8282 Fix: Enable browser downloads via CDP Browser.setDownloadBehavior
@vishaltandale00
7.0/10
✓ Consensus

Removes the redundant conversation transcript from the extraSystemPrompt in the voice response generator to avoid duplicated context, reduce token usage, and improve latency.

2 duplicates performance area: voice-call · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8251 fix(voice-call): remove redundant transcript from extraSystemPrompt
@geodeterra
8.4/10
✓ Consensus
#2
#8251 fix(voice-call): remove redundant transcript from extraSystemPrompt
@geodeterra
8.4/10
✓ Consensus

Adds support for `payload.fallbacks` in isolated cron jobs, allowing users to specify a list of fallback models to use if the primary model fails, optimizing token costs and reducing latency.

2 duplicates feature area: cron · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8274 feat(cron): add payload.fallbacks support for isolated jobs
@marcelomar21
8.8/10
✓ Consensus
#2
#8274 feat(cron): add payload.fallbacks support for isolated jobs
@marcelomar21
8.8/10
✓ Consensus

Fixes Telegram long-polling failure on macOS with Node.js 22.22.0 by skipping the autoSelectFamily workaround that causes fetch() calls to timeout.

2 duplicates bugfix area: Telegram network config · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#8194 fix(telegram): skip autoSelectFamily workaround on macOS
@xandorklein
9.3/10
✓ Consensus
#2
#8194 fix(telegram): skip autoSelectFamily workaround on macOS
@xandorklein
9.3/10
✓ Consensus

Adds support for Nebius Token Factory as an OpenAI-compatible provider, including onboarding flows, documentation, and automatic model discovery.

2 duplicates feature area: providers · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#8232 Nebius token factory Provider support
@KiranChilledOut
7.3/10
⚠ Human Review
#2
#8232 Nebius token factory Provider support
@KiranChilledOut
7.3/10
⚠ Human Review

Add a real-time Model Requests panel to the Control UI for monitoring model API calls with success/failure status, timing, token usage, and error details

2 duplicates feature area: gateway · confidence: 98.0%
Rank
Pull Request
Quality
Review
⭐#1
#8522 feat(control-ui): Add Model Requests panel for real-time API monitoring
@GiantAxeWhy
7.1/10
⚠ Human Review
#2
#8522 feat(control-ui): Add Model Requests panel for real-time API monitoring
@GiantAxeWhy
7.1/10
⚠ Human Review

Persist session token totals by falling back to transcript usage parsing or a bounded token estimate when live usage metadata is missing, and improve transcript lookup reliability by passing session identifiers.

2 duplicates feature area: TUI · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8477 TUI: persist session token totals when usage metadata is missing
@LarHope
8.1/10
✓ Consensus
#2
#8477 TUI: persist session token totals when usage metadata is missing
@LarHope
8.1/10
✓ Consensus

Detects early Chromium process exits during startup to prevent the Gateway from hanging and provides a more informative error message.

2 duplicates bugfix area: browser · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#8614 fix(browser): detect early chromium exit to prevent startup hang
@Wren-OC
7.5/10
✓ Consensus
#2
#8614 fix(browser): detect early chromium exit to prevent startup hang
@Wren-OC
7.5/10
✓ Consensus

Enhance Slack interaction handling by attributing confirmation messages to the acting user and exposing structured select entity arrays (users, channels, conversations) in the payload normalization.

2 duplicates feature area: Slack integration · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#18467 Slack: expand advanced modal controls payloads and confirms
@Solvely-Colin
7.5/10
✓ Consensus
#2
#18474 Slack: attribute interaction confirmations and structured selects
@Solvely-Colin
7.3/10
⚠ Human Review

Fixes a bug where cron jobs get stuck in the running state indefinitely after a timeout or crash by adding a timeout to the executeJob function, scheduling maintenance ticks, and reducing the stuck run time.

2 duplicates bugfix area: cron · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#16880 fix(cron): respect per-job timeoutSeconds in executeJob path (#16841)
@echoVic
9.0/10
✓ Consensus
#2
#18144 fix(cron): clear stuck runningAtMs after timeout and add maintenance ticks
@taw0002
8.3/10
✓ Consensus

Adds a CONTRIBUTING.md file to the documentation to provide guidelines for contributing to the OpenClaw documentation, including instructions on building a local preview, required frontmatter, style and writing tips, and the pull request process.

2 duplicates docs area: docs · confidence: 98.0%
Rank
Pull Request
Quality
Review
⭐#1
#8509 docs: add docs CONTRIBUTING.md
@ethanpalm
7.5/10
✓ Consensus
#2
#8509 docs: add docs CONTRIBUTING.md
@ethanpalm
7.5/10
✓ Consensus

Improve the error message for launchctl bootstrap failures related to GUI domain issues, providing more helpful guidance to the user.

2 duplicates bugfix area: gateway · confidence: 90.0%
Rank
Pull Request
Quality
Review
⭐#1
#13795 Gateway: MacOS clarify launchctl GUI domain bootstrap failure
@vincentkoc
9.3/10
✓ Consensus
#2
#8642 fix: improve launchctl bootstrap error messages for GUI domain issues
@dbottme
9.0/10
✓ Consensus

Implement per-model cooldown tracking for rate limit errors, allowing other models from the same provider to be used even if one model is rate-limited.

2 duplicates feature area: auth · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#8359 feat: implement per-model cooldown tracking for rate limit errors
@silhuzz
8.1/10
⚠ Human Review
#2
#16797 fix(auth-profiles): implement per-model rate limit cooldown tracking
@mulhamna
8.0/10
⚠ Human Review

Adds a comprehensive Cisco Webex Teams channel plugin for OpenClaw, enabling bidirectional messaging with Webex Teams through the bot API

2 duplicates feature area: gateway · confidence: 93.0%
Rank
Pull Request
Quality
Review
⭐#1
#9199 feat: Add Cisco Webex Teams channel plugin
@chrharri
8.5/10
✓ Consensus
#2
#9199 feat: Add Cisco Webex Teams channel plugin
@chrharri
8.5/10
✓ Consensus

Adds support for reading output files generated by the parakeet-mlx CLI tool within the media understanding pipeline.

2 duplicates feature area: media-understanding · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#9177 feat(media): add parakeet-mlx CLI output support
@mac-110
8.1/10
⚠ Human Review
#2
#9177 feat(media): add parakeet-mlx CLI output support
@mac-110
8.1/10
⚠ Human Review

Fixes a bug where new agent messages were not rendering in the Control UI after a successful chat.history WebSocket response due to missing properties in the GatewayHost type definition.

2 duplicates bugfix area: UI · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#9195 Fix: Control UI fails to render new messages after chat.history WebSocket response
@vishaltandale00
7.6/10
✓ Consensus
#2
#9195 Fix: Control UI fails to render new messages after chat.history WebSocket response
@vishaltandale00
7.6/10
✓ Consensus

Adds a link and embedded video of the freeCodeCamp OpenClaw tutorial to the documentation showcase page.

2 duplicates docs area: docs · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#9151 Docs: add freeCodeCamp OpenClaw full tutorial to showcase
@kiankyars
8.6/10
⚠ Human Review
#2
#9151 Docs: add freeCodeCamp OpenClaw full tutorial to showcase
@kiankyars
8.6/10
⚠ Human Review

Configures the concurrency of the nested command lane in the gateway to prevent timeouts during `sessions_send` operations by increasing the number of concurrent tasks it can handle.

2 duplicates bugfix area: gateway · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#9266 fix(gateway): configure nested lane concurrency to prevent sessions_send timeout
@100menotu001
8.4/10
✓ Consensus
#2
#9266 fix(gateway): configure nested lane concurrency to prevent sessions_send timeout
@100menotu001
8.4/10
✓ Consensus

Changes the default installation source for four channel plugins from npm to local to prevent 404 errors during setup due to the packages not being published to the npm registry.

2 duplicates bugfix area: onboarding and plugin installation · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#9196 Fix: Use local plugins for unpublished npm packages
@vishaltandale00
8.8/10
✓ Consensus
#2
#9196 Fix: Use local plugins for unpublished npm packages
@vishaltandale00
8.8/10
✓ Consensus

Strips dangerous environment variables like NODE_OPTIONS, LD_PRELOAD, and DYLD_INSERT_LIBRARIES from the base environment when executing commands on the host (gateway/node) via the exec tool to prevent unintended inheritance and potential security vulnerabilities.

2 duplicates security area: agents · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#9200 Fix: Strip dangerous env vars from baseEnv in host execution
@vishaltandale00
8.3/10
✓ Consensus
#2
#9200 Fix: Strip dangerous env vars from baseEnv in host execution
@vishaltandale00
8.3/10
✓ Consensus

Prevents uncaught EPIPE exceptions during rapid systemd service restarts by safely writing to stdout, checking if the stream is writable and handling potential write errors.

2 duplicates bugfix area: gateway · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#9214 Fix: EPIPE exception in systemd service operations
@vishaltandale00
8.1/10
⚠ Human Review
#2
#9214 Fix: EPIPE exception in systemd service operations
@vishaltandale00
8.1/10
⚠ Human Review

Adds a contribution note summarizing observed Mattermost WebSocket disconnect symptoms and troubleshooting recommendations for Issue #9211.

2 duplicates docs area: Mattermost integration · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#9319 [Swarm] [Mattermost] WebSocket disconnects with "client si
@swarmagents
6.7/10
⚠ Human Review
#2
#9319 [Swarm] [Mattermost] WebSocket disconnects with "client si
@swarmagents
6.7/10
⚠ Human Review

Adds a markdown file containing hypotheses and debugging suggestions for a connection error issue on Intel-based Macs.

2 duplicates docs area: Swarm · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#9317 [Swarm] [Bug]: Connection error on Intel MacBook Pro persi
@swarmagents
6.2/10
⚠ Human Review
#2
#9317 [Swarm] [Bug]: Connection error on Intel MacBook Pro persi
@swarmagents
6.2/10
⚠ Human Review

Adds a new skill to parse documents (images and PDFs) using the PaddleOCR API, providing structured output in JSON format.

2 duplicates feature area: skills · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#9338 feat: add paddleocr doc parsing skill
@Bobholamovic
6.6/10
✓ Consensus
#2
#9338 feat: add paddleocr doc parsing skill
@Bobholamovic
6.6/10
✓ Consensus

Fixes plugin installation failure on Windows by adding `shell: true` option when spawning `.cmd` files, validating command arguments, and filtering out null/undefined arguments.

2 duplicates bugfix area: process execution · confidence: 96.0%
Rank
Pull Request
Quality
Review
⭐#1
#9250 Fix: Add shell:true for Windows .cmd files to prevent spawn EINVAL error
@vishaltandale00
8.8/10
✓ Consensus
#2
#9250 Fix: Add shell:true for Windows .cmd files to prevent spawn EINVAL error
@vishaltandale00
8.8/10
✓ Consensus

Implements resumable file uploads to Microsoft Teams for files larger than 4MB to improve reliability and prevent failures during large file transfers.

2 duplicates feature area: msteams · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#9217 feat(msteams): implement resumable upload sessions for files >4MB
@hubertusgbecker
8.8/10
✓ Consensus
#2
#9217 feat(msteams): implement resumable upload sessions for files >4MB
@hubertusgbecker
8.8/10
✓ Consensus

Adds error handling around message processing in the Mattermost monitor to prevent crashes caused by malformed messages, logging errors and skipping the problematic messages to maintain monitor stability.

2 duplicates bugfix area: mattermost · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#9152 fix(mattermost): add error handling to prevent monitor crashes
@hubertusgbecker
7.2/10
✓ Consensus
#2
#9152 fix(mattermost): add error handling to prevent monitor crashes
@hubertusgbecker
7.2/10
✓ Consensus

Fixes a bug where the `/whoami` command in Feishu group chats displays the sender's ID instead of the chat ID, leading to session context confusion.

2 duplicates bugfix area: auto-reply · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#9253 Fix: Feishu chat ID mismatch causing session context confusion
@vishaltandale00
8.2/10
✓ Consensus
#2
#9253 Fix: Feishu chat ID mismatch causing session context confusion
@vishaltandale00
8.2/10
✓ Consensus

Fixes a bug where the `openclaw gateway install` command on macOS ignores the node version managed by fnm/nvm and hardcodes the Homebrew node path in the launchd plist.

2 duplicates bugfix area: gateway · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#18112 fix(daemon): gateway install on macOS ignores fnm/nvm node (#18090)
@yinghaosang
9.1/10
✓ Consensus
#2
#15475 fix(update): Handle Homebrew+Node Cellar path mismatch
@brandonwise
8.3/10
✓ Consensus

Prevents the webchat UI from crashing when a tool returns a large or circular object by sanitizing the tool's arguments before rendering and adding a try-catch block around the message building process.

2 duplicates bugfix area: webchat UI · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#9248 Fix: Webchat UI goes grey/unresponsive after Slack message tool calls
@vishaltandale00
8.5/10
✓ Consensus
#2
#9248 Fix: Webchat UI goes grey/unresponsive after Slack message tool calls
@vishaltandale00
8.5/10
✓ Consensus

Fixes a bug where WhatsApp QR codes were not rendering in the chat interface by allowing `` tags and `src` and `alt` attributes in the markdown sanitizer, and restricts image sources to data URLs for security.

2 duplicates bugfix area: UI · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#9237 Fix: WhatsApp QR code not rendering in chat
@vishaltandale00
8.3/10
⚠ Human Review
#2
#9237 Fix: WhatsApp QR code not rendering in chat
@vishaltandale00
8.3/10
⚠ Human Review

Fixes a bug in the TUI where API responses were silently dropped when events arrived out of order or were duplicated after a runId was finalized, by ensuring that 'final' events are always processed even if the runId is in finalizedRuns.

2 duplicates bugfix area: TUI event handling · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#9750 fix(tui): process final event even when runId is in finalizedRuns (#9203)
@lailoo
8.5/10
✓ Consensus
#2
#9220 Fix: TUI drops API responses silently when runID already finalized
@vishaltandale00
8.4/10
✓ Consensus

Fixes a bug where heartbeat runs were incorrectly using the session's model override instead of the configured heartbeat model.

2 duplicates bugfix area: auto-reply · confidence: 90.0%
Rank
Pull Request
Quality
Review
⭐#1
#13016 fix(heartbeat): ignore session modelOverride when heartbeat.model is configured
@asklee-klawd
9.3/10
✓ Consensus
#2
#9429 fix: skip session model override for heartbeat runs
@dbottme
8.5/10
✓ Consensus

Corrects the fallback path used to locate the bundled Chrome extension directory in the CLI, ensuring it resolves to the correct location within the package's assets directory instead of potentially resolving to a location within node_modules.

2 duplicates bugfix area: CLI · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#10937 fix(browser): correct fallback path for bundled Chrome extension
@dddabtc
8.9/10
✓ Consensus
#2
#9796 fix(cli): correct fallback path for bundled Chrome extension (#9772)
@lailoo
8.5/10
⚠ Human Review

Fixes a memory leak in the gateway process by clearing the `seqByRun` map when an agent run context is cleared, preventing unbounded growth of the map.

2 duplicates bugfix area: agent-events · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#12979 fix(memory): Clean up seqByRun on lifecycle end to prevent memory leak
@trevorgordon981
6.3/10
⚠ Human Review
#2
#10281 fix(infra): clear seqByRun entry when agent run context is cleared
@programming-pupil
6.2/10
⚠ Human Review

Replace insecure string comparison with timing-safe comparison to prevent timing attacks on hook token authentication.

2 duplicates security area: gateway · confidence: 92.0%
Rank
Pull Request
Quality
Review
⭐#1
#14814 fix(gateway): use timing-safe comparison for hook token auth
@Rami8612
9.2/10
✓ Consensus
#2
#10527 security: use timing-safe comparison for hook token authentication
@abdelsfane
8.9/10
✓ Consensus

Adds an `after_tool_call` plugin hook to allow plugins to observe tool execution results, errors, and duration without blocking the tool's execution.

2 duplicates feature area: agents · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#10678 feat(hooks): wire after_tool_call hook into tool execution pipeline
@yassinebkr
9.2/10
✓ Consensus
#2
#13369 fix: wire up after_tool_call plugin hook
@mconcat
9.1/10
✓ Consensus

Updates the coding-agent skill documentation to use the `openclaw system event` command instead of the removed `openclaw gateway wake` command, and clarifies the event delivery semantics.

2 duplicates docs area: skills/coding-agent · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#10665 fix(docs): replace removed gateway wake with system event in coding-agent skill
@Yida-Dev
9.5/10
✓ Consensus
#2
#11009 fix: Correct data path in SKILL.md (coding-agent)
@HenryLoenwind
9.1/10
⚠ Human Review

Adds internationalization (i18n) support to the UI, including English, Chinese (Simplified and Traditional), and Portuguese translations, with a language selector and persistent user preferences.

2 duplicates feature area: UI · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#10657 feat(ui): add i18n support with English, Chinese, and Portuguese
@SalimBinYousuf1
7.4/10
✓ Consensus
#2
#13622 feat(i18n): add complete multi-language support (EN, TR, FR, DE)
@vaur94
7.1/10
✓ Consensus

Fixes a bug where the `session_status` tool displays incorrect thinking/reasoning levels by reading them from the session entry instead of defaulting to agent settings.

2 duplicates bugfix area: agents · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#10970 fix(session-status): pass session-level overrides to buildStatusMessage (#10867)
@lailoo
9.4/10
✓ Consensus
#2
#10998 fix(agents): pass session thinking/reasoning levels to session_status display
@wony2
9.3/10
✓ Consensus

Fixes a TypeError during Matrix media downloads by correctly destructuring the return value of `MatrixClient.downloadContent()` to access the media data buffer and propagates the content type.

2 duplicates bugfix area: matrix · confidence: 91.0%
Rank
Pull Request
Quality
Review
⭐#1
#10721 fix for matrix media: destructure downloadContent return value in media handler
@mklasen
8.4/10
⚠ Human Review
#2
#11902 fix(matrix): handle downloadContent returning {data, contentType} object
@jacoblyles
8.0/10
✓ Consensus

Updates SwiftFormat and SwiftLint configuration files to reflect the renaming of MoltbotProtocol to OpenClawProtocol by adjusting excluded paths.

2 duplicates config area: build · confidence: 87.0%
Rank
Pull Request
Quality
Review
⭐#1
#11935 fix(ci): update SwiftFormat and SwiftLint excludes for OpenClawProtocol rebrand
@leszekszpunar
9.3/10
✓ Consensus
#2
#10744 fix: update stale MoltbotProtocol paths to OpenClawProtocol
@marezgui
9.1/10
✓ Consensus

Fixes a bug where auth profiles were incorrectly rotated due to timeouts during active tool use, leading to crash loops in single-account setups.

2 duplicates bugfix area: agents · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#17559 fix: don't rotate auth profile on timeout during active tool use
@jg-noncelogic
8.7/10
✓ Consensus
#2
#16554 fix(agent): prevent session deadlock on timeout during tool execution
@mverrilli
8.4/10
✓ Consensus

Adds a configuration option to allow users to customize the OpenClaw instance name displayed in the Control UI title, improving identification of multiple instances.

2 duplicates feature area: gateway · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#10991 feat(gateway): add configurable instance name for Control UI title
@Annaxiebot
9.0/10
✓ Consensus
#2
#11528 feat(control-ui): configurable page title with hostname default
@Annaxiebot
7.4/10
✓ Consensus

Fixes a bug where model fallback mechanism fails when fallbacks are configured at the agent level by checking agent-scoped fallbacks and forwarding fallbacksOverride to runEmbeddedPiAgent.

2 duplicates bugfix area: agents · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#13191 pi-embedded: enable failover when per-agent fallbacks are configured
@zesty-clawd
8.9/10
✓ Consensus
#2
#11288 Agent fallback: check agent-scoped fallbacks and forward fallbacksOverride to runEmbeddedPiAgent (#11218)
@lailoo
7.9/10
⚠ Human Review

Preserve the original error information when re-throwing an error during LanceDB loading to comply with the `preserve-caught-error` lint rule.

2 duplicates bugfix area: memory-lancedb · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#11113 fix(memory-lancedb): preserve error cause in LanceDB load failure
@marezgui
8.0/10
✓ Consensus
#2
#11405 fix(extensions): add cause to lancedb load errorfix(extensions): add cause to lancedb load error
@dinakars777
7.9/10
✓ Consensus

Improves the mobile user experience of the chat compose area by restyling the layout for smaller screens, stacking elements vertically and making buttons full-width.

2 duplicates style area: UI · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#11167 style(chat): UI: add mobile layout for chat compose actions
@junyiz
7.6/10
✓ Consensus
#2
#16593 fix: mobile compose row layout
@alewcock
7.3/10
✓ Consensus

Fixes a bug where Telegram update offsets were not scoped to the bot token, causing messages to be skipped after a token change by storing and validating the bot ID in the offset file.

2 duplicates bugfix area: Telegram · confidence: 87.0%
Rank
Pull Request
Quality
Review
⭐#1
#12472 fix(telegram): discard stale update offset after bot token swap
@Yida-Dev
9.3/10
✓ Consensus
#2
#11347 fix: scope Telegram update offset to bot token
@owleyes
9.1/10
✓ Consensus

Fixes a bug where isolated cron sessions were ignoring the `subagents.model` configuration, forcing users to explicitly specify the model in every cron job payload, and adds a test case to verify the fix.

2 duplicates bugfix area: cron · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#11476 Cron: respect subagents.model in isolated cron sessions (#11461)
@lailoo
9.2/10
✓ Consensus
#2
#11474 fix(cron): respect subagents.model in isolated cron sessions
@AnonO6
8.7/10
✓ Consensus

Adds support for running multiple Matrix accounts from a single OpenClaw gateway, enabling per-account message routing and credential management.

2 duplicates feature area: matrix · confidence: 87.0%
Rank
Pull Request
Quality
Review
⭐#1
#14852 feat(matrix): add multi-account support
@tfm-neo-ai
8.6/10
✓ Consensus
#2
#11869 feat: Multi-account Matrix plugin with accountId routing
@jacoblyles
8.1/10
✓ Consensus

Fixes a cron job spin loop that occurs when a job completes within the same second it was scheduled, by ensuring the next run is always computed for the next second and adding a minimum re-fire gap.

2 duplicates bugfix area: cron · confidence: 91.0%
Rank
Pull Request
Quality
Review
⭐#1
#17967 fix(cron): prevent spin loop when job completes within firing second
@Operative-001
9.3/10
✓ Consensus
#2
#18073 fix(cron): prevent spin loop when job completes within scheduled second
@widingmarcus-cyber
9.2/10
✓ Consensus

Fixes an issue where the media stream auth token was being dropped by Twilio because it was passed as a URL query parameter, which Twilio silently strips, by passing the token via a TwiML Parameter element instead.

2 duplicates bugfix area: voice-call · confidence: 93.0%
Rank
Pull Request
Quality
Review
⭐#1
#12471 fix(voice-call): pass stream auth token via TwiML Parameter for Twilio Media Streams
@Yida-Dev
9.1/10
✓ Consensus
#2
#11913 fix(voice-call): pass stream auth token via TwiML Parameter, not URL query
@jason-alvarez-git
8.9/10
✓ Consensus

Fixes a session lock leak in the embedded runner that occurs when `waitForCompactionRetry()` hangs indefinitely after an aborted run, preventing proper cleanup and rendering the agent unresponsive.

2 duplicates bugfix area: embedded runner · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#12227 fix: wrap waitForCompactionRetry with abort signal to prevent session lock leak
@Yida-Dev
9.2/10
✓ Consensus
#2
#15449 fix(embedded-runner): abort compaction wait on timeout
@wangai-studio
8.9/10
✓ Consensus

Apply automated formatting changes using SwiftFormat across the codebase to resolve linting errors and ensure consistent code style.

2 duplicates style area: macOS · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#12121 Fix Swift formatting issues across codebase
@PythonUser42
6.9/10
⚠ Human Review
#2
#12784 chore(macos): run SwiftFormat on sources
@unisone
6.4/10
✓ Consensus

Allows the openclaw-cli Docker container to connect to the openclaw-gateway Docker container by sharing the same network namespace, resolving connection issues when both are running in separate containers.

2 duplicates bugfix area: docker · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#13941 fix: use openclaw-gateway network for cli
@mine260309
9.0/10
✓ Consensus
#2
#12504 fix: allow docker cli container to connect to gateway
@bvanderdrift
7.7/10
✓ Consensus

Fixes a bug where the llm-task extension fails on npm global installs due to an incorrect import path for the bundled version of `runEmbeddedPiAgent`.

2 duplicates bugfix area: llm-task extension · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#12844 fix(llm-task): use correct import path for built/npm installs
@scout-wolfe
9.0/10
✓ Consensus
#2
#13176 fix: resolve llm-task module import for global installs
@striking
9.0/10
✓ Consensus

Add a production-ready WeCom (WeChat Work / 企业微信) Channel plugin for OpenClaw, enabling support for the most important enterprise messaging ecosystem in China

2 duplicates feature area: messaging ecosystem · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#13228 Add WeCom (WeChat Work / 企业微信) Channel plugin for China enterprise ecosystem
@YanHaidao
7.3/10
✓ Consensus
#2
#14009 feat(wecom): add wecom(企业微信) channel extension
@xl370869-art
7.3/10
✓ Consensus

Fixes a bug where the compaction-safeguard extension was not loading in embedded Pi sessions, causing `ctx.model` to be undefined during compaction, and adds a fallback mechanism to provide a transcript-based summary when summarization fails.

2 duplicates bugfix area: agents · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#4572 fix(agents): provide model fallback for compaction safeguard extension
@HirokiKobayashi-R
8.9/10
✓ Consensus
#2
#5005 fix(agents): load compaction-safeguard extension to fix ctx.model undefined
@Diaspar4u
7.3/10
⚠ Human Review

Fixes Grok/xAI Responses parsing to correctly extract the message content from the web_search response when tool call outputs precede the message.

2 duplicates bugfix area: agents · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#13956 fix(web-search): fix grok web search returning empty content
@seraphg
9.0/10
✓ Consensus
#2
#13327 fix(tools): find message output in Grok web_search response
@nezovskii
7.0/10
✓ Consensus

Fixes a bug where the `systemPrompt` field returned by the `before_agent_start` hook was being ignored, preventing plugins from modifying the system prompt.

2 duplicates bugfix area: agents · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#14602 fix(plugins): hook systemPrompt gets collected then thrown away (#14583)
@yinghaosang
9.3/10
✓ Consensus
#2
#13473 fix: honor systemPrompt from before_agent_start hook result
@kira-ariaki
7.9/10
✓ Consensus

Fixes Grok xAI 400 error and empty response content by removing unsupported request parameter, rewriting response parsing, and extracting inline citation annotations

2 duplicates bugfix area: web-search · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#13522 fix(tools): extract Grok web_search citations from nested xAI Responses API output
@lailoo
9.2/10
✓ Consensus
#2
#13560 fix(web-search): fix Grok xAI 400 error and empty response content
@billpku
9.1/10
✓ Consensus

Redact sensitive values in the output of the `openclaw config get` command to prevent exposure of credentials.

2 duplicates security area: CLI · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#13777 security(cli): redact sensitive values in config get output
@SleuthCo
9.1/10
✓ Consensus
#2
#15296 Harden config redaction defaults; add explicit --show-secrets opt-in
@clangky
8.4/10
✓ Consensus

Strips resolved API keys from the models.json file to prevent credential exposure, while preserving environment variable names for API keys.

2 duplicates security area: agents · confidence: 92.0%
Rank
Pull Request
Quality
Review
⭐#1
#15756 [Security]: strip provider apiKey from models.json before prompt serialization
@SecBear
9.2/10
✓ Consensus
#2
#14836 fix: strip apiKey from models.json to prevent credential exposure
@pahud
8.7/10
✓ Consensus

Converts Markdown formatting to Google Chat's markup syntax to ensure proper rendering of bold and strikethrough text in Google Chat messages.

2 duplicates feature area: googlechat · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#14940 fix(googlechat): convert Markdown formatting to Google Chat markup
@brandonwise
8.4/10
✓ Consensus
#2
#15172 fix(googlechat): convert Markdown formatting to Google Chat markupfix(googlechat): convert Markdown formatting to Google Chat markup
@EnzoGaillardSystems
8.1/10
✓ Consensus

Fixes a bug where peer-based routing bindings would fail to match when a channel plugin sent `peer.kind = 'dm'` instead of `'direct'` due to asymmetric normalization of the peer kind.

2 duplicates bugfix area: routing · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#14888 fix(routing): normalize peer.kind in matchesPeer for symmetric comparison
@omair445
9.4/10
✓ Consensus
#2
#14820 fix: normalize peer.kind in routing to handle dm/direct variants
@superlowburn
8.8/10
✓ Consensus

Fixes a bug where stale token counts after compaction could trigger unnecessary memory flushes, by resetting totalTokens to zero when a post-compaction token estimate is unavailable.

2 duplicates bugfix area: session management · confidence: 92.0%
Rank
Pull Request
Quality
Review
⭐#1
#15173 fix(session): reset totalTokens after compaction when estimate unavailablefix(session): reset totalTokens after compaction when estimate unavai…
@EnzoGaillardSystems
8.4/10
⚠ Human Review
#2
#15196 fix: clear stale token totals after compaction
@bufordtjustice2918
6.3/10
✓ Consensus

Improves the Chrome extension relay's connection resilience by adding auto-reconnect, state persistence, a keepalive mechanism, and improved tab lifecycle management to address connection drops and data loss issues.

2 duplicates feature area: Chrome extension relay · confidence: 91.0%
Rank
Pull Request
Quality
Review
⭐#1
#16023 fix(chrome-relay): resilient reconnect, MV3 persistence, and navigation re-attach
@codexGW
7.7/10
⚠ Human Review
#2
#15817 fix(chrome-relay): auto-reconnect, MV3 persistence, and keepalive
@derrickburns
7.6/10
⚠ Human Review

Fixes a bug where the ack reaction was not removed after a block-streamed reply in Telegram due to an incorrect check for final response delivery.

2 duplicates bugfix area: Telegram · confidence: 87.0%
Rank
Pull Request
Quality
Review
⭐#1
#14977 fix(telegram): remove ack reaction after block-streamed replies
@Diaspar4u
9.3/10
✓ Consensus
#2
#17316 fix: ack reaction not removed when block streaming is enabled (Telegram & Discord)
@czmathew
8.7/10
✓ Consensus

Preserve the original case of Google Chat space IDs when storing delivery context to prevent 403 errors due to case-sensitive API calls.

2 duplicates bugfix area: googlechat · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#15901 fix: preserve Google Chat space ID case for API replies
@echoVic
8.3/10
⚠ Human Review
#2
#15902 fix: pass all Slack file attachments to agent, not just first
@echoVic
5.9/10
⚠ Human Review

Updates the systemd unit file with the correct service version after an update, preventing stale version information from being displayed and adding a check to `openclaw doctor` to detect version mismatches.

2 duplicates bugfix area: gateway · confidence: 90.0%
Rank
Pull Request
Quality
Review
⭐#1
#16016 fix: update systemd unit version on gateway restart
@jbold
8.8/10
✓ Consensus
#2
#16185 fix: patch systemd unit version before service restart
@nozh
8.7/10
✓ Consensus

Adds Kubernetes deployment configurations, including a Helm chart and Kustomize overlays, to facilitate the deployment and management of OpenClaw within a Kubernetes environment.

2 duplicates feature area: Kubernetes deployment · confidence: 95.0%
Rank
Pull Request
Quality
Review
⭐#1
#16219 Kubernetes self re-deploy openclaw
@egkristi
7.7/10
⚠ Human Review
#2
#16213 Feature/k8s openclaw
@egkristi
5.6/10
✓ Consensus

Adds support for processing image attachments in the OpenAI chat completions endpoint by extracting base64 encoded images from the request and passing them to the agent command.

2 duplicates feature area: gateway · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#16346 feat: support image attachments in OpenAI chat completions endpoint
@sh1nj1
8.8/10
✓ Consensus
#2
#16777 feat(gateway): add multimodal image support to /v1/chat/completions
@dzianisv
8.6/10
✓ Consensus

Adds a new 'create_from_markdown' action to the Feishu doc tool, allowing the creation of documents from Markdown content via the Feishu import task API.

2 duplicates feature area: Feishu extension · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#16438 feat(feishu): add create_from_markdown import action
@ciberponk
8.6/10
✓ Consensus
#2
#16592 feat(feishu): add write mode import for markdown documents
@ciberponk
8.6/10
✓ Consensus

Fixes a bug in the web UI where extra newlines were being injected into assistant messages when tool output was hidden, causing inconsistent formatting.

2 duplicates bugfix area: UI · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#16873 Fix extra newlines in web UI when thinking toggle is off
@niceysam
9.5/10
✓ Consensus
#2
#16733 fix(ui): avoid injected newlines when tool output is hidden
@jp117
9.4/10
✓ Consensus

Fixes a regression where the `exec` tool returns empty output on Windows Scheduled Tasks due to detached process spawning preventing stdout/stderr pipes from connecting, by conditionally disabling detached mode on Windows.

2 duplicates bugfix area: process · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#18067 fix(process): disable detached spawn on Windows to fix empty exec output
@arosstale
9.2/10
✓ Consensus
#2
#17862 fix: Windows exec returns empty output when pty=false
@MisterGuy420
8.4/10
⚠ Human Review

Correctly classify statements containing the word 'need' as 'preference' within the memory-lancedb extension.

2 duplicates bugfix area: memory-lancedb · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#16678 fix(memory-lancedb): classify need statements as preference
@ciberponk
9.1/10
✓ Consensus
#2
#16703 fix(memory-lancedb): classify important statements as preference
@ciberponk
9.1/10
✓ Consensus

Enables default rate limiting for authentication endpoints in the gateway to prevent brute-force attacks, while allowing explicit disabling of rate limiting.

2 duplicates security area: gateway · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#16963 fix: enable auth rate limiting by default
@StressTestor
9.5/10
✓ Consensus
#2
#16881 fix(gateway): enable auth rate limiting by default
@Limitless2023
5.3/10
⚠ Human Review

Correctly classify Czech 'preferuji' statements as 'preference' in the memory-lancedb extension by updating the category detection logic to align with the capture logic.

2 duplicates bugfix area: memory-lancedb · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#17232 fix(memory-lancedb): classify preferuji statements as preference
@ciberponk
9.6/10
✓ Consensus
#2
#16770 fix(memory-lancedb): classify nechci statements as preference
@ciberponk
9.4/10
✓ Consensus

Adds the missing `customBindHost` field to the gateway zod schema to allow configuration validation to pass when `gateway.bind` is set to `custom`.

2 duplicates config area: gateway · confidence: 92.0%
Rank
Pull Request
Quality
Review
⭐#1
#12499 fix(config): add missing customBindHost to gateway Zod schema
@sfo2001
9.5/10
✓ Consensus
#2
#16192 fix(config): add customBindHost to gateway zod schema (#5435)
@Glucksberg
9.4/10
✓ Consensus

Fixes a bug where Telegram HTML formatter produces empty output for certain markdown constructs, leading to message delivery failure, by adding fallbacks to plain text and auto-detecting markdown tables.

2 duplicates bugfix area: telegram · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#17769 fix(telegram): preserve reply text in threaded mode dispatch
@Glucksberg
9.3/10
✓ Consensus
#2
#17629 fix(telegram): fall back to plain text when HTML formatter produces empty output
@Glucksberg
8.6/10
✓ Consensus

Fixes a bug where parsing Docker bind mounts on Windows would incorrectly truncate the host path due to drive letters containing colons, leading to incorrect filesystem path resolution in the sandbox environment.

2 duplicates bugfix area: sandbox · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#17955 fix(sandbox): parse Windows bind mounts in fs-path mapping
@Clawborn
9.2/10
✓ Consensus
#2
#13873 fix(sandbox): prevent Windows PATH from poisoning docker exec
@alessandrorodi
8.8/10
✓ Consensus

Fixes sandbox path validation to allow access to files within Docker bind mount host paths, enabling sandboxed agents to use read, write, and edit tools on those files.

2 duplicates bugfix area: agents · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#16509 Fix sandbox path validation rejecting Docker bind mount paths
@Clawborn
8.1/10
⚠ Human Review
#2
#16389 fix: allow Docker bind mount paths in sandbox tools
@Limitless2023
7.7/10
✓ Consensus

Fixes an issue where the zsh completion script would fail if `compinit` was not initialized before the script was sourced, by adding a check and initialization of `compinit` within the script itself.

2 duplicates bugfix area: cli · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#17325 fix(completion): avoid zsh compdef error when compinit is not initialized
@ephelia-ai
9.4/10
✓ Consensus
#2
#17922 fix(completion): initialize compinit when compdef is unavailable
@Clawborn
8.6/10
✓ Consensus

Adds a staleness check to the cron job execution to prevent jobs from being permanently blocked if a previous execution crashed without clearing the running marker, allowing manual triggers to proceed after a timeout.

2 duplicates bugfix area: cron · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#17895 fix(cron): add staleness check for runningAtMs on manual trigger
@PlayerGhost
9.2/10
✓ Consensus
#2
#12018 fix(cron): clear stale running markers based on job timeout
@benzer25
6.5/10
✓ Consensus

Adds a configuration option to allow users to specify extra command-line arguments when launching Chrome, enabling customization like stealth flags and user-agent overrides.

2 duplicates feature area: browser · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#15690 feat(browser): add browser.args config field for custom Chrome launch flags (#14803)
@lailoo
9.2/10
✓ Consensus
#2
#18443 feat(browser): add extraArgs config for custom Chrome launch args
@JayMishra-source
9.1/10
✓ Consensus

Implements per-thread session keys for Slack channels and groups to prevent context mixing, fixes a bug where the previousTimestamp was not correctly read from the thread-level session, and increases the thread cache TTL and max entries.

2 duplicates refactor area: Slack integration · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#17908 fix(slack): per-thread session keys to prevent context mixing
@tonydehnke
8.9/10
✓ Consensus
#2
#10686 fix(slack): use thread-level sessions for channels to prevent context mixing
@pablohrcarvalho
8.3/10
✓ Consensus

Improves gateway restart performance by skipping cache-busting for bundled hook imports, allowing V8 to reuse its module cache, and using file modification time for other hook types to only re-parse when necessary.

2 duplicates performance area: hooks · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#16960 perf: skip cache-busting for bundled hooks, use mtime for workspace hooks
@mudrii
9.1/10
✓ Consensus
#2
#17053 perf(hooks): skip cache-busting for immutable bundled hooks
@Limitless2023
4.8/10
✓ Consensus

Refactor duplicated allowlist normalization logic from Slack, Signal, and iMessage monitors into a shared helper function to reduce code duplication and improve maintainability.

2 duplicates refactor area: integrations · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#17878 Refactor: share allowlist normalization
@iyoda
9.1/10
✓ Consensus
#2
#17793 refactor(allowlist): reuse shared matcher helper
@iyoda
8.6/10
✓ Consensus

Adds the ability to configure compaction settings on a per-agent basis, overriding the global defaults, allowing for more granular control over memory management for different agent types.

2 duplicates feature area: agents · confidence: 92.0%
Rank
Pull Request
Quality
Review
⭐#1
#14598 feat: support per-agent compaction overrides in agents.list[]
@curtismercier
8.6/10
✓ Consensus
#2
#14487 feat(config): support per-agent compaction overrides (#14446)
@lailoo
8.6/10
✓ Consensus

Adds a human-readable timestamp to the inbound_meta.v1 payload to provide agents with continuous time awareness during long chat sessions, improving their ability to track time and avoid time-related errors.

2 duplicates feature area: auto-reply · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#16403 feat: add readable timestamp to inbound_meta.v1 payload
@mcinteerj
8.6/10
✓ Consensus
#2
#17017 feat(auto-reply): make agent time-aware with message timestamps
@liuy
7.9/10
✓ Consensus

Adds support for configuring a primary heartbeat model with a chain of fallback models to be used if the primary model fails, along with different fallback strategies and state persistence to track the current fallback model.

2 duplicates feature area: heartbeat · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#9486 feat(heartbeat): support primary/fallbacks model config
@sauerdaniel
8.0/10
✓ Consensus
#2
#16289 feat: heartbeat model fallback chain support
@Unwatched2345
7.8/10
✓ Consensus

Fixes a gateway crash caused by unhandled promise rejections when the Telegram getFile API fails due to network issues by adding error handling to the immediate-flush path in the inbound debouncer.

2 duplicates bugfix area: gateway · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#17243 fix(telegram): catch getFile network failures to prevent gateway crash (#17227)
@robbyczgw-cla
8.8/10
✓ Consensus
#2
#12870 fix: recover from telegram fetch errors (issue #12835)
@ambicuity
8.7/10
✓ Consensus

Increase the timeout for fetching attachments in the Signal integration to 30 seconds to prevent AbortErrors on slower connections or for larger attachments.

2 duplicates bugfix area: signal · confidence: 89.0%
Rank
Pull Request
Quality
Review
⭐#1
#16573 fix(signal): increase attachment fetch timeout to 30s (#16545)
@robbyczgw-cla
8.6/10
⚠ Human Review
#2
#6576 fix(signal): increase attachment fetch timeout to 60s
@rwarettg
8.0/10
✓ Consensus

Fixes a bug where the WhatsApp Web channel would fail to start if the initial connection attempt resulted in a DNS or network error, by ensuring the reconnect loop handles initial connection failures.

2 duplicates bugfix area: WhatsApp Web gateway · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#9727 fix(whatsapp): retry reconnect loop on initial connection failure
@luizlf
9.0/10
✓ Consensus
#2
#14484 fix(whatsapp): catch connection-phase errors in reconnect loop
@onthway
8.5/10
✓ Consensus

Fixes a crash after `openclaw update` by spawning a new process for daemon restart and post-update doctor command to avoid stale module references due to content-hashed filenames.

2 duplicates bugfix area: cli · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#17251 fix(cli): spawn new process for daemon restart after update
@CornBrother0x
8.7/10
✓ Consensus
#2
#17388 fix: spawn new process for daemon restart after update to avoid module loading errors
@Limitless2023
8.5/10
✓ Consensus

Fixes a bug where third-party memory plugins were incorrectly displayed as 'unavailable' in the `openclaw status` command by probing the plugin's status via gateway RPC or marking it as 'active' if the gateway is unreachable.

2 duplicates bugfix area: status command · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#14466 fix(status): report memory status for all memory plugins (#14261)
@lailoo
9.4/10
✓ Consensus
#2
#12596 fix(status): show third-party memory plugins as active instead of unavailable
@nhadaututtheky
9.0/10
✓ Consensus

Suppress file-size error replies in Telegram groups when `requireMention` is enabled and the bot is not mentioned, preventing multiple bots from spamming the same error message.

2 duplicates bugfix area: Telegram bot handlers · confidence: 87.0%
Rank
Pull Request
Quality
Review
⭐#1
#17081 fix(telegram): suppress file-size error replies in groups when bot is not mentioned
@p697
9.1/10
✓ Consensus
#2
#17138 fix: skip file size error in Telegram groups when requireMention is enabled
@Limitless2023
4.7/10
✓ Consensus

Adds support for the Gemini embedding model and a configurable base URL for OpenAI-compatible APIs to the memory-lancedb plugin, and fixes a TUI crash related to terminal width overflow.

2 duplicates feature area: memory-lancedb · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#17701 fix(memory-lancedb): add gemini-embedding-001 and baseUrl support
@Phineas1500
8.7/10
✓ Consensus
#2
#17696 fix(memory-lancedb): add gemini-embedding-001 and baseUrl support
@aldoeliacim
8.7/10
✓ Consensus

Improve the security of OpenClaw by providing guidance on redacting sensitive information in security reports and offering a quick hardening checklist for users.

2 duplicates docs area: security · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#5507 docs(security): redaction guidance + quick hardening checklist
@mitre88
8.6/10
⚠ Human Review
#2
#12062 docs: Add security hardening guide for OpenClaw configurations
@wlshlad85
7.7/10
✓ Consensus

Enforce consistent Slack Block Kit validation across all message sending and editing paths, including runtime calls, to ensure payload integrity and prevent errors.

2 duplicates feature area: Slack · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#18284 feat(slack): centralize Block Kit input validation
@Solvely-Colin
8.6/10
✓ Consensus
#2
#18416 Slack: validate runtime blocks in send and edit paths
@Solvely-Colin
7.9/10
⚠ Human Review

Prevents binary audio files from being incorrectly identified as UTF-16 text during file extraction, which would lead to garbage data being injected into the context window.

2 duplicates bugfix area: media-understanding · confidence: 90.0%
Rank
Pull Request
Quality
Review
⭐#1
#5588 fix(media): skip binary audio in file extraction to prevent false UTF-16 detection
@NSEvent
9.3/10
✓ Consensus
#2
#7454 fix: skip UTF-16 heuristic for audio/video/image MIME types (#7444)
@gavinbmoore
8.7/10
✓ Consensus

Fixes a race condition in webchat streaming where tool events could arrive before the preceding text, causing text truncation or incorrect positioning by flushing the text buffer before broadcasting tool start events.

2 duplicates bugfix area: gateway · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#14946 fix(webchat): accumulate text across blocks in streaming buffer
@mcaxtr
8.6/10
✓ Consensus
#2
#5681 fix(gateway): flush text buffer before tool events in webchat
@MaudeBot
8.0/10
✓ Consensus

Fixes a bug where LLM slug generation fails in environments without Anthropic configured by using the configured default agent model instead of defaulting to Anthropic.

2 duplicates bugfix area: LLM slug generator hook · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#15574 fix(hooks): use configured model for llm slug generation (#15510)
@TsekaLuk
9.3/10
✓ Consensus
#2
#5945 fix: use configured model for slug generator (AI-assisted)
@HEDELKA
7.7/10
✓ Consensus

Fixes a bug where the `/status` command would not reflect the thinking level set by a `/think` command in the same message when used in the directive-only path.

2 duplicates bugfix area: auto-reply · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#16700 fix: /status shows stale thinking level after directive change
@cmfinlan
8.9/10
✓ Consensus
#2
#5992 Fix: /status shows correct think level when used with /think (fixes #5919)fix(auto-reply): /status shows correct think level when combined with…
@simran122
8.5/10
✓ Consensus

Adds configuration options to customize the auto-compaction process, allowing users to specify custom instructions for the summary and override the model used for compaction.

2 duplicates feature area: gateway · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#11089 feat(compaction): support customInstructions and model override for auto-compaction
@p697
8.8/10
✓ Consensus
#2
#11970 feat: add model.compact config for dedicated compaction model
@meaadore1221-afk
6.8/10
⚠ Human Review

Preserve Web UI scopes when allowInsecureAuth is enabled to fix a 'missing scope: operator.read' error when accessing the Web UI over LAN (plain HTTP) without device authentication.

2 duplicates bugfix area: gateway · confidence: 83.0%
Rank
Pull Request
Quality
Review
⭐#1
#17681 fix: preserve Web UI scopes when allowInsecureAuth is enabled
@peteropenclaw
9.1/10
✓ Consensus
#2
#16866 fix: preserve scopes when shared-auth succeeds (Web UI LAN access)
@MisterGuy420
8.7/10
✓ Consensus

Prevent the `formal-conformance` CI workflow from failing on fork PRs due to GitHub token restrictions when attempting to post PR comments, while still uploading the drift artifact.

2 duplicates config area: CI workflows · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#17426 ci(formal): don't fail on fork PRs when PR comment is blocked
@mitre88
9.4/10
✓ Consensus
#2
#17056 ci(formal): use step summary instead of PR comment for drift notification
@LucasAIBuilder
7.9/10
✓ Consensus

Fixes a cold-start race condition in `lookupContextTokens` by adding a synchronous fallback cache populated from the user's config file, ensuring the correct context window is used before the async model discovery cache is populated.

2 duplicates bugfix area: agents · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#12270 fix: add synchronous config fallback to lookupContextTokens
@Yida-Dev
9.3/10
✓ Consensus
#2
#12195 fix(agents): sync config fallback for lookupContextTokens cold-start race
@mcaxtr
9.1/10
✓ Consensus

Fixes a race condition on Windows where concurrent reads of the session store file can observe a truncated or empty file during writes, leading to loss of session context, by implementing atomic writes using a temporary file and rename operation, and adding retry logic for both read and write operations.

2 duplicates bugfix area: session store · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#16542 fix(sessions): use atomic temp+rename write on Windows
@aldoeliacim
8.7/10
✓ Consensus
#2
#18347 fix: atomic session store writes to prevent context loss on Windows
@twcwinston
8.4/10
✓ Consensus

Formats timestamps in the `sessions_history` tool output using the user's configured timezone, falling back to the host timezone if none is configured, and handles potentially invalid timestamps gracefully.

2 duplicates feature area: sessions_history tool · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#12268 fix: format sessions_history timestamps using configured userTimezone
@mcaxtr
9.1/10
✓ Consensus
#2
#12358 fix: Sessions format timestamps in sessions_history using userTimezone
@xialonglee
9.0/10
✓ Consensus

Fixes an issue where sandbox agents cannot resolve container-absolute paths and rewrites bundled skill paths to workspace-local copies when running inside a sandbox.

2 duplicates bugfix area: agents/sandbox · confidence: 86.0%
Rank
Pull Request
Quality
Review
⭐#1
#7915 Fix sandbox skill paths
@sunnoy
7.9/10
✓ Consensus
#2
#17402 fix:sandbox path issue
@luckylhb90
7.0/10
✓ Consensus

Fixes a bug where Discord messages from unconfigured channels were incorrectly dropped when `groupPolicy` was set to 'open' and a partial channel configuration existed.

2 duplicates bugfix area: discord · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#17513 fix(discord): respect groupPolicy in channel config fallback (#4555)
@aronchick
9.6/10
✓ Consensus
#2
#15816 fix(discord): respect groupPolicy "open" in channel allowed checks
@arosstale
8.5/10
✓ Consensus

Allow plugins to override the model selection for an agent run using the `before_agent_start` hook, enabling use cases like cost-optimizing model routers and A/B testing.

2 duplicates feature area: agents · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#14647 feat(plugins): allow before_agent_start hook to override model (#14585)
@lailoo
8.5/10
✓ Consensus
#2
#17614 feat: allow before_agent_start hook to override model selection
@plc
7.9/10
✓ Consensus

Configures Mattermost to render Markdown tables natively by default instead of wrapping them in code blocks, and adds tests to verify the configuration and overrides.

2 duplicates bugfix area: markdown rendering · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#12257 fix(mattermost): default table mode to 'off' for native Markdown rendering
@mcaxtr
9.6/10
✓ Consensus
#2
#12809 fix(mattermost): preserve Markdown formatting + native tables
@echo931
9.1/10
✓ Consensus

Fixes a bug where the LINE channel status check incorrectly reports the channel as unconfigured when credentials are provided via files by using the `configured` flag from the `ChannelAccountSnapshot` instead of attempting to read credentials directly from the snapshot.

2 duplicates bugfix area: LINE channel plugin · confidence: 93.0%
Rank
Pull Request
Quality
Review
⭐#1
#11110 fix(line): false 'not configured' warnings when tokenSource=file
@lailoo
9.4/10
✓ Consensus
#2
#10487 fix(line): use snapshot configured flag in collectStatusIssues
@mcaxtr
9.2/10
✓ Consensus

Fixes a bug where verbose tool output was missing the file path when the tool used the 'file_path' alias instead of 'path' in its arguments, and adds tests to ensure both 'path' and 'file_path' are handled correctly, with 'path' taking precedence.

2 duplicates bugfix area: agents · confidence: 82.0%
Rank
Pull Request
Quality
Review
⭐#1
#10189 fix: resolve file_path param in tool display for read/write tools
@Yida-Dev
9.3/10
✓ Consensus
#2
#10102 fix: handle file_path alias in verbose tool display
@mcaxtr
9.1/10
✓ Consensus

Adds SearXNG as a web search provider, allowing users to leverage a self-hosted, privacy-respecting metasearch engine within the application.

2 duplicates feature area: gateway · confidence: 93.0%
Rank
Pull Request
Quality
Review
⭐#1
#13665 feat(web-search): add SearXNG as a search provider
@sfo2001
8.8/10
✓ Consensus
#2
#16895 feat(web-search): add SearXNG as a search provider
@rustyorb
7.1/10
⚠ Human Review

Updates the diagnostics-otel plugin to be compatible with version 2.x of the @opentelemetry/resources package by using the resourceFromAttributes function instead of the Resource class constructor.

2 duplicates bugfix area: diagnostics-otel · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#11957 fix(diagnostics-otel): use @opentelemetry/resources v2 API
@scott-memco
9.1/10
✓ Consensus
#2
#2574 fix(diagnostics-otel): update to @opentelemetry/resources v2.x API
@dillera
8.3/10
⚠ Human Review

Fixes a bug where chat messages were written to a different session than they were read from due to inconsistent use of session keys, causing messages to not appear in chat history.

2 duplicates bugfix area: gateway · confidence: 91.0%
Rank
Pull Request
Quality
Review
⭐#1
#3182 fix(gateway): use canonical session key in chat.send
@chrisherold
8.0/10
✓ Consensus
#2
#3182 fix(gateway): use canonical session key in chat.send
@chrisherold
8.0/10
✓ Consensus

Prevents corrupted agent session transcripts by dropping toolResult messages that do not have a corresponding pending tool call, thus avoiding 'No tool call found' loops.

2 duplicates bugfix area: agents · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#3622 fix(agents): drop orphan tool results
@mickobizzle
9.0/10
✓ Consensus
#2
#3622 fix(agents): drop orphan tool results
@mickobizzle
9.0/10
✓ Consensus

Refactors the GatewayDiscoveryModel to use structured concurrency with `Task` instead of `Task.detached` to ensure proper actor context inheritance and cancellation handling within the MainActor context.

2 duplicates refactor area: gateway · confidence: 97.0%
Rank
Pull Request
Quality
Review
⭐#1
#3424 Use structured concurrency instead of Task.detached in GatewayDiscoveryModel
@abhijeet117
8.1/10
✓ Consensus
#2
#3424 Use structured concurrency instead of Task.detached in GatewayDiscoveryModel
@abhijeet117
8.1/10
✓ Consensus

Fixes a TypeError on Matrix bot startup when E2EE is enabled and the crypto SDK does not have the `requestOwnUserVerification` function by adding a runtime check for the function's existence.

2 duplicates bugfix area: matrix · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#2902 fix(matrix): check if requestOwnUserVerification exists before calling
@dokterdok
9.1/10
✓ Consensus
#2
#2902 fix(matrix): check if requestOwnUserVerification exists before calling
@dokterdok
9.1/10
✓ Consensus

Clarify in the Discord skill documentation that Discord search does not support boolean operators and suggest alternative approaches for searching multiple terms.

2 duplicates docs area: Discord skill documentation · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#3402 docs(discord): clarify search doesn't support OR/AND operators
@pvoo
9.1/10
⚠ Human Review
#2
#3402 docs(discord): clarify search doesn't support OR/AND operators
@pvoo
9.1/10
⚠ Human Review

Fixes OAuth credential extraction for the Google Gemini CLI when installed via version managers like mise by resolving shims and expanding search paths for the oauth2.js file.

2 duplicates bugfix area: auth · confidence: 98.0%
Rank
Pull Request
Quality
Review
⭐#1
#3521 fix(gemini-auth): handle mise shims and nested node_modules paths
@sebslight
6.7/10
✓ Consensus
#2
#3521 fix(gemini-auth): handle mise shims and nested node_modules paths
@sebslight
6.7/10
✓ Consensus

Fixes a crash in the macOS app caused by SwiftPM resource bundles not being located correctly within the app bundle's resource directory by patching the generated Swift code to use `resourceURL` instead of `bundleURL`.

2 duplicates bugfix area: macos-app · confidence: 99.0%
Rank
Pull Request
Quality
Review
⭐#1
#3337 fix(macos-app): patch SwiftPM Bundle.module accessor for app bundle
@skymoore
7.7/10
⚠ Human Review
#2
#3337 fix(macos-app): patch SwiftPM Bundle.module accessor for app bundle
@skymoore
7.7/10
⚠ Human Review

Improves the reliability of the autoCapture feature in the memory-lancedb extension by correctly identifying and capturing relevant user and assistant messages, even when autoRecall is enabled and injecting context into the messages.

2 duplicates bugfix area: memory-lancedb · confidence: 88.0%
Rank
Pull Request
Quality
Review
⭐#1
#15896 fix(memory-lancedb): capture even with injected recall context
@aelaguiz
8.6/10
✓ Consensus
#2
#3401 fix(memory-lancedb): improve autoCapture with turn-by-turn processing
@mike-nott
8.5/10
✓ Consensus

Fixes a bug where one-shot cron jobs with `deleteAfterRun: true` would enter an infinite loop if they were skipped or failed, by ensuring they are deleted regardless of their execution status.

2 duplicates bugfix area: cron · confidence: 84.0%
Rank
Pull Request
Quality
Review
⭐#1
#3693 fix(cron): delete deleteAfterRun jobs regardless of execution status
@HirokiKobayashi-R
9.3/10
✓ Consensus
#2
#11657 fix(cron): treat skipped heartbeat as ok for one-shot jobs
@DukeDeSouth
9.1/10
✓ Consensus

Fixes a configuration validation error in Docker deployments caused by the missing memory-core plugin by ensuring its dependencies are installed during the Docker image build process.

2 duplicates bugfix area: docker · confidence: 96.0%
Rank
Pull Request
Quality
Review
⭐#1
#4450 fix bug #4366: Error: Config validation failed: plugins.slots.memory: plugin not found: memory-core
@tryagain3
7.3/10
✓ Consensus
#2
#4450 fix bug #4366: Error: Config validation failed: plugins.slots.memory: plugin not found: memory-core
@tryagain3
7.3/10
✓ Consensus

Fixes intermittent sandbox execution failures by using an absolute path for the shell and adds the ability to allow reads from specific directories outside the workspace root via an allowlist.

2 duplicates bugfix area: sandbox · confidence: 94.0%
Rank
Pull Request
Quality
Review
⭐#1
#3907 fix(sandbox): use absolute /bin/sh path + add allowedReadPaths config
@pvoo
8.0/10
✓ Consensus
#2
#3907 fix(sandbox): use absolute /bin/sh path + add allowedReadPaths config
@pvoo
8.0/10
✓ Consensus

Bypasses the config validation check when running `moltbot tui --url` to allow remote TUI clients to connect without requiring a local configuration.

2 duplicates feature area: CLI · confidence: 100.0%
Rank
Pull Request
Quality
Review
⭐#1
#4109 fix(cli): bypass config guard for tui --url
@hopenjin
8.7/10
✓ Consensus
#2
#4109 fix(cli): bypass config guard for tui --url
@hopenjin
8.7/10
✓ Consensus

Fixes compatibility issues with OpenTelemetry v2.x API in the diagnostics-otel plugin, addressing Resource constructor, Semantic Conventions, and LoggerProvider API changes.

2 duplicates bugfix area: diagnostics-otel plugin · confidence: 85.0%
Rank
Pull Request
Quality
Review
⭐#1
#4255 fix(diagnostics-otel): complete OpenTelemetry v2.x compatibility
@arbgjr
8.8/10
✓ Consensus
#2
#11530 diagnostics-otel: fix OpenTelemetry v2 resource/logs API compatibility
@erain
8.4/10
✓ Consensus

Fixes deployment issues in containerized environments by updating the Docker Compose configuration to build the image from source and use the correct volume mount path, resolving image pull failures and EBUSY errors.

2 duplicates config area: deployment · confidence: 91.0%
Rank
Pull Request
Quality
Review
⭐#1
#3965 Fix Docker Compose configuration for moltbot deployment
@YoByron
8.4/10
✓ Consensus
#2
#3965 Fix Docker Compose configuration for moltbot deployment
@YoByron
8.4/10
✓ Consensus

Prevents OpenAI-compatible clients from crashing when the SSE stream terminates by ensuring a final `chat.completion.chunk` with a `finish_reason` is sent before `data: [DONE]` and improves compatibility with older client payload formats.

2 duplicates bugfix area: gateway · confidence: 98.0%
Rank
Pull Request
Quality
Review
⭐#1
#4300 Gateway: prevent OpenAI-compatible client crash on SSE termination
@perryraskin
8.1/10
✓ Consensus
#2
#4300 Gateway: prevent OpenAI-compatible client crash on SSE termination
@perryraskin
8.1/10
✓ Consensus

🧭 Vision Alignment

How well each PR aligns with the project's stated architecture and goals. Low scores indicate potential drift.

#11191 feat: REALLYopenClaw JAILBREAK - disable global gateway lock by default @latamapac
CLOSE 1.0/10
The PR introduces significant changes that diverge from the project's vision and goals, and may lead to conflicts and instability.
#17976 Update print statement from 'Hello' to 'Goodbye' @canarylumen-droid
CLOSE 1.5/10
The PR does not align with the project's goals or architecture, and does not follow the contributing guidelines.
#7315 Launch: SotyBot v0.1.0 MVP - The Open Agent Engine @descambiado
CLOSE 1.5/10
The PR is not aligned with the OpenClaw project's vision and goals, and introduces significant changes that are not documented or discussed in the project's roadmap or contributing guidelines.
#8876 Confirmaciones para equipo de IT @m4xjunior
CLOSE 1.5/10
The PR contains high-impact security issues and drifts significantly from the project's vision and current focus.
#13655 acceptAdd nixpacks configuration for Python and Node.js @Manosage67
CLOSE 1.5/10
The PR introduces significant drift from the project's architecture and conventions, and would break deployment if merged.
#9829 Fix MCP transport reconnect and SSE header handling @mabengda
CLOSE 2.0/10
The PR introduces significant changes to the safety and privacy guidance in the AGENTS.md template, which may compromise the security and trust of the OpenClaw project.
#12725 Update gateway-smoke.ts @yasir-shahhhhh
CLOSE 2.0/10
The PR lacks essential information, such as a description, labels, and actual changes, making it difficult to evaluate its alignment with the project vision and goals.
#14712 New files from Fly.io Launch @Sandro-AAA
CLOSE 2.0/10
The PR introduces high-impact configuration errors that would break deployments and persistence, and is not aligned with the project's documented deployment requirements.
#16246 feat(p2p): Decentralized Agent Collaboration & Compute Exchange Layer @Agnuxo1
CLOSE 2.0/10
The PR introduces significant security concerns, lacks proper integration with the existing system, and has critical implementation issues, making it unsuitable for merging.
#18255 Fix memory vector store dimension mismatch by resetting index @Clawborn
CLOSE 2.5/10
While the PR addresses a specific issue, it lacks focus and includes unrelated changes, making it difficult to review and understand the impact on the project.
#17764 fix: CLI update module loading - syntax fixes (v2) @Limitless2023
CLOSE 2.5/10
While the PR attempts to fix a specific issue, it introduces new errors and lacks proper testing, requiring a thorough review and revision before merging.
#5950 Improvement/windows shell enhancement @zzjj7000
CLOSE 2.5/10
While the PR improves PowerShell execution reliability, it introduces several unrelated changes that may cause issues and drift from the project's vision, requiring further discussion and refinement
#7030 feat: add line balancing animation for Double End M12 Cable Assembly @ceasarcapuno
CLOSE 2.5/10
The PR introduces a significant new feature that is not aligned with the project's current focus or roadmap, and does not follow the project's guidelines for contributing new features.
#9330 [Swarm] [DX]: Improve gateway.bind validation error messag @swarmagents
CLOSE 2.5/10
The PR does not meet the project's contribution guidelines and does not implement the described behavior change, requiring further discussion and clarification before it can be considered for merge.
#13775 Lucas/enable corememories @Itslouisbaby
CLOSE 2.5/10
The PR has a critical issue and introduces drift from the project's guidelines, requiring discussion and revision before it can be considered for merge.
#14469 feat: Add automatic pnpm install to shell hook @marcoziti
CLOSE 2.5/10
The PR requires further discussion to ensure that the changes align with the project's vision and architecture, and to address the concerns around the shellHook's behavior and the introduction of new inputs and modules.
#15941 fix(sessions): allow session file paths from other agents' sessions dirs @LiJianLi128
CLOSE 2.5/10
The PR introduces a security vulnerability and does not align with the project's security goals, requiring further discussion and revision before merging.
#16032 Local first @bczaicki
CLOSE 2.5/10
While the PR includes some aligned aspects, such as comprehensive test coverage and updated documentation, the significant changes and drift from the project's original vision and goals warrant further discussion and review.
#17648 fix: Discord guild channel detection using rawMessage.guild_id @MisterGuy420
CLOSE 3.0/10
The PR requires further discussion to clarify the changes and ensure they align with the project's vision and architecture.
#7030 feat: add line balancing animation for Double End M12 Cable Assembly @ceasarcapuno
CLOSE 3.0/10
The PR introduces a significant new feature that is not aligned with the project's vision or roadmap, and does not follow the project's guidelines for contributing new features.
#7206 feat: add V-Infinite elite assistant persona and cyber-warrior skill set @oki3505F
CLOSE 3.0/10
The PR raises significant concerns about safety and policy, and requires further discussion and review to ensure alignment with the project's goals and values.
#7206 feat: add V-Infinite elite assistant persona and cyber-warrior skill set @oki3505F
CLOSE 3.0/10
The PR introduces new features that could be beneficial, but it also raises significant concerns about safety and alignment with the project's goals and values, requiring further discussion and review.
#7639 [Agent] [Bug]: Missing 'zop' module at extension/mattermost and remo @swarmagents
CLOSE 3.0/10
The PR's changes seem unrelated to the project's current focus and do not address a documented need, requiring further discussion to understand its relevance and potential impact on the project.
#9317 [Swarm] [Bug]: Connection error on Intel MacBook Pro persi @swarmagents
CLOSE 3.0/10
The PR does not align with the project's goals and guidelines, and does not provide a fix or tests for the reported bug, so it requires further discussion and clarification before it can be merged.
#9317 [Swarm] [Bug]: Connection error on Intel MacBook Pro persi @swarmagents
CLOSE 3.0/10
The PR does not align with the project's vision and guidelines, and further discussion is needed to determine the best course of action to address the reported bug.
#9340 feat(simulation): Add 100-bot society simulation with complete lifecycle @zandis
CLOSE 3.0/10
While the PR is well-structured and aligns with the project's goals, it introduces significant complexity and is not explicitly mentioned in the project's roadmap, requiring further discussion and review.
#11272 Update render.yaml @raushan-s
CLOSE 3.0/10
The PR introduces changes that may break the app's functionality and data persistence, requiring a thorough review to ensure the changes are safe and compatible with the project's requirements.
#14280 feat: add Rube MCP plugin for 500+ app integrations @qdonohue
CLOSE 3.0/10
Due to fundamental errors in plugin manifest naming, type imports, package scope, and tool naming, this PR significantly deviates from the project's architecture and contribution guidelines, requiring substantial rework before it can be considered.
#15466 Vps setup merge @tsekula
CLOSE 3.0/10
The PR introduces significant security regressions and does not align with the project's recommended setup path, requiring further discussion and review before merging.
#16543 [AI-assisted] feat(usage): support cache-hit differentiated pricing @OwenJiong24
CLOSE 3.0/10
While the PR addresses a specific need and follows project conventions, it contains critical bugs and issues that need to be addressed before merging.
#18157 docs(mattermost): add always chatmode and requireMention workaround @andrey-esipov
CLOSE 3.5/10
While the PR adds useful documentation, it also introduces inconsistencies and potential issues that need to be addressed before merging.
#13839 Zhch158 @zhch158
CLOSE 3.5/10
The PR has some aligned aspects, but the introduction of a user-specific file with personal information and the lack of adherence to project guidelines raise concerns that need to be discussed before merging.
#5947 Feature/kimi reasoning support @zzjj7000
CLOSE 3.5/10
While the PR addresses a specific issue, its scope and risk are significantly increased by the introduction of unrelated changes, making it necessary to discuss and refactor the PR before merging.
#12694 Devin/1770645191 add elizaos adapter @latamapac
CLOSE 3.5/10
The PR introduces significant changes to the project's architecture and workflow, but lacks clear justification or explanation of its purpose, which requires further discussion and review before merging.
#13539 Claude/update dockerfile cmd 1 te te @federiconicolasvozza-oss
CLOSE 3.5/10
While the PR updates the Docker image and Render blueprint, it introduces conflicts and unrelated changes that require further review and testing.
#17007 fixed stacy voice @tashen247
CLOSE 3.5/10
The PR requires further review to ensure that the changes align with the project's architecture and goals, and to verify that the fix is correct and thoroughly tested.
#7085 test: skip flaky workspace-paths & safe-bins tests on non-Linux/CI (refs #7057) @ThinkIbrokeIt
REVIEW 4.0/10
While the PR addresses a specific issue and provides a temporary fix, it includes unrelated functional changes and a package version rollback that need to be reviewed and addressed before merging.
#9331 [Swarm] [Bug]: Memory search broken - Cannot find module d @swarmagents
REVIEW 4.0/10
While the PR provides valuable analysis and insights, it does not address the underlying issue and may require further work to ensure alignment with the project's goals and architecture.
#10912 feat: add --session-key to clawdis system event @SocialNerd42069
DISCUSS 4.0/10
While the PR addresses a specific problem and provides a clear solution, it introduces unrelated changes and lacks a complete implementation, requiring further discussion and refinement.
#11967 Feature/maxwell @mmyyfirstb
DISCUSS 4.0/10
The PR introduces potentially problematic changes to the Feishu channel and includes a non-portable `codeindex.cm` file, requiring discussion and revision before merging.
#12996 feat(infra): Add session persistence with atomic writes and recovery @trevorgordon981
DISCUSS 4.0/10
While the PR adds valuable features to the project, it also introduces a security issue that needs to be addressed before merging, and requires further discussion on how the session persistence module is intended to be used in production.
#13958 Claude/secureclaw env supabase dz q hh @kbpranay
DISCUSS 4.0/10
While the PR addresses some security concerns and adds new features, it also introduces significant changes to the project's architecture and branding, which require further discussion and alignment with the project's maintainers and community.
#14509 feat: setup and configure proxy system @montelli99
DISCUSS 4.0/10
While the PR addresses a specific need, it introduces significant changes to the project's architecture and configuration management, which require further discussion and review to ensure alignment with the project's goals and existing architecture.
#15253 Adding structured log content @emailhxn
DISCUSS 4.0/10
While the PR adds valuable structured log content, it raises significant concerns about sensitive data exposure and needs further discussion to address these issues before merging.
#17986 feat: Add GOALS.md and SOUVENIR.md template files @ibrahimq21
REVIEW 4.5/10
While the PR adds new template files, it deviates from the established pattern of using generic placeholders, which may cause inconsistencies in the codebase, and therefore requires further review and discussion.
#18224 fix(telegram): allow per-message link preview override @Clawborn
DISCUSS 4.5/10
While the PR includes some useful changes, it also includes multiple unrelated changes and a critical security issue, which needs to be discussed and addressed before merging.
#7044 feat: Add local model tool calling support @jokelord
REVIEW 4.5/10
While the PR introduces a useful feature, it contains unrelated breaking changes and potential issues that need to be addressed before merging.
#7328 Feat/integrate chutes ai Details in Readme_chutes.md @Trompetilla
DISCUSS 4.5/10
While the PR adds new features and integrations, it raises concerns about OAuth-only user handling and the functionality of the new CLI command, requiring further discussion and clarification before merging.
#7316 fix: /chat dashboard performance @felipcsousa
REVIEW 4.5/10
While the PR addresses a specific performance issue, it also introduces some concerns around maintainability and potential unexpected behavior, which require further review and discussion.
#9319 [Swarm] [Mattermost] WebSocket disconnects with "client si @swarmagents
DISCUSS 4.5/10
While the PR is well-written and follows contribution guidelines, it does not provide a concrete solution to the reported issue and may not align with the project's current priorities, requiring further discussion and clarification.
#9319 [Swarm] [Mattermost] WebSocket disconnects with "client si @swarmagents
DISCUSS 4.5/10
While the PR is well-formatted and provides a clear analysis, it does not actually fix the issue and does not meet the project's contribution expectations, so further discussion is needed to determine the best course of action.
#9861 fix(agents): re-run tool_use/tool_result repair after limitHistoryTurns @CyberSinister
DISCUSS 4.5/10
While the PR addresses a real issue, it also introduces unrelated changes that may cause problems and drift from the project's vision.
#13576 P2P Chia blockchain wallet monitoring @Koba42Corp
DISCUSS 4.5/10
While the PR adds a new feature that could be useful to some users, it introduces new dependencies and potential architecture drift, and its implementation has some issues that need to be addressed.
#15583 docs: Autonomous Governance Framework for bot ecosystem @Insider77Circle
DISCUSS 4.5/10
While the PR addresses a need for a governance framework, it introduces significant complexity and relies heavily on AI-generated content, which requires further discussion and review before proceeding.

⭐ Top Quality PRs

Highest-scoring PRs across all quality dimensions.

#17232 fix(memory-lancedb): classify preferuji statements as preference @ciberponk
9.6/10
High-quality PR with excellent test coverage, focused scope, and minimal breaking risk.
#17513 fix(discord): respect groupPolicy in channel config fallback (#4555) @aronchick
9.6/10
High-quality PR with thorough tests and minimal scope, but minor style inconsistencies.
#12257 fix(mattermost): default table mode to 'off' for native Markdown rendering @mcaxtr
9.6/10
High-quality PR with comprehensive tests and minimal scope, but minor style inconsistencies.
#16978 fix(hooks): preserve before_tool_call marker across abort signal wrapping @arosstale
9.6/10
High-quality PR with clear rationale, comprehensive test coverage, and minimal, targeted fix.
#3967 fix(sandbox): correct workspace prompt path @sweepies
9.5/10
High-quality PR with focused scope, good test coverage, and minimal breaking risk.
#3967 fix(sandbox): correct workspace prompt path @sweepies
9.5/10
High-quality PR with a focused change, thorough tests, and minimal risk of breaking existing functionality.
#6857 docs: clarify that /elevated on is an alias for ask @whoknowsmann
9.5/10
High-quality doc update with clear explanations and minimal code changes, but could benefit from additional tests.
#9425 refactor(agents): replace console.warn with SubsystemLogger in compaction.ts @dinakars777
9.5/10
High-quality, focused refactor with good test coverage and minimal risk.
#10665 fix(docs): replace removed gateway wake with system event in coding-agent skill @Yida-Dev
9.5/10
High-quality documentation-only change with clear explanations and minimal risk of breaking existing functionality.
#10726 fix: re-read session store inside lock in updateLastRoute @Yida-Dev
9.5/10
High-quality PR with a focused fix, good test coverage, and minimal risk of breaking existing functionality.