Is OpenClaw v2026.6.10 stable?
-178/100Fact score: -178/100 · evidence-based, not a YES/NO verdict
“v2026.6.10 picked up fresh gated evidence: exec output can vanish, model/provider routing still trips on real configs, and companion surfaces are throwing punches. The score was already in the basement; now it found stairs.”
Stability Score
-178Base
80
Evidence
-178
Votes
-0
Survived
ignored
Curated
ignored
-178 evidence debt=-178
Affected components
acpattachmentsauthbrowserchannel-configcodexconfig-migrationcron-runtimediscorddoctorexecfeishuinstallerlinemcpmemorymessage-deliveryplugin-installplugin-systemprompt-sizeprovider-authprovider-cacheprovider-routingreasoningruntimesession-stateskill-workshopslacktelegramtlstoolsuiusage-accountingvoiceweb-searchwebchatwhatsapp
Install this version
npm install openclaw@2026.6.10openclaw update --tag 2026.6.10Score Evidence
| Issue | Area | Type | Penalty | Reason |
|---|---|---|---|---|
| openclaw/openclaw issue 78493 → | config-migration | kernel | -5 | Still reproducible on 2026.6.10: unreadable config/EACCES fallback can proceed to config writes, risking config clobber and crash-loop startup. |
| openclaw/openclaw issue 96374 → | message-delivery | kernel | -5 | Telegram isolated ingress can leave stale claimed rows after restart, blocking all subsequent inbound delivery on 2026.6.10. |
| openclaw/openclaw issue 96337 → | provider-routing | runtime | -3 | anthropic-vertex route=native on 2026.6.10 returns non-visible-output for pure text Claude responses; tool-call responses still work. |
| openclaw/openclaw issue 96335 → | memory | runtime | -3 | lossless-claw context engine fails during read-only plugin registration on 2026.6.10 and falls back to the legacy engine. |
| openclaw/openclaw issue 95515 → | config-migration | runtime | -3 | Upgrade to 2026.6.10 still reproduces email channel config corruption with an invalid groupAllowFrom field. |
| openclaw/openclaw issue 95997 → | auth | runtime | -3 | Gateway CLI read probes can poison local device scopes so later write-scoped agent calls hit scope-upgrade pending approval; path is present in current main/release line. |
| openclaw/openclaw issue 91266 → | skill-workshop | tool-specific | -2 | skill_workshop dynamic-tool apply still times out under approval wait on OpenClaw 2026.6.10 while the CLI path succeeds. |
| openclaw/openclaw issue 96363 → | telegram | channel-specific | -1 | Telegram /status final reply fails with RICH_MESSAGE_EMAIL_INVALID when richMessages=true on stable 2026.6.10. |
| openclaw/openclaw issue 96657 → | feishu | channel-specific | -5 | Feishu non-inbound tool calls can fall back to the global default account on 2026.6.10, causing cross-tenant 403/resource-access failures. |
| openclaw/openclaw issue 96564 → | runtime | runtime | -4 | claude-cli headless warm-stdin loses conversation continuity on 2026.6.8–2026.6.10, wiping the session binding every turn. |
| openclaw/openclaw issue 96704 → | browser | tool-specific | -3 | Managed browser cookies are in-memory only on 2026.6.10, so login sessions disappear after browser/gateway restart. |
| openclaw/openclaw issue 96585 → | runtime | runtime | -3 | Windows/Node 25 reports repeated FileHandle garbage-collection crashes against OpenClaw 2026.6.10. |
| openclaw/openclaw issue 96239 → | message-delivery | runtime | -3 | Gateway reply ordering can surface the tool warning instead of the real answer on 2026.6.10-beta/current 6.10 path. |
| openclaw/openclaw issue 96452 → | codex | tool-specific | -2 | Codex Computer Use get_app_state can hang for 120s awaiting tools/call on a 2026.6.10 build. |
| openclaw/openclaw issue 96441 → | provider-routing | tool-specific | -2 | Ollama Cloud/OpenAI-compatible tool_calls can fail on second turn because function.arguments is sent as an object instead of a string in the 2026.6.10 line. |
| openclaw/openclaw issue 96600 → | provider-routing | runtime | -2 | Google Vertex model provider overrides via openclaw.json are not honored on 2026.6.10. |
| openclaw/openclaw issue 96665 → | discord | channel-specific | -2 | ACP thread-bound session replies can be generated but not delivered back to the Discord thread on 2026.6.10. |
| openclaw/openclaw issue 96698 → | discord | channel-specific | -2 | Discord second message can fail from a false stale-snapshot caused by skillsSnapshot hydration mismatch on 2026.6.10. |
| openclaw/openclaw issue 96716 → | mcp | tool-specific | -2 | MCP tool calls with optional null arguments fail via OpenClaw on 2026.6.10 while other MCP apps succeed. |
| openclaw/openclaw issue 96732 → | reasoning | runtime | -2 | Moonshot/Kimi reasoning_content can leak into user-visible chat output on 2026.6.10. |
| openclaw/openclaw issue 96773 → | runtime | runtime | -2 | Turn-scoped developer instructions create divergent message prefixes and break DeepSeek KV-cache reuse on 2026.6.10. |
| openclaw/openclaw issue 96586 → | voice | tool-specific | -1 | voice_call get_status returns found:false for completed calls after in-memory eviction on @openclaw/voice-call 2026.6.10. |
| openclaw/openclaw issue 96535 → | slack | channel-specific | -1 | Slack outbound replies persist new single-message delivery-mirror sessions instead of reusing the thread session through 2026.6.10. |
| openclaw/openclaw issue 96660 → | ui | other | -1 | The 2026.6.10 workspace side panel has reproducible root-path, false missing-label, and layout regressions. |
| openclaw/openclaw issue 96463 → | provider-routing | runtime | -1 | Custom OpenAI-compatible providers report usage as zero with the embedded runner on 2026.6.10. |
| openclaw/openclaw issue 96815 → | provider-routing | runtime | -3 | OpenClaw Gateway reports a false Codex subscription usage-limit on 2026.6.10 while the same Codex CLI OAuth route succeeds. |
| openclaw/openclaw issue 96820 → | plugin-install | tool-specific | -2 | ClawHub search/install API returns a Vercel security checkpoint instead of JSON for 2026.6.10 CLI flows. |
| openclaw/openclaw issue 96967 → | ui | other | -1 | TUI can display the assistant reply twice when a Telegram-triggered 2026.6.10 session reloads history after delivery. |
| openclaw/openclaw issue 96834 → | channel-specific | -1 | WhatsApp 1:1 inbound image on 2026.6.10 can wedge the main lane for about three minutes before processing. | |
| openclaw/openclaw issue 96771 → | provider-routing | runtime | -2 | Provider unification in 2026.6.10 can leave openai/gpt-5.5 routed to the wrong backend unless provider-level routing is repaired. |
| openclaw/openclaw issue 96677 → | prompt-size | runtime | -2 | 2026.6.10 still injects per-run UUIDs into the Runtime prompt line, rebusting prompt-prefix caching and inflating token use. |
| openclaw/openclaw issue 97180 → | doctor | runtime | -3 | On 2026.6.10, doctor --fix can silently add and enable the uninstalled codex plugin when openai is enabled, altering runtime routing instead of only repairing the requested plugin drift. |
| openclaw/openclaw issue 97241 → | provider-routing | runtime | -3 | Amazon Bedrock provider plugin loads on 2026.6.10 but never populates the provider registry, so Bedrock models fail at runtime as Unknown model. |
| openclaw/openclaw issue 97088 → | channel-specific | -5 | WhatsApp reconnect on 2026.6.10 can send unsolicited pairing messages to unrelated contacts, crossing an external-message trust boundary. | |
| openclaw/openclaw issue 96836 → | slack | channel-specific | -3 | Slack Socket Mode can remain connected after context overflow/compaction on 2026.6.10 while inbound replies wedge silently. |
| openclaw/openclaw issue 96835 → | exec | tool-specific | -2 | Windows exec on 2026.6.10 pops a visible cmd/PowerShell window for every command, a regression from v2026.6.8 headless behavior. |
| openclaw/openclaw issue 97047 → | usage-accounting | runtime | -2 | DeepSeek V4 usage.cost reports zero on 2026.6.10, causing Control UI spend/accounting to underreport actual model cost. |
| openclaw/openclaw issue 96910 → | tls | runtime | -3 | Auto-generated gateway TLS certs on 2026.6.10 lack subjectAltName, breaking strict-TLS CLI apps. |
| openclaw/openclaw issue 96878 → | web-search | tool-specific | -3 | web_search providers such as SearXNG/Tavily and official plugin install flows are reported broken across the 2026.6.10 line. |
| openclaw/openclaw issue 97108 → | provider-auth | runtime | -4 | Embedded/channel agent runtime can reject Anthropic subscription setup-token auth on 2026.6.10 with a false extra-usage billing error despite confirmed headroom. |
| openclaw/openclaw issue 97060 → | channel-specific | -3 | WhatsApp Native Channel connects on 2026.6.10 but registered state remains false, producing a silent channel availability failure. | |
| openclaw/openclaw issue 97176 → | provider-routing | runtime | -2 | Bedrock adaptive-thinking models on 2026.6.10 are hard-capped at 4096 output tokens and ignore model maxTokens/config overrides. |
| openclaw/openclaw issue 97186 → | acp | runtime | -4 | ACP binding sessions on 2026.6.10 can spawn a process but never deliver systemSent, leaving the session silently failed. |
| openclaw/openclaw issue 97237 → | attachments | tool-specific | -2 | Inbound PDFs/docs and other non-image attachments are exposed as unresolvable media://inbound URIs on 2026.6.10, so the model cannot read them. |
| openclaw/openclaw issue 97178 → | installer | runtime | -4 | openclaw gateway install on 2026.6.10 can add a duplicate gui-domain LaunchAgent over an existing system LaunchDaemon, causing restart-storm risk. |
| openclaw/openclaw issue 96947 → | provider-cache | runtime | -3 | OpenRouter Anthropic cacheWrite drops to zero after a 2026.6.10 upgrade, regressing conversation cache behavior. |
| openclaw/openclaw issue 96916 → | mcp | tool-specific | -3 | MCP tool calls fail on 2026.6.10 when LLMs serialize array/object parameters as strings, affecting MiMo/Ollama-style routes. |
| openclaw/openclaw issue 97287 → | feishu | channel-specific | -2 | Feishu invalid-token errors on 2026.6.10 do not trigger automatic token refresh/retry, requiring manual gateway restart to recover. |
| openclaw/openclaw issue 97319 → | exec | tool-specific | -1 | exec failure formatting on 2026.6.10 makes framework failure labels look like agent-typed shell commands, confusing operators during failures. |
| openclaw/openclaw issue 97335 → | cron-runtime | runtime | -4 | Cron-triggered isolated sessions on 2026.6.10 can fail LLM requests even when the same fallback model works in normal sessions. |
| openclaw/openclaw issue 97347 → | cron-runtime | runtime | -3 | Isolated cron agentTurn on 2026.6.10 can lose exec capability when toolsAllow narrows to exec/bash, breaking allowed automation paths. |
| openclaw/openclaw issue 97435 → | line | channel-specific | -3 | LINE inbound events on 2026.6.10 were delayed roughly 1.5–2 hours before the agent run and later drained, causing stale channel replies. |
| openclaw/openclaw issue 97457 → | webchat | runtime | -4 | WebChat RPC abort after compaction on 2026.6.10 can lose the original session context and reroute into restart-recovery/new-session state. |
| openclaw/openclaw issue 95323 → | slack | channel-specific | -2 | Slack DM turns on a clean 2026.6.10 build can render the inbound system event twice, duplicating runtime context into the model-facing turn. |
| openclaw/openclaw issue 97055 → | memory | runtime | -3 | memorySearch.provider config on 2026.6.10 can be ignored, silently routing embeddings to the wrong Ollama instance. |
| openclaw/openclaw issue 97048 → | provider-routing | runtime | -2 | Model catalog validation on 2026.6.10 rejects audio/video modalities produced by OpenClaw catalog fetch, dropping multimodal models from routing. |
| openclaw/openclaw issue 99128 → | channel-config | channel-specific | -3 | Docker image 2026.6.10 hides multi-account configuration for Telegram, Feishu, and WeCom despite documented support. |
| openclaw/openclaw issue 99185 → | plugin-system | runtime | -4 | Installing a managed npm plugin can break resolution of every workspace plugin loaded via plugins.load.paths on 2026.6.10. |
| openclaw/openclaw issue 98378 → | tools | kernel | -4 | Switching model within the same session can break all tool calls on 2026.6.10. |
| openclaw/openclaw issue 98081 → | discord | channel-specific | -3 | Discord turns can be missed or finish silently across gateway restart/recovery on 2026.6.10. |
| openclaw/openclaw issue 100329 → | mcp | tool-specific | -2 | HTTP MCP loopback strips image/audio/resource fields on v2026.6.10 by normalizing non-text tool content to text-only blocks. |
| openclaw/openclaw issue 98565 → | config-migration | runtime | -4 | Container image upgrade from v2026.6.10 to v2026.6.11 can skip upgrade migrations before gateway startup, leaving stale version metadata and pending repair. |
| openclaw/openclaw issue 103287 → | session-state | kernel | -5 | Queued inbound iMessage can be processed against stale session state on v2026.6.10, producing contradictory replies seconds apart. |
| openclaw/openclaw issue 106080 → | usage-accounting | runtime | -2 | Model cost accounting reports $0 because model_capability_cache never populates, reproduced on 2026.6.10. |
| openclaw/openclaw issue 105528 → | tools | runtime | -4 | exec/read tools can silently return empty output on Windows across the 2026.6.x release line. |