openclaw - ✅(Solved) Fix Azure AI Foundry Responses API: `type: "message"` missing from input items causes 400 error [2 pull requests, 1 comments, 2 participants]
ON THIS PAGE
Recommended Tools
×6Utilities matched from this issue’s tags and category — try them while you read without losing context.
GitHub issue graph ai analysis
Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.
The report is written in English Markdown for sharing and archival.
Helpful · Quick feedback
OpenClaw's openai-responses and azure-openai-responses transports both fail against Azure AI Foundry project endpoints. The root cause is that convertResponsesMessages() does not include type: "message" on user/developer input items, which Azure AI Foundry's Responses API requires. OpenAI's direct API infers the type when absent; Azure does not.
A secondary issue prevents using api: "azure-openai-responses" as a workaround: the AzureOpenAI SDK injects an api-version query parameter that Foundry project endpoints reject.
Root Cause
OpenClaw's openai-responses and azure-openai-responses transports both fail against Azure AI Foundry project endpoints. The root cause is that convertResponsesMessages() does not include type: "message" on user/developer input items, which Azure AI Foundry's Responses API requires. OpenAI's direct API infers the type when absent; Azure does not.
Fix Action
Fix / Workaround
A secondary issue prevents using api: "azure-openai-responses" as a workaround: the AzureOpenAI SDK injects an api-version query parameter that Foundry project endpoints reject.
400 Invalid value: ''. Supported values are: 'apply_patch_call', ..., 'message', 'reasoning', ...
param: input[1]
code: invalid_valueVerified Workaround
PR fix notes
PR #74163: WORKING: All Microsoft Issues and PRs (refresh)
- Repository: openclaw/openclaw
- Author: BradGroux
- State: open | merged: False
- Link: https://github.com/openclaw/openclaw/pull/74163
Description (problem / solution / changelog)
Microsoft Ecosystem Issues & PRs Tracker
Purpose: Living checklist for maintainers to track all open Microsoft-related issues and PRs (Teams, Windows, WSL, Azure, M365/SharePoint).
How to use:
- Mark items resolved by editing this PR body and changing
[ ]to[x]- Claim items by adding your GitHub handle to the
Assigneecolumn- Priority guide: P0 = crash/blocker/security, P1 = significant bug/regression, P2 = minor bug/enhancement, P3 = nice-to-have/stale
- Items marked (stale) have been flagged by the stale bot due to inactivity
Last updated: 2026-05-20 (closed #82873 as superseded; refreshed Microsoft tracker scope)
Summary
| Category | Issues | PRs | Total | Closed | Remaining |
|---|---|---|---|---|---|
| MS Teams (channel plugin) | 6 | 44 | 50 | 8 | 42 |
| Windows platform | 67 | 38 | 105 | 17 | 88 |
| WSL | 7 | 4 | 11 | 1 | 10 |
| Azure | 8 | 6 | 14 | 2 | 12 |
| SharePoint / M365 | 0 | 0 | 0 | 0 | 0 |
| Total | 88 | 92 | 180 | 28 | 152 |
1. MS Teams Channel Plugin — Issues
Bugs / Crashes
| Resolved? | Priority | # | Title | Labels | Assignee |
|---|---|---|---|---|---|
| [ ] | P1 | #67177 | [msteams] Inbound file attachments silently fail in DMs — file.download.info downloadUrl not rewritten to Graph shares endpoint | ||
| [ ] | P1 | #65329 | bug(msteams): DM inline images and file attachments silently dropped | ||
| [ ] | P1 | #62765 | msteams dmPolicy=pairing silently drops unpaired senders with HTTP 200, no log line, no auto-reply | ||
| [ ] | P2 | #42099 | fix(plugins): false-positive duplicate plugin ID warning on gateway start (msteams) | P2 clawsweeper:no-new-fix-pr clawsweeper:needs-product-decision clawsweeper:source-repro clawsweeper:linked-pr-open issue-rating: 🦞 diamond lobster |
Feature Requests
| Resolved? | Priority | # | Title | Labels | Assignee |
|---|---|---|---|---|---|
| [ ] | P2 | #81084 | [Feature]: MSTeams channel-bound agents need opt-out from per-thread sessions |
2. MS Teams Channel Plugin — PRs
| Resolved? | Priority | # | Title | Size | Assignee |
|---|---|---|---|---|---|
| [ ] | P0 | #81729 | Remove system event trust metadata | S | |
| [ ] | P0 | #81402 | refactor: move runtime state to SQLite | XL | |
| [ ] | P0 | #79972 | feat: add SQLite transcript frontier and delta API | XL | |
| [ ] | P0 | #79970 | feat: expose durable session id match selection helpers | XL | |
| [ ] | P0 | #79925 | feat: context-pressure-aware continuation (continue_work / continue_delegate / request_compaction) | XL | |
| [ ] | P0 | #63827 | fix(security): preserve dmPolicy settings during wizard runs | XL | |
| [ ] | P0 | #60643 | feat(agents): cognitive processing scaffolding and structured memory prompt | S | |
| [ ] | P0 | #57511 | feat(msteams): Teams live voice support with .NET media worker | XL | |
| [ ] | P0 | #55485 | Config: plumb opt-in SSRF policy for web fetch, citation redirects, and remote media | L | |
| [ ] | P0 | #50875 | feat: add before_identity_resolve plugin hook | M | |
| [ ] | P0 | #43190 | MS Teams: add channel archive persistence and deleted-channel cleanup | XL | |
| [ ] | P0 | #37656 | feat: load workspace .env per-agent at exec time | S | |
| [ ] | P1 | #78172 | feat(tts): add skipEmojiSymbols option to prevent TTS from reading emoji/symbols | M | |
| [ ] | P1 | #77784 | Add Teams delegated auth for plugin tools | XL | |
| [ ] | P1 | #76262 | fix(msteams): rebase TeamsSDK patterns to simplify Teams Integration | XL | @BradGroux |
| [ ] | P1 | #75043 | Add provider-aware automatic TTS emotion mapping | XL | |
| [x] | P2 | #83973 | fix(msteams): mark external system events as non-owner | S | @LaPhilosophie |
| [ ] | P2 | #82354 | fix(msteams): emit message:sent hook on reply delivery | M | |
| [ ] | P2 | #79609 | Show session cleanup dry-run counts by label | L | |
| [ ] | P2 | #79185 | fix(tts/xiaomi): support Token Plan TTS endpoint | S | |
| [ ] | P2 | #78839 | [codex] Add Teams member-info action gate | S | |
| [ ] | P2 | #77921 | feat(inworld): default to inworld-tts-2 (Realtime TTS-2) | XS | |
| [ ] | P2 | #76560 | feat(plugins): allow community plugins to use openKeyedStore with man… | L | @vincentkoc |
| [ ] | P2 | #70287 | fix(msteams): drop unsupported $search on msteams:search (AI-assisted) | M | |
| [ ] | P2 | #69428 | fix(msteams): paginate thread replies and keep recent context | S | |
| [ ] | P2 | #69417 | fix(mcp): allow SecretRef values in mcp.servers env and headers [AI-assisted] | XL | |
| [ ] | P2 | #67761 | fix: remove truncated preview from inbound system events | XS | |
| [ ] | P2 | #67460 | feat(mention-gating): suppress always-on agent when another agent is explicitly mentioned | M | |
| [ ] | P2 | #67174 | Teams: support separate graphTenantId for cross-tenant Graph API access | M | |
| [ ] | P2 | #66327 | feat(msteams): implement sendPayload for interactive approval cards | M | |
| [ ] | P2 | #64503 | fix(msteams): forward messageBack card actions (Action.Submit) to agent (#60952) | S | |
| [ ] | P2 | #63347 | feat(msteams): support webhook host binding | S | |
| [ ] | P2 | #60630 | fix(ci): Windows task tests and Telegram setup promotion surface | L | |
| [ ] | P2 | #59986 | refactor(plugins): add lane-oriented channel interface | XL | |
| [ ] | P2 | #59294 | fix(msteams): isolate thread sessions, outbound targeting, and attachment resolution | L | |
| [ ] | P2 | #57366 | fix(msteams): extract emoji unicode from Teams CDN img tags instead of treating as image attachments | S | |
| [ ] | P2 | #57364 | fix(msteams): delete FileConsentCard after user accepts, declines, or upload expires | S | |
| [ ] | P2 | #55828 | feat(msteams): add native plugin interactivity parity | XL |
3. Windows Platform — Issues
Bugs / Crashes
| Resolved? | Priority | # | Title | Labels | Assignee |
|---|---|---|---|---|---|
| [ ] | P0 | #48780 | [Bug]: [Windows] exec() and read() commands corrupted with </arg_value>> suffix | bug bug:behavior P1 clawsweeper:no-new-fix-pr clawsweeper:needs-security-review clawsweeper:source-repro +4 | |
| [ ] | P1 | #84001 | Windows: openclaw status / status --json hangs in 2026.5.18 while status --all succeeds | P2 clawsweeper:no-new-fix-pr clawsweeper:needs-maintainer-review clawsweeper:needs-live-repro impact:crash-loop issue-rating: 🐚 platinum hermit | |
| [ ] | P1 | #83943 | [Bug]: Session resource loader grows unbounded across warm turns — 5.x regression vs 4.23 baseline (Windows + Feishu + MiniMax OAuth) | bug | |
| [ ] | P1 | #83277 | WhatsApp channel: "web login provider is not available" on Windows despite wacli installed and authenticated | bug bug:behavior P2 clawsweeper:fix-shape-clear clawsweeper:queueable-fix clawsweeper:source-repro +1 | |
| [ ] | P1 | #80416 | [Bug] core-plugin-tools ~3.5s overhead on every embedded run persists after #75520 fix — Windows + Node 24 + isolated cron jobs | P2 clawsweeper:no-new-fix-pr clawsweeper:needs-maintainer-review clawsweeper:needs-live-repro impact:crash-loop | |
| [ ] | P1 | #80344 | [Bug]: Discord voice /vc join fails on Windows with AggregateError + gateway heartbeat timeout / event loop starvation | bug bug:crash | |
| [ ] | P1 | #79437 | Prebuilt node-llama-cpp Windows binaries crash (0xC0000005) on Intel Alder Lake-N (N95) — qmd LLM half unusable | ||
| [ ] | P1 | #77443 | [Bug]: WhatsApp event loop blocked (eventLoopDelayMaxMs=12088ms) on first inbound message — 2026.5.3-1 Windows | bug regression | |
| [ ] | P1 | #74378 | [Bug]: OpenClaw CLI commands remain alive as node.exe processes after execution on Windows | bug regression | |
| [ ] | P1 | #71865 | Auth login blocked by size-drop guard when openclaw.json was created by PowerShell (verbose/BOM format) | ||
| [ ] | P1 | #71699 | [Bug]: Gateway hard-crashes with 0xC0000409 (STATUS_STACK_BUFFER_OVERRUN) on Windows during Mattermost streaming reply; auto-respawn frequently wedges | ||
| [ ] | P1 | #70788 | fix(windows): suppress startup-folder cmd window flash via wscript silent launcher | ||
| [ ] | P1 | #68493 | [Bug]: Editing openclaw.json while gateway is running triggers hot-reload crash loop on Windows (stale lock file + EADDRINUSE) | @vincentkoc | |
| [ ] | P1 | #67035 | [Bug]: 2026.4.14 Windows chat UI regression: input text swallowed, streamed replies often invisible until refresh, typing indicator flashes then blanks | ||
| [ ] | P1 | #63257 | Windows Gateway Feishu API timeout 30s at startup | ||
| [ ] | P1 | #62099 | EPERM on auth-profiles.json causes full gateway failure cascade (Windows) | P1 clawsweeper:no-new-fix-pr clawsweeper:source-repro clawsweeper:linked-pr-open impact:auth-provider impact:crash-loop +1 | |
| [ ] | P1 | #62055 | Windows: CLI crashes with stack overflow / heap OOM on v2026.4.5 (large ESM module graph exceeds V8 default stack) | P1 clawsweeper:needs-live-repro impact:crash-loop issue-rating: 🐚 platinum hermit | |
| [ ] | P1 | #59362 | [Bug]: Windows: exec tool causes console window flash when spawning commands | bug regression P1 clawsweeper:no-new-fix-pr clawsweeper:fix-shape-clear clawsweeper:needs-maintainer-review +3 | |
| [ ] | P1 | #59281 | [Bug]: Windows plugin TS source-loading via jiti is pathologically slow in real production call sites | bug bug:behavior P2 clawsweeper:no-new-fix-pr clawsweeper:needs-maintainer-review clawsweeper:needs-live-repro +2 | |
| [ ] | P1 | #54669 | [Field Report] Chrome 136+ binds CDP to [::1] (IPv6) on Windows — portproxy v4tov4 breaks silently | P1 clawsweeper:fix-shape-clear clawsweeper:queueable-fix clawsweeper:source-repro issue-rating: 🦞 diamond lobster | |
| [ ] | P1 | #44559 | [Bug]: Windows: Gateway 关闭 PowerShell 窗口后断连 | bug bug:behavior P2 clawsweeper:no-new-fix-pr clawsweeper:fix-shape-clear clawsweeper:needs-maintainer-review +4 | |
| [ ] | P2 | #83890 | Windows restart script builds ProcessStartInfo.Arguments via string concatenation without quoting embedded double-quotes | ||
| [ ] | P2 | #82594 | [Bug]: openclaw onboard extremely slow on Windows during model loading | ||
| [ ] | P2 | #81673 | Build official OpenClaw companion downloads for Windows and Linux | ||
| [ ] | P2 | #80650 | [Bug]: [Bug] openclaw backup create 在Windows上失败(退出代码255) | bug | |
| [ ] | P2 | #79899 | DefaultResourceLoader.reload() blocks event loop for 12-15s on Windows due to synchronous filesystem scanning | P2 clawsweeper:no-new-fix-pr clawsweeper:fix-shape-clear clawsweeper:needs-maintainer-review clawsweeper:needs-product-decision clawsweeper:needs-live-repro +1 | |
| [ ] | P2 | #79099 | Windows gateway probe still reports unreachable while gateway health is OK on 2026.5.6 | ||
| [ ] | P2 | #78640 | fix(memory): EPERM on Windows persists after 64187 retry — needs copyFile/unlink fallback (was in closed PR 71611) | ||
| [ ] | P2 | #78435 | [Bug]: channels.slack.start-account phase blocks event loop 5+ minutes while a model_call is in flight (Windows, 2026.5.4) | ||
| [ ] | P2 | #77730 | [Bug]: file-transfer plugin nodeHostCommands not advertised by Windows node host on live handshake (2026.5.3-1) | ||
| [ ] | P2 | #76884 | [Bug]: OpenClaw on native Windows getting notably slower and slower with each new version??? | bug | |
| [ ] | P2 | #76702 | Windows + Feishu DM becomes very slow after upgrade to 2026.5.2; latency appears in agent/session processing, likely amplified by large session context | ||
| [ ] | P2 | #76553 | [Bug]: Windows: Claude Code not detected by OpenClaw, Gateway in restart loop after PATH workaround | bug bug:behavior | |
| [ ] | P2 | #73859 | [Bug]: Built-in plugins (minimax, google, talk-voice) fail with RangeError: Maximum call stack size exceeded on Windows | ||
| [ ] | P2 | #73059 | [Bug]: Windows linked source install can skip Control UI auto-build through junction-launched scripts/ui.js | ||
| [ ] | P2 | #72922 | [Bug]: Sluggish response time and unstable Web GUI and CLI on Windows Server 2022 | bug | |
| [ ] | P2 | #71717 | exec tool returns EPERM on Windows, all commands fail | bug | |
| [ ] | P2 | #70451 | [Bug]: CLI hooks enable times out / SIGKILL on Windows | ||
| [ ] | P2 | #66746 | [Bug] Windows memory indexing falls back to FTS-only in 2026.4.14 even though direct node:sqlite + sqlite-vec works | ||
| [ ] | P2 | #66479 | Windows: skill not discovered due to UTF-8 BOM injected by PowerShell WriteAllText | ||
| [ ] | P2 | #64443 | OpenClaw chat interface causes very high WindowServer CPU on Intel Retina iMac | ||
| [ ] | P2 | #64253 | Gateway becomes unresponsive under subagent load on Windows - completion announcements timeout | ||
| [ ] | P2 | #63491 | [Bug]: Windows Scheduled Task gateway restart/health becomes inconsistent after ready | ||
| [ ] | P2 | #58433 | [Bug]: [Windows] Path character loss bug - "system" becomes "ystem" in file paths | bug bug:behavior P2 clawsweeper:no-new-fix-pr clawsweeper:needs-maintainer-review clawsweeper:needs-info +1 | |
| [ ] | P2 | #58139 | [Bug]: memory-lancedb plugin fails with Windows Docker bind mount | bug bug:behavior P2 clawsweeper:no-new-fix-pr clawsweeper:source-repro clawsweeper:linked-pr-open +2 | |
| [ ] | P2 | #56284 | Windows: gateway restart does not wait for active tasks and loses session state | P1 clawsweeper:no-new-fix-pr clawsweeper:fix-shape-clear clawsweeper:needs-maintainer-review clawsweeper:needs-product-decision clawsweeper:needs-live-repro +4 | |
| [ ] | P2 | #56106 | Transcript JSONL encoding corrupted on Windows (GBK/UTF-8 mix) | P2 clawsweeper:no-new-fix-pr clawsweeper:needs-maintainer-review clawsweeper:needs-info impact:session-state impact:data-loss +1 | |
| [ ] | P2 | #44293 | Make pnpm check:docs work in native PowerShell | P2 clawsweeper:no-new-fix-pr clawsweeper:source-repro clawsweeper:linked-pr-open issue-rating: 🦞 diamond lobster | |
| [ ] | P2 | #44291 | Add native PowerShell smoke coverage for contributor commands | P2 clawsweeper:no-new-fix-pr clawsweeper:fix-shape-clear clawsweeper:needs-maintainer-review clawsweeper:needs-product-decision issue-rating: 🌊 off-meta tidepool | |
| [ ] | P2 | #40694 | Browser-opened temporary tabs/windows should close automatically after task completion | P2 clawsweeper:no-new-fix-pr clawsweeper:fix-shape-clear clawsweeper:needs-maintainer-review clawsweeper:needs-product-decision clawsweeper:source-repro +2 | |
| [ ] | P2 | #40540 | [Bug]: openclaw update command fails with EBUSY error on Windows | bug bug:behavior P1 clawsweeper:source-repro issue-rating: 🦞 diamond lobster |
Feature Requests
| Resolved? | Priority | # | Title | Labels | Assignee |
|---|---|---|---|---|---|
| [ ] | P0 | #75 | Linux/Windows Clawdbot Apps | enhancement help wanted P2 clawsweeper:no-new-fix-pr clawsweeper:needs-maintainer-review clawsweeper:needs-product-decision +4 | |
| [ ] | P1 | #82125 | [Feature] Windows: crash auto-restart parity with systemd Restart=always / launchd KeepAlive | ||
| [ ] | P2 | #72595 | [Feature]: Feishu channel needs per-channel proxy bypass for mixed Windows proxy setups | enhancement | |
| [ ] | P2 | #57775 | Windows headless node host supports exec approvals via CLI, but nodes describe / Control UI do not advertise system.execApprovals.get/set | P2 clawsweeper:fix-shape-clear clawsweeper:queueable-fix clawsweeper:source-repro issue-rating: 🦞 diamond lobster | |
| [ ] | P2 | #46590 | Feature Request: Add cron field to Agent configuration for Agent-owned scheduled tasks | P2 clawsweeper:no-new-fix-pr clawsweeper:fix-shape-clear clawsweeper:needs-maintainer-review clawsweeper:needs-product-decision issue-rating: 🌊 off-meta tidepool | |
| [ ] | P2 | #18985 | [Feature]: Supports Windows 11 MSYS environment and Fishshell. | enhancement P2 clawsweeper:no-new-fix-pr clawsweeper:fix-shape-clear clawsweeper:needs-maintainer-review clawsweeper:needs-product-decision +2 | |
| [ ] | P2 | #7057 | Flaky tests on Windows/WSL: timeouts and ENOENT in pi-tools workspace-paths & safe-bins | enhancement P2 clawsweeper:no-new-fix-pr clawsweeper:needs-maintainer-review clawsweeper:needs-live-repro issue-rating: 🐚 platinum hermit |
4. Windows Platform — PRs
| Resolved? | Priority | # | Title | Size | Assignee |
|---|---|---|---|---|---|
| [ ] | P0 | #81443 | fix: resolve QMD Windows shims and guard image URL downloads | M | |
| [ ] | P0 | #50116 | fix: handle Windows-style session paths when running on POSIX | XS | |
| [ ] | P0 | #46956 | feat(cli): add trust windows for time-bounded exec approval | XL | |
| [ ] | P0 | #44215 | fix(path): add Windows PATH bootstrap dirs | S | |
| [ ] | P0 | #38932 | docs(gateway): add Windows no-Docker hardening fallback guide | XS | |
| [ ] | P2 | #81330 | fix(windows): suppress persistent cmd window from scheduled-task node launch | XS | |
| [ ] | P2 | #80683 | fix(memory-lancedb): add retry mechanism for Windows Docker bind mount sync delays | S | |
| [ ] | P2 | #79694 | fix(update): hide post-core update and completion cache child windows on Windows | XS | |
| [ ] | P2 | #76245 | [codex] Fallback when Windows gateway task exits early | S | |
| [ ] | P2 | #75649 | fix(windows): preserve staged update handoff | XL | |
| [ ] | P2 | #74425 | fix: ensure CLI processes exit after command completion on Windows | S | |
| [ ] | P2 | #73889 | fix(cli): stabilize Windows scheduled-task restart health after ready | S | |
| [ ] | P2 | #73751 | fix(exec): decode Windows command output with codepage-aware streaming | M | |
| [ ] | P2 | #70762 | refactor(agents): share hook history windows | XL | @vincentkoc |
| [ ] | P2 | #69059 | fix: retry sqlite-vec load without .dll suffix on Windows | S | |
| [ ] | P2 | #68819 | fix: resolve Windows .cmd shims to underlying .exe before spawn | M | |
| [ ] | P2 | #68725 | feat(amazon-bedrock-mantle): add known context windows for open-weight Mantle models | S | |
| [ ] | P2 | #68149 | feat(daemon): use PowerShell Register-ScheduledTask for Windows auto-start | M | |
| [ ] | P2 | #67655 | fix(exec): fail closed on Windows shell wrappers in allowlist mode | XS | |
| [ ] | P2 | #64110 | feat: Deleting scheduled tasks also clears tasks in the queue. | L | |
| [ ] | P2 | #63651 | fix: remove duplicate restart message on Windows (schtasks) | S | |
| [ ] | P2 | #59705 | [codex] improve parallels windows smoke logging | M | |
| [ ] | P2 | #59013 | fix: tolerate EPERM in session write-lock on Windows | S | |
| [ ] | P2 | #51486 | fix(daemon): query Windows task runtime directly | S | |
| [ ] | P2 | #50136 | fix(windows): stabilize gateway restart and avoid false stale cleanup [AI-assisted] | M | |
| [ ] | P2 | #48887 | Fix/docs format check windows clean | M | |
| [ ] | P2 | #48130 | fix: correct Windows Chrome executable path extraction regex | XS | |
| [ ] | P2 | #45380 | Make env-prefixed npm scripts work on Windows | S | |
| [ ] | P2 | #44228 | fix(reply): normalize Windows media paths for dedupe | XS | |
| [ ] | P2 | #39644 | fix(windows): PowerShell completion install and time-format detection | S |
5. WSL (Windows Subsystem for Linux) — Issues
Bugs / Crashes
| Resolved? | Priority | # | Title | Labels | Assignee |
|---|---|---|---|---|---|
| [ ] | P1 | #68966 | [Bug]: [WSL] openclaw browser command terminated by SIGKILL causing timeout | bug bug:crash | |
| [ ] | P1 | #61616 | [Bug]: [WSL2] Global 30-min gateway stall (:29/:59) affects Telegram + Control UI | bug P1 clawsweeper:no-new-fix-pr clawsweeper:needs-maintainer-review clawsweeper:needs-product-decision clawsweeper:needs-info +3 | |
| [ ] | P1 | #59209 | Misleading CDP "Empty reply from server" in WSL2 caused by portproxy self-loop (svchost/iphlpsvc), not Chrome | bug regression P2 clawsweeper:fix-shape-clear clawsweeper:queueable-fix clawsweeper:source-repro +1 | |
| [ ] | P2 | #81873 | Bug: browser user profile (existing-session / Chrome MCP) ignores cdpUrl config in WSL environment | ||
| [ ] | P2 | #80336 | [Bug]: placeholder.openclaw.cloud unreachable on WSL2 with custom gateway port | bug bug:behavior | |
| [ ] | P2 | #73602 | [Bug]: WhatsApp flaps and Telegram polling stalls on WSL2 in 2026.4.26 | ||
| [ ] | P2 | #73152 | Docs/doctor request: clarify gateway reachability for OrbStack/WSL/VM/Tailscale setups |
Feature Requests
No currently open items found.
6. WSL (Windows Subsystem for Linux) — PRs
| Resolved? | Priority | # | Title | Size | Assignee |
|---|---|---|---|---|---|
| [ ] | P1 | #46698 | fix(auth): fix GitHub device flow polling and add --wait flag for WSL… | S | |
| [ ] | P2 | #68400 | daemon/systemd: distinguish WSL user D-Bus socket missing from missing systemctl | S | |
| [ ] | P2 | #58853 | feat(doctor): add WSL environment diagnostics check [AI-assisted] | L |
7. Azure (Provider / Infrastructure) — Issues
Bugs / Crashes
| Resolved? | Priority | # | Title | Labels | Assignee |
|---|---|---|---|---|---|
| [ ] | P1 | #84109 | Azure AI Foundry Responses API: type: "message" missing from input items causes 400 error | P2 clawsweeper:fix-shape-clear clawsweeper:queueable-fix clawsweeper:source-repro impact:auth-provider issue-rating: 🦞 diamond lobster | |
| [ ] | P1 | #60546 | [Bug]: microsoft-foundry provider selects Claude deployments but routes them through OpenAI Foundry endpoints | P2 clawsweeper:no-new-fix-pr clawsweeper:source-repro clawsweeper:linked-pr-open impact:auth-provider issue-rating: 🦞 diamond lobster | |
| [ ] | P1 | #48793 | feat: centralized PluginResourceManager interface for consistent async cleanup across all channel plugins | P2 clawsweeper:no-new-fix-pr clawsweeper:fix-shape-clear clawsweeper:needs-maintainer-review clawsweeper:needs-product-decision impact:crash-loop +1 | |
| [ ] | P2 | #80926 | Azure OpenAI Responses stalls before first event when memory tools are exposed | maintainer | |
| [ ] | P2 | #79570 | openai-responses adapter is unusable against Azure OpenAI: every turn returns a synthetic 0-token refusal (openai-completions works) | ||
| [ ] | P2 | #48788 | feat: centralized filename encoding utility for multi-encoding Content-Disposition handling | P2 clawsweeper:no-new-fix-pr clawsweeper:needs-product-decision impact:data-loss issue-rating: 🌊 off-meta tidepool |
Feature Requests
| Resolved? | Priority | # | Title | Labels | Assignee |
|---|---|---|---|---|---|
| [ ] | P2 | #71058 | [Feature]: Support for multiple Azure/Teams bots on a single Openclaw Gateway | enhancement |
8. Azure (Provider / Infrastructure) — PRs
| Resolved? | Priority | # | Title | Size | Assignee |
|---|---|---|---|---|---|
| [ ] | P1 | #55395 | fix: centralize plugin command auth requirements | M | |
| [ ] | P1 | #47285 | feat(memory-lancedb): native Azure OpenAI support | S | |
| [ ] | P1 | #47181 | feat: add Azure Claude (AI Foundry) onboarding path | L | |
| [ ] | P2 | #70922 | refactor(whatsapp): centralize account policy | L | |
| [ ] | P2 | #55211 | fix: prevent re-entrant loop in internal hook trigger | S |
9. Microsoft 365 / SharePoint — Issues
Bugs / Crashes
No currently open items found.
Feature Requests
No currently open items found.
10. Microsoft 365 / SharePoint — PRs
No currently open items found.
Appendix: P0 Blockers (Start Here)
| Category | Type | Priority | # | Title |
|---|---|---|---|---|
| MS Teams (channel plugin) | pr | P0 | #81729 | Remove system event trust metadata |
| MS Teams (channel plugin) | pr | P0 | #81402 | refactor: move runtime state to SQLite |
| MS Teams (channel plugin) | pr | P0 | #79972 | feat: add SQLite transcript frontier and delta API |
| MS Teams (channel plugin) | pr | P0 | #79970 | feat: expose durable session id match selection helpers |
| MS Teams (channel plugin) | pr | P0 | #79925 | feat: context-pressure-aware continuation (continue_work / continue_delegate / request_compaction) |
| MS Teams (channel plugin) | pr | P0 | #63827 | fix(security): preserve dmPolicy settings during wizard runs |
| MS Teams (channel plugin) | pr | P0 | #60643 | feat(agents): cognitive processing scaffolding and structured memory prompt |
| MS Teams (channel plugin) | pr | P0 | #57511 | feat(msteams): Teams live voice support with .NET media worker |
| MS Teams (channel plugin) | pr | P0 | #55485 | Config: plumb opt-in SSRF policy for web fetch, citation redirects, and remote media |
| MS Teams (channel plugin) | pr | P0 | #50875 | feat: add before_identity_resolve plugin hook |
| MS Teams (channel plugin) | pr | P0 | #43190 | MS Teams: add channel archive persistence and deleted-channel cleanup |
| MS Teams (channel plugin) | pr | P0 | #37656 | feat: load workspace .env per-agent at exec time |
| Windows platform | issue | P0 | #48780 | [Bug]: [Windows] exec() and read() commands corrupted with </arg_value>> suffix |
| Windows platform | issue | P0 | #75 | Linux/Windows Clawdbot Apps |
| Windows platform | pr | P0 | #81443 | fix: resolve QMD Windows shims and guard image URL downloads |
| Windows platform | pr | P0 | #50116 | fix: handle Windows-style session paths when running on POSIX |
| Windows platform | pr | P0 | #46956 | feat(cli): add trust windows for time-bounded exec approval |
| Windows platform | pr | P0 | #44215 | fix(path): add Windows PATH bootstrap dirs |
| Windows platform | pr | P0 | #38932 | docs(gateway): add Windows no-Docker hardening fallback guide |
Appendix: High-Priority Bugs / Regressions
| Category | Type | Priority | # | Title |
|---|---|---|---|---|
| MS Teams (channel plugin) | issue | P1 | #67177 | [msteams] Inbound file attachments silently fail in DMs — file.download.info downloadUrl not rewritten to Graph shares endpoint |
| MS Teams (channel plugin) | issue | P1 | #65329 | bug(msteams): DM inline images and file attachments silently dropped |
| MS Teams (channel plugin) | issue | P1 | #62765 | msteams dmPolicy=pairing silently drops unpaired senders with HTTP 200, no log line, no auto-reply |
| MS Teams (channel plugin) | pr | P1 | #78172 | feat(tts): add skipEmojiSymbols option to prevent TTS from reading emoji/symbols |
| MS Teams (channel plugin) | pr | P1 | #77784 | Add Teams delegated auth for plugin tools |
| MS Teams (channel plugin) | pr | P1 | #76262 | fix(msteams): rebase TeamsSDK patterns to simplify Teams Integration |
| MS Teams (channel plugin) | pr | P1 | #75043 | Add provider-aware automatic TTS emotion mapping |
| Windows platform | issue | P1 | #84001 | Windows: openclaw status / status --json hangs in 2026.5.18 while status --all succeeds |
| Windows platform | issue | P1 | #83943 | [Bug]: Session resource loader grows unbounded across warm turns — 5.x regression vs 4.23 baseline (Windows + Feishu + MiniMax OAuth) |
| Windows platform | issue | P1 | #83277 | WhatsApp channel: "web login provider is not available" on Windows despite wacli installed and authenticated |
| Windows platform | issue | P1 | #82125 | [Feature] Windows: crash auto-restart parity with systemd Restart=always / launchd KeepAlive |
| Windows platform | issue | P1 | #80416 | [Bug] core-plugin-tools ~3.5s overhead on every embedded run persists after #75520 fix — Windows + Node 24 + isolated cron jobs |
| Windows platform | issue | P1 | #80344 | [Bug]: Discord voice /vc join fails on Windows with AggregateError + gateway heartbeat timeout / event loop starvation |
| Windows platform | issue | P1 | #79437 | Prebuilt node-llama-cpp Windows binaries crash (0xC0000005) on Intel Alder Lake-N (N95) — qmd LLM half unusable |
| Windows platform | issue | P1 | #77443 | [Bug]: WhatsApp event loop blocked (eventLoopDelayMaxMs=12088ms) on first inbound message — 2026.5.3-1 Windows |
| Windows platform | issue | P1 | #74378 | [Bug]: OpenClaw CLI commands remain alive as node.exe processes after execution on Windows |
| Windows platform | issue | P1 | #71865 | Auth login blocked by size-drop guard when openclaw.json was created by PowerShell (verbose/BOM format) |
| Windows platform | issue | P1 | #71699 | [Bug]: Gateway hard-crashes with 0xC0000409 (STATUS_STACK_BUFFER_OVERRUN) on Windows during Mattermost streaming reply; auto-respawn frequently wedges |
| Windows platform | issue | P1 | #70788 | fix(windows): suppress startup-folder cmd window flash via wscript silent launcher |
| Windows platform | issue | P1 | #68493 | [Bug]: Editing openclaw.json while gateway is running triggers hot-reload crash loop on Windows (stale lock file + EADDRINUSE) |
| Windows platform | issue | P1 | #67035 | [Bug]: 2026.4.14 Windows chat UI regression: input text swallowed, streamed replies often invisible until refresh, typing indicator flashes then blanks |
| Windows platform | issue | P1 | #63257 | Windows Gateway Feishu API timeout 30s at startup |
| Windows platform | issue | P1 | #62099 | EPERM on auth-profiles.json causes full gateway failure cascade (Windows) |
| Windows platform | issue | P1 | #62055 | Windows: CLI crashes with stack overflow / heap OOM on v2026.4.5 (large ESM module graph exceeds V8 default stack) |
| Windows platform | issue | P1 | #59362 | [Bug]: Windows: exec tool causes console window flash when spawning commands |
| Windows platform | issue | P1 | #59281 | [Bug]: Windows plugin TS source-loading via jiti is pathologically slow in real production call sites |
| Windows platform | issue | P1 | #54669 | [Field Report] Chrome 136+ binds CDP to [::1] (IPv6) on Windows — portproxy v4tov4 breaks silently |
| Windows platform | issue | P1 | #44559 | [Bug]: Windows: Gateway 关闭 PowerShell 窗口后断连 |
| WSL | issue | P1 | #68966 | [Bug]: [WSL] openclaw browser command terminated by SIGKILL causing timeout |
| WSL | issue | P1 | #61616 | [Bug]: [WSL2] Global 30-min gateway stall (:29/:59) affects Telegram + Control UI |
| WSL | issue | P1 | #59209 | Misleading CDP "Empty reply from server" in WSL2 caused by portproxy self-loop (svchost/iphlpsvc), not Chrome |
| WSL | pr | P1 | #46698 | fix(auth): fix GitHub device flow polling and add --wait flag for WSL… |
| Azure | issue | P1 | #84109 | Azure AI Foundry Responses API: type: "message" missing from input items causes 400 error |
| Azure | issue | P1 | #60546 | [Bug]: microsoft-foundry provider selects Claude deployments but routes them through OpenAI Foundry endpoints |
| Azure | issue | P1 | #48793 | feat: centralized PluginResourceManager interface for consistent async cleanup across all channel plugins |
| Azure | pr | P1 | #55395 | fix: centralize plugin command auth requirements |
| Azure | pr | P1 | #47285 | feat(memory-lancedb): native Azure OpenAI support |
| Azure | pr | P1 | #47181 | feat: add Azure Claude (AI Foundry) onboarding path |
Appendix: Stale Items (Consider Closing)
No matching items found.
Audit Notes
- Rebuilt from the format of PR #49126 after the issue/PR purge.
- Source set is current open GitHub issues and PRs from
openclaw/openclaw, plus cumulative closed/merged tracker rows recorded in maintainer update comments through 2026-05-20 and verified closed live. - Closed counts exclude rows explicitly removed as non-Microsoft false positives by the Microsoft-scope scrub comments.
- Included title/label matches for
msteams, Microsoft Teams, Windows, WSL, Azure, Entra/AAD, MSAL, managed identity, DefaultAzureCredential, Microsoft Graph, SharePoint, OneDrive, and Microsoft 365. - Scope note: broad multi-channel PRs stay in this tracker only when the Microsoft surface is primary or independently reviewable. #83348 remains open outside this tracker queue; #82873 was closed as superseded by #83348.
- Generated with
node scripts/generate-microsoft-tracker.mjsso the tracker and PR body can be refreshed after future triage passes.
Changed files
CHANGELOG.md(modified, +1/-0)MICROSOFT_TRACKER.md(added, +361/-0)scripts/generate-microsoft-tracker.mjs(added, +428/-0)
PR #84170: fix(openai): add responses message item types
- Repository: openclaw/openclaw
- Author: hclsys
- State: open | merged: False
- Link: https://github.com/openclaw/openclaw/pull/84170
Description (problem / solution / changelog)
Fixes #84109.
Summary
- add explicit
type: "message"to system/developer/user Responses input items - normalize system/developer prompt content to
input_textcontent arrays - keep Codex Responses empty-input fallback on the same explicit message item shape
Real behavior proof
- Behavior or issue addressed: Azure AI Foundry Responses endpoints reject shared Responses input items when system/developer/user entries omit the explicit
type: "message"discriminator. This patch makes the exported Responses payload builder emit that stricter message-item shape for system/developer/user inputs. - Real environment tested: Local OpenClaw checkout on commit
0a54691b3dafter rebasing onto currentmain(d0f7c8fa28), Node.js runtime with the repo source loaded throughtsx, using a Foundry-shapedopenai-responsesmodel config (https://example.services.ai.azure.com/api/projects/demo/openai/v1). - Exact steps or command run after this patch:
node --import tsx -e ...was run from the repo root to importbuildOpenAIResponsesParams, build a Foundry-shaped Responses payload, and printparams.input. - Evidence after fix: Console output from the post-patch runtime command showed both input items include
type: "message"andinput_textcontent.
[
{
"type": "message",
"role": "system",
"content": [
{
"type": "input_text",
"text": "system"
}
]
},
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": "Hello"
}
]
}
]- Observed result after fix: The shared Responses payload builder now emits explicit
type: "message"entries for the system and user input items and wraps the system prompt asinput_text, matching the stricter Azure AI Foundry payload shape reported in #84109. - What was not tested: No live Azure AI Foundry request was sent because no Azure credentials/project endpoint are available in this environment.
Validation
node scripts/run-vitest.mjs src/agents/openai-transport-stream.test.ts -t "Responses"-> 2 files passed, 50 tests passed, 288 skippednode scripts/run-vitest.mjs src/agents/openai-transport-stream.test.ts src/agents/openai-responses-payload-policy.test.ts extensions/microsoft-foundry/index.test.ts-> 4 files passed, 374 tests passedpnpm lint -- src/agents/openai-transport-stream.ts src/agents/openai-transport-stream.test.ts CHANGELOG.md-> 0 warnings, 0 errorsgit diff --check main...HEAD-> clean
Note: NODE_OPTIONS=--max-old-space-size=8192 pnpm exec tsc --noEmit --pretty false hit Node OOM after ~115s before diagnostics, so no typecheck diagnostics were produced locally.
Changed files
CHANGELOG.md(modified, +1/-0)src/agents/openai-transport-stream.test.ts(modified, +49/-4)src/agents/openai-transport-stream.ts(modified, +10/-2)
Code Example
{
"azure-openai-primary": {
"baseUrl": "https://<resource>.services.ai.azure.com/api/projects/<project>/openai/v1",
"apiKey": "***",
"api": "openai-responses",
"authHeader": false,
"headers": { "api-key": "***" },
"models": [{ "id": "gpt-5.3-codex", "reasoning": true }]
}
}
---
400 Invalid value: ''. Supported values are: 'apply_patch_call', ..., 'message', 'reasoning', ...
param: input[1]
code: invalid_value
---
// Current output:
{ role: "developer", content: "..." }
{ role: "user", content: [{ type: "input_text", text: "..." }] }
---
// Expected:
{ type: "message", role: "developer", content: [{ type: "input_text", text: "..." }] }
{ type: "message", role: "user", content: [{ type: "input_text", text: "..." }] }RAW_BUFFERClick to expand / collapse
Summary
OpenClaw's openai-responses and azure-openai-responses transports both fail against Azure AI Foundry project endpoints. The root cause is that convertResponsesMessages() does not include type: "message" on user/developer input items, which Azure AI Foundry's Responses API requires. OpenAI's direct API infers the type when absent; Azure does not.
A secondary issue prevents using api: "azure-openai-responses" as a workaround: the AzureOpenAI SDK injects an api-version query parameter that Foundry project endpoints reject.
Context
Azure AI Foundry project endpoints use a different URL structure than traditional Azure OpenAI resources:
- Traditional:
https://<resource>.openai.azure.com/openai/v1 - Foundry project:
https://<resource>.services.ai.azure.com/api/projects/<project>/openai/v1
These Foundry endpoints expose only the Responses API (/responses) — the Chat Completions API (/chat/completions) returns "unsupported operation". They also require an explicit type field on every input item in the input array, which OpenAI's direct API does not.
This is increasingly common: Azure AI Foundry is Microsoft's recommended deployment path for new models (GPT-5.x, Codex, etc.), meaning more users will hit this as they migrate from traditional Azure OpenAI resources.
Steps to Reproduce
- Configure a provider targeting an Azure AI Foundry project endpoint:
{
"azure-openai-primary": {
"baseUrl": "https://<resource>.services.ai.azure.com/api/projects/<project>/openai/v1",
"apiKey": "***",
"api": "openai-responses",
"authHeader": false,
"headers": { "api-key": "***" },
"models": [{ "id": "gpt-5.3-codex", "reasoning": true }]
}
}-
Assign an agent to use this model:
model: { "primary": "azure-openai-primary/gpt-5.3-codex" } -
Send any message. The request fails immediately with:
400 Invalid value: ''. Supported values are: 'apply_patch_call', ..., 'message', 'reasoning', ...
param: input[1]
code: invalid_valueRoot Cause Analysis
Issue 1: Missing type field on input items
In openai-responses-shared.js, convertResponsesMessages() outputs user and developer messages without a type field:
// Current output:
{ role: "developer", content: "..." }
{ role: "user", content: [{ type: "input_text", text: "..." }] }Azure AI Foundry requires:
// Expected:
{ type: "message", role: "developer", content: [{ type: "input_text", text: "..." }] }
{ type: "message", role: "user", content: [{ type: "input_text", text: "..." }] }Note: developer messages also need their content wrapped as an array with type: "input_text" — a bare string works on OpenAI direct but fails on Azure.
Issue 2: azure-openai-responses transport incompatible with Foundry endpoints
Switching to api: "azure-openai-responses" does not help because:
- The
AzureOpenAISDK automatically appends?api-version=v1to requests - Foundry project endpoints (with
/v1already in the path) reject this:400 api-version query parameter is not allowed when using /v1 path - Even if the SDK issue were resolved,
convertResponsesMessages()still omitstype: "message"— the same input formatting problem applies
Issue 3: prompt_cache_retention and store not supported
The openai-responses transport sends prompt_cache_retention and store: false in the request body. Foundry endpoints may reject these fields (unconfirmed but likely).
Verified Workaround
Using the generic OpenAI client (not AzureOpenAI) with type: "message" explicitly added to every input item works correctly — including streaming, tools, and multi-turn conversation history with function calls. Confirmed via standalone Node.js testing against the live Foundry endpoint.
Suggested Solutions
I would appreciate guidance on which approach you would prefer. Some options:
Option A: Add type: "message" unconditionally
In convertResponsesMessages(), add type: "message" to all user/developer/system message objects. This is harmless for OpenAI's direct API (which accepts it) and required by Azure. This is the simplest fix.
Option B: Add a provider-level compat flag
Introduce something like compat.explicitInputTypes: true on the provider/model config. When set, convertResponsesMessages() includes type: "message" on input items. This is more targeted but requires config changes.
Option C: Dedicated azure-foundry-responses transport
A new API type that uses the generic OpenAI client (no api-version injection), always includes type: "message", and strips unsupported fields like store and prompt_cache_retention. This would be the most robust long-term solution.
Option D: Fix azure-openai-responses to handle Foundry endpoints
Detect Foundry project URLs (contain /api/projects/) and either suppress the api-version parameter or switch to the generic OpenAI client for those endpoints. Combined with Option A or B for the type field.
Happy to submit a PR if you point me at the preferred approach.
Vote matrix · Quick signals
Still need to ship something?
×6Another batch ranked right after the header list — different links, same matching logic.
TRENDING
- Feature Request: Configurable per-minute rate limiting (RPM) for models to prevent 429 errors
- Android: Hermes App + Termux install share ~/.hermes and cause silent permission loops
- hermes update emits unicode-animations ANSI demo in non-interactive logs
- hermes update downgrades aiohttp from 3.13.4 to 3.13.3
- npm install warns about deprecated @babel/plugin-proposal-private-methods
- DingTalk inbound media URLs are skipped as unreadable native image paths
- fix(dashboard): ChatPage clears header action buttons on ALL pages, not just Sessions
- [Bug]: check_web_api_key() hardcodes built-in backends — third-party web search plugins silently disabled
- Hermes Web UI 修复经验:GatewayManager 补丁、进程 D 状态、数据库升级问题
- Telegram gateway can silently drop turn after /stop with response=0 chars while internal work continues
- Bug Report: v0.14.0 上下文污染 — 历史回复碎片回注到新请求
- Bug: hermes skills search table truncates Identifier column — install fails with copied value
- [skills-index-watchdog] Skills index is stale or degraded (degraded)
- Discord approval embed not rendering on web/mobile — embed data present in API but invisible
- Idea: Discord voice-channel participation / opt-in auto-join mode
- [Feature]: Claude Code--ultrawork
- build-arm64 job deterministically fails on cold cache (Azure SAS token expires mid-build)
- [Enhancement] computer_use: action=type should fall back to key events for terminal emulators (Ghostty/Terminal.app/iTerm2)
- Feature Request: Session Recovery on Temporary Provider Outage
- [Bug]: Hermes dashboard not working on NixOS (container)
- [Feature]: Add option to ignore @all/@everyone mentions in Feishu group chats
- QQ Bot WebSocket 频繁断开:长时间工具执行阻塞 asyncio 事件循环导致心跳超时
- patch tool: new_string escape sequences (\t) get written literally
- Feature Request: i18n / 多语言支持(国际化)
- Bug: web_crawl schema lets models auto-guess "instructions" instead of asking the user via clarify
- feat: `!command` prefix for direct shell execution (like Claude Code)
- Expose currently-running cron jobs via /api/jobs (or new endpoint)
- [Bug]: Kanban parent-child handoff: scratch workspace GC destroys artifacts before child can read them
- [Bug, Windows] hermes gateway restart loses session context — planned_stop_marker not written before SIGTERM
- [Bug]: Codex→DeepSeek fallback sends assistant turns without reasoning_content → HTTP 400 (require-side cross-provider failover)
- [Bug]: Update got stuck half way, reboot it, then ModuleNotFoundError: No module named 'hermes_cli'
- Kanban dispatcher corrupt-board handling and multi-profile gateway ownership ambiguity
- Gateway can resend a short fallback message when the real final Telegram response was already delivered
- [BUG] Bedrock: Fix 'Invalid API Key format' for presigned URL tokens
- Secret redaction corrupts code syntax in tool output (write_file, execute_code, terminal)
- Unable to connect Ollama Cloud with Pro Subscription to Hermes
- feat: fuzzy substring matching for /skill autocomplete
- PRD: Autonomous market-impact prediction briefing system
- Kanban dashboard should support task/card deep links
- [Feature] Native Feishu CardKit Streaming: consolidate best-in-class implementations
- [Feature]: Inject mental model into context when using Hindsight
- Interactive CLI hides tool output despite display.tool_progress=all, and hermes chat -v does not restore it
- fix(api_server): _handle_responses drops text.format JSON schema — structured output constraints silently ignored
- state.db FTS corruption goes undetected — no integrity check, no repair path
- bug: fallback routing can select text-only models for image requests and hide the primary failure
- feat(kanban): persist worker session_id per run and pass --resume on respawn after unblock
- feat(kanban): support GitHub/OMO lifecycle bridge for Xiyou-style automation
- Expose update-safe TUI/composer hooks for voice transcript and composer events
- Hide or configure voice transcript status rows in editable dictation mode
- [Feature]: Per-Tool / Per-Toolset Approval Policies
- Context compression creates orphan sessions missing from state.db
- messaging platform
- feat: Add read-only / silent monitoring mode for WhatsApp adapter
- double-.hermes path mismatch, the HOME env var leak, and the fallback-notification UX problem
- Bug: Plattform-Bundle name `hermes-yuanbao` in `agent.disabled_toolsets` silently kills ALL tools in gateway path (Telegram + cron), CLI unaffected
- CLI /yolo (in-chat) does not bypass dangerous command approvals — env var freeze + missing enable_session_yolo call
- OpenAI Codex provider crashes with "'NoneType' object is not iterable" (HTTP None)
- DEEPSEEK_API_KEY blocked by env blocklist in gateway process — cron jobs fail with deepseek provider
- fix(feishu): Card action callback routing issues - invalid message_id and unrecognized /card command
- Discord plugin: profiles without explicit `discord:` block silently get `require_mention=true` + `auto_thread=true` (regression in cc8e5ec2a)
- [Bug]: DISCORD_ALLOWED_ROLES ignored by gateway _is_user_authorized — role-authorized users get 'Unauthorized user' rejection
- [Bug]: /new, /clear, and /reset commands freeze the terminal session
- openai-codex subscription backend returns HTTP 200 with response.output=None, causing Slack/cron failures
- RFC: Centralized Model/Provider Registry
- bug: openai-codex provider — TypeError: 'NoneType' object is not iterable on every request (gpt-5.5)
- [Feature]: Source-aware instruction gate — architectural mitigation for indirect prompt injection
- Named custom provider stale_timeout_seconds ignored because runtime provider is normalized to `custom`
- guard test (ignore)
- [Feature]: per-platform LLM request_overrides (extra_body / reasoning_effort / service_tier)
- One-shot smoke: add Flue-backed orchestration fixture
- Gateway should not treat stale Codex app-server progress as final response after post-tool silence
- `docker_run_as_host_user: true` breaks bundled skills: Hermes home is mounted into `/root/.hermes` but the container runs as a non-root user (`HOME=/home/pn`)
- [Bug]: gateway api_server streaming bypasses server-side tool-call loop when chat_template_kwargs.enable_thinking=false (model emits tool name as plain text)
- [Feature]: Pre-install python-telegram-bot in Umbrel Hermes Docker image
- YouTube Shorts filter not working in youtube-content skill
- v0.15.0 PyPI release breaks ALL platforms — plugin.yaml manifests missing from package
- RFC: On-demand tool/skill/MCP discovery — decouple schema registration from process lifecycle
- Pixshelf: local-first stock photo workflow command center
- [Bug]: baoyu infographic skill should not silently bypass image_generate
- Pixshelf v1.5: manual submission tracking for stock agencies
- `hermes config set` silently accepts unknown keys, writing them where the runtime never reads
- Honcho memory prefetch hang on fresh CLI subprocess in v0.15.0 (regression from #27190)
- [Bug] v0.15.0 Docker image: stage2-hook.sh, main-wrapper.sh missing; container_boot module removed
- Feature: Reduce cache-read token overhead for DeepSeek providers — configurable cache_ttl, skills snapshot trimming, memory compaction
- Windows: three bugs from daily use (plugin discovery, gateway exit code, Unicode decode
- holographic memory: HRR silently degrades to FTS5 when numpy is missing
- Make max_tokens configurable for aux vision calls
- Conversation compression desynchronizes session ID between agent context and gateway routing, causing silent message loss
- [Bug]: v0.15.0 Docker image:The TUI cannot be used in the dashboard.
- cron: skip_memory=True blocks fact_store/memory tools from all cron jobs
- TUI: Node.js OOM crash when agent uses browser tools repeatedly
- feat: model_profiles — per-model toolset and memory config
- Automatic background skill patching disrupts active sessions (severe impact on local models)
- ensure_hermes_home() creates root-owned dirs in profile subdirectories when kanban workers are dispatched
- Feature: opt-in webhook bypass for DISCORD_ALLOW_BOTS — allow operator-initiated probes without weakening bot-loop guard
- v0.15.0: Codex requests fail HTTP 400 when participant display_name contains non-ASCII (emoji breaks input[].name pattern)
- Architecture: State Persistence Precedence (Memory vs Skills vs Hooks)
- [Bug]: cronjob tool: create action always fails with "schedule is required for create" even when parameters are provided
- codex-oauth: 'NoneType' object is not iterable in _run_codex_stream (gpt-5.5) — every turn fails non-retryably
- Docs/Config: Plugin local scope enablement ambiguity
- [Bug]: CLI freezes after using /new command (WSL)
- Profile Codex auth can ignore global credential pool when local state is stale
- [workflow-engine] CRITICAL: variable substitution crashes on regex metachars in user input
- [workflow-engine] HIGH: loop and bash nodes leak subprocesses on timeout
- [workflow-engine] HIGH: README documents config env vars the engine never reads
- [workflow-engine] MEDIUM: workflow_run rate limit bypassable via concurrent calls (TOCTOU)
- [workflow-engine] chore: manifest gaps, side-effectful register(), dead code, unauth kanban dispatch
- [mcp_lazy] HIGH: synthetic mcp_server_<name> stub collides with a real MCP server named 'server'
- [mcp_lazy] HIGH: promote_server eager flag documented but never persisted
- [mcp_lazy] MEDIUM: _prev_mode dict leaks and goes stale; not cleared on session evict
- [mcp_lazy] MEDIUM: get_pool has unlocked check-then-set race on pool creation
- [mcp_lazy] MEDIUM: pre_tool_call gives no guidance for unpromoted server-stub calls
- [mcp_lazy] chore: undeclared pre_tool_call hook, nonexistent 'mcp_load_tools' name in docs, missing tests
- [a2a_fleet] CRITICAL: server never auto-starts — register() runs outside an event loop
- [a2a_fleet] CRITICAL: auth_required defaults to false on a cross-machine surface
- [a2a_fleet] HIGH: remove invented disable() hook — loader never calls it, port leaks on reload
- [a2a_fleet] HIGH: plugin.yaml missing kind / provides_tools / requires_env (token env undeclared)
- [a2a_fleet] MEDIUM: tighten wide-open CORS, anonymous /health peer leak, and peer-URL SSRF
- [a2a_fleet] MEDIUM: relocate tests to tests/plugins/ and cover sync-register + auth-default paths
- xai-oauth auxiliary client incorrectly uses Responses API (CodexAuxiliaryClient), causing 403 on compression/vision/web_extract
- [Bug]: Direct Copilot gpt-5.5 large resumes are killed by 12s Codex TTFB watchdog
- [Bug]: `hermes uninstall` does not work on Windows
- TUI: Thinking block leaks raw JSON and Σ character
- Hostinger VPS: migration Hermes Agent → Hermes WebUI impossible (tini + UID mismatch + sessions)
- /goal judge over-continues exploratory goals unless the assistant explicitly says the goal is complete
- /goal auto-continuation can be amplified by preflight compression/session split and resurrect stale task state
- Dashboard infinite reload loop in loopback mode — GET /api/auth/me returns 401 on every page load
- [Bug]: Provider/LLM switch leaves stale encrypted_content causing 400 errors on Telegram sessions
- [Bug]: Infinite reload loop / React state loop on Sessions tab (Firefox + Chrome) — repeated 401 on /api/auth/me (v0.15.0)
- show_reasoning should work independently of streaming in CLI mode
- Feature Request: Strip reasoning/<think> blocks from TTS preprocessing
- mcp add / mcp test raise NameError when mcp package not installed
- v0.14.0 dashboard breaks behind reverse proxies — two regressions
- Skills hub creates empty category directories when no skills installed
- [Bug]: Custom endpoint: ChatCompletions returns content, but Hermes treats response as empty (v0.14.0)
- fix: atomic_replace() fails with EXDEV when HERMES_HOME is a cross-filesystem symlink
- fix(gateway): Feishu session cancellation orphans session guard, permanently blocking messages
- Custom endpoint pricing can overestimate Crof qwen3.5-9b cost by 1,000,000x
- MCP OAuth callback: module-level port global causes port collisions and structural weaknesses vs upstream
- Bug: send_message tool bypasses validate_media_delivery_path security check
- Proposal: Add Mnemosyne to official memory provider documentation
- feat(swarm): support custom verifier/synthesizer body + skills
- Template conversion failed
- Error occurred in the operation of the agent node in the workflow.
- PubSub client overrides Sentinel client when REDIS_USE_SENTINEL is enabled
- Frontend description of the Retrieval node output does not match the actual output
- JSON type input var raise Intenal server error
- cannot extract elements from a scalar
- 负载均衡 为模型配置多组凭据,并自动调用,此功能无法选择
- add models is error
- panic: could not create filter
- Persist partially generated messages when /chat-messages/:task_id/stop is called
- MCP server connection fails with 403 — request never leaves Dify (SSRF proxy suspected)
- Support durable async execution backends for long-running workflow steps
- [Xiaomi MiMo] Credentials validation fails with 400 "Not supported model mimo-v2-flash" when using Token Plan endpoint (v0.0.7)
- After clicking preview on a parent-child segmented knowledge base, it shows 0 chunks
- Retrieval score differs between UI upload (.docx) and API upload (.txt) despite identical chunk content and embedding model
- gemini cli crash again
- Xbox gift card code damage
- Damage caused by the gemini cli crash
- ioctl(2) failed, EBADF (Bad File Descriptor)
- Feat: Support Bun as an alternative runtime/package manager for updates and extensions
- fatal error again!!!!
- ioctl error
- Critical Crash: ioctl(2) failed, EBADF in ShellExecutionService.resizePty
- ioctl(2) failed, EBADF
- v0.44.0 Regression: Critical crash with ioctl(2) failed, EBADF during PTY resize
- Crash on startup: ioctl(2) failed, EBADF in UnixTerminal.resize
- Crash: `ioctl(2) failed, EBADF` in `node-pty` during PTY resize on macOS
- Gemini CLI crashes with `ioctl(2) failed, EBADF` in `node-pty` during `resizePty`
- Remote Role
- ERROR ioctl(2) failed, EBADF /home/mich
- RangeError: Maximum call stack size exceeded
- EBADF Error during folder creationg broke session and terminal glitches
- MAIP / Gargoub Project - Mediterania - North Coast
- Gemini cli crash again in this morning
- ERROR ioctl(2) failed, EBADF
- Verified node install fails — Checksum verification failed (Cloud)
- The extended debugging key did not arrive during registration.
- CollaborationPane unmounts collaboration store on single-user instances, causing permanent "No network connection" state
- Workflow cannot be saved when the name contains "->" (Potentially malicious string)
- automation does not work and does not show an error
- Raj Ai Automation
- Default Data Loader: DOMMatrix is not defined error
- Feature: Per-node execution timestamp overlay on canvas during workflow run
- AI Agent + Vertex `gemini-3.5-flash`: 400 "missing thought_signature" on sequential multi-turn tool calls (post-#24982)
- PDF Loader in Pinecone Vector Store fails due to pdf-parse version conflict (v2 not supported)
- emailReadImap: add UID deduplication, batch size cap, and numeric uid enforcement
- Manual node execution fails with "Could not find a node" when autosave is disabled (N8N_WORKFLOWS_AUTOSAVE_DISABLED)
- Schedule Trigger stopped firing — workflow Published & active, manual executions succeed, no automated fires for 2+ hours
- [MCP SDK] create_workflow_from_code intermittently returns HTTP 500, often as a false negative (workflow persists anyway, causing duplicates on retry)
- Credential-load wedge: workflows using googleApi/jwtAuth credentials silently fail to execute after key rotation
- Google Sheets Trigger every minute is not working manual Execute is working sent email
- [BUG] Plugin marketplace MCP connector remains stuck "still connecting" when mcp-remote requires OAuth
- [redacted at user request]
- Opus 4.7 behavioral regression: loaded instruction-following discipline degraded in recent Claude Code/Cowork updates
- [BUG] Tailscale via Homebrew CLI + Mac App Store GUI, both Macs on macOS, Cowork blocked by VPN detector despite Tailscale being a mesh VPN with no traffic interception
- stopShellPty on tab switch kills active sessions (exit 143) — regression in May 27 build
- [BUG] Long URLs are broken into multiple lines and become unclickable in terminal output
- [BUG] claude rm/stop/reap SIGKILLs background session tree without SIGTERM grace, orphaning git index.lock and similar
- [BUG] Default git workflow in the system prompt was pushed without context or consent
- [MODEL] Inconsistent output quality / Ignoring instructions (overfitting and inappropriate repetition of Korean vocabulary)
- You've hit your weekly limit · resets May 31 at 5pm (Asia/Shanghai)
- Paid yearly subscription silently downgraded to Free with no user action
- [Regression v2.1.153] Plugin bash hooks fail with "echo: write error: Permission denied" on Windows (claude-mem, shell: "bash")
- [BUG] Connector toggles in conversation are not clickable — must click text label instead
- [remote-control] Input from mobile app/browser not reaching host session — output works fine
- Model fails to read/reference CLAUDE.md contents despite being loaded in context
- [BUG] Claude Desktop reinstall destroys Code chat history (transcripts + Recents) while regular Chat history, project files, and memory all survive
- Bypass mode clamps to Accept Edits even with the toggle ON (Claude Code Desktop 1.9255.2 / CC 2.1.149)
- [BUG] TUI input freezes randomly mid-typing — entire prompt becomes unresponsive for minutes
- [BUG] Cowork downloads Linux ELF binary instead of macOS binary on macOS Sonoma 14.8.7 — exit code 132 (SIGILL) on every session
- [Feature Request] Persistent project memory — sessions forget everything on close, forcing users to keep many sessions open
- [Bug] Thread context stale after sleep/resume, returns outdated date and calendar data
- [FEATURE] Add context window usage indicator and warning before auto-compaction
- [BUG] Dictation error: Invalid character in header content ["x-config-keyterms"] on Windows
- [Bug] Anthropic API Error: Server rate limiting despite normal usage
- Does delegating work to `claude -p` subprocesses reduce context accumulation in the parent session?
- [BUG] Claude Code hangs on M1 Mac when terminal says "opening browser to sign in" and browser opens
- [BUG] Claude_Preview MCP preview_start spawns dev server with main-repo cwd instead of session's worktree cwd
- [Bug] Anthropic API Error: Server rate limiting during request execution
- [Bug] Anthropic API Error: Server rate limiting on concurrent requests
- [Bug] Ultraplan ready notification fires before cloud agent completes execution
- [BUG] API 500 ERROR ALL THROUGHOUT THE DAY
- [BUG] Cowork: Live Artifacts folder path changed in 1.9255.2, no automatic migration from Documents\Claude\Artifacts
- [Bug] Auto-compact never triggers despite statusline reporting "100% context used" (v2.1.153, Max sub, 200K mode)
- [BUG] [Desktop / macOS] 'Open in → New Window' detached session: font renders smaller than main, no per-window controls, Cmd+/Cmd- keystrokes routed to main window instead
- Feature request: option to switch between classic and new minimal UI
- [Feature Request] Show timestamps for each message
- [BUG] Terminal corruption when permission prompt appears while navigating Agent Teams agent selection menu
- [FEATURE] Allow users to customize the background color of the Claude desktop app beyond the current light/dark theme presets.
- [BUG] Statusline not displaying on Windows [fixed]
- Background agent UI Stop button is a no-op for stuck agents — process keeps consuming tokens
- Background agents silently die on session pause/resume — no completion notification, no work recovery
- Add option to hide email address from welcome banner
- [BUG] SSH Remote: `projects` field in remote ~/.claude.json becomes null after desktop restart — jsonl files intact, UI shows 'No messages yet' for every session
- [Bug] Claude Code not applying fixes despite claiming to complete tasks
- billing is unfair and poorly documented
- [BUG] Claude Code on the web: declared plugins inactive on first session, require restart to fully load
- [BUG] Restore from archive deleted sessions instead of restoring them
- [BUG] M365 connector fails with AADSTS50011 in Cowork — localhost vs 127.0.0.1 redirect URI mismatch
- claude agents: workflow slash-commands missing from dispatch-input completion (regression-adjacent to #61424)
- Claude Desktop's Info.plist missing TCC usage strings, blocks all EventKit-based MCP servers
- False-positive safety blocks on self-administered governance amendments — request for owner-authority mode for verified professional users
- [BUG] Stop pushing "AUTO"-mode
- [DOCS] Plugin marketplace guide omits `skipLfs` option for git-based sources
- [DOCS] MCP docs omit combined startup notification for MCP server and connector authentication
- [DOCS] Agent view docs omit macOS Privacy & Security identity for background agents
- [DOCS] Npm update docs do not explain release-channel behavior for `claude update`
- [DOCS] Agent SDK docs omit `subagent_type: "claude"` worktree and output persistence behavior
- [DOCS] Background session docs omit `$CLAUDE_JOB_DIR` temp-file behavior
- [FR] mask env-var values in 'claude mcp get <server>' output
- [FR] subagent worktrees should not inherit stale local 'user.email' from prior dispatches
- [BUG] Windows: Grep tool leaks rg.exe + conhost.exe processes (~2000 zombies / 14 GB RAM in long sessions)
- [BUG] Stats dashboard "Peak hour" appears off by one hour
- [BUG] Diff highlight (teal SGR background) bleeds past changed text in 2.1.150–2.1.153
- [FEATURE] confirm before deleting session
- Plugin PostToolUse hooks still silently skip in Claude Desktop / Cowork (re-filing closed #51904)
- /code-review skill: silent fallback to main...HEAD reviews other people's commits, and JSON-only output is hard to read
- Monitor tool doesn't source the shell snapshot like Bash does; PATH-dependent tools (jq, sleep, etc.) fail in Monitor commands on macOS/Nix
- [Bug] Long input lines truncated with ellipsis while typing instead of wrapping in terminal UI
- [FEATURE] VS Code extension: Render submitted user messages as Markdown in chat
- OSC 52 copy from Claude TUI doesn't reach clipboard inside tmux (regression in 2.1.146–2.1.153)
- [BUG] RemoteTrigger create/update returns HTTP 400 with circular error: "event_type is required" / "unknown field event_type"
- [BUG] Option to hide or minimize the built-in "status footer" (multi-line debug/cost panel) [re-raise of #31475]
- [Bug] Feedback submissions being closed without review or action
- [FEATURE] Word-jump cursor navigation in Chat input (option+arrow / bindable actions)
- [FEATURE] ! shell mode: filesystem tab completion
- [BUG] API Error: Usage credits required for 1M context
- claude agents: OSC 52 clipboard emission broken in tmux (regression in 2.1.146–2.1.153)
- CLI crashes on macOS 15 M3 - exit code 1
- [FEATURE] Support Cmd+V image paste from clipboard
- [FEATURE] Enhance claude.ai M365 connector to support MS Planner
- [BUG] Slash command autocomplete hijacks pasted absolute file paths starting with /
- PreToolUse hook `if` filter false-positives on complex Bash commands
- [BUG] Diff panel hangs/whites out
- Feature Request: Support drag-and-drop for binary documents (.wps, .doc, .docx, .xlsx, .pdf) in VS Code extension
- [BUG] activation of 1M context in VSCode
- [FEATURE] Support i18n / language localization for built-in slash command outputs
- Ctrl+V para colar imagens deixou de funcionar no CLI (Windows, PowerShell)
- [FEATURE] Please add Norwegian (Bokmål/Nynorsk) language support to the Claude Code interface
- [BUG] OTel log events (claude_code.user_prompt, api_request_body, tool_decision, hook_execution_complete) emitted with empty trace_id/span_id while sibling spans correlate correctly
- [BUG] Cowork crashes on every message, no VM logs generated, missing AppData\Roaming\Claude
- [FEATURE] first-class session handoff + per-session token budgets for unattended runs
- [FEATURE] Smart paste: convert clipboard code to file reference chips (like Cursor)
- [Feature Request] Restore chat pin functionality to title chat submenu
- [BUG] SIGILL issues with version 2.1.153
- [BUG] Cowork plugin upload fails with generic "Plugin validation failed" when a `description` field in any SKILL.md frontmatter contains angle brackets (`<…>`)
- [BUG] Desktop App 2.1.144+: startup scanner deletes cliSessionId from claude-code-sessions local files on every launch — session not found on disk
- [Feature Request] Add keyboard shortcut to copy last message with proper formatting
- [MODEL] Opus 4.7 not 1M
- Allow naming/renaming background agents in `claude agents` view
- Stale worktrees in .claude/worktrees/ are never cleaned up, consuming massive disk space
- Agent worktrees are never cleaned up, silently consuming disk space
- Subagent worktrees not auto-cleaned when reviewer writes scratch files
- [Bug] Skill initialization hangs for extended duration in Plan Mode
- Claude Desktop writes malformed registry Run entry (nested escaped quotes) - crashes Windows Task Manager and other Run-key parsers
- IME candidate window shows at bottom-right corner instead of caret position (Windows CMD)
- [BUG] Pressing 'Escape' doesn't close the /BTW conversation when the main conversation is asking for approval
- [BUG] Opus 4.7 (1M) intermittently emits empty-string values for tool_use.input fields, killing the session
- FleetView agent UI shows "running" with incrementing elapsed time after agent has returned
- /doctor flags context-scoped cmd+c binding as macOS conflict (false positive)
- [BUG] Text Rendering in Elvish
- Desktop app: Bypass Permissions mode flips to Accept Edits on first prompt (M5 / macOS 26.5)
- [Workaround] Date-Weekday Verification Hook — Prevents Claude from writing wrong weekdays
- [BUG] Claude Code create c:/memfs directory without asking me.
- [BUG] Claude Code's Bash execution waits forever with no processes running
- [BUG] usage stays stuck waiting for 5 hr limit after upgrading to premium seat in team plan
- [Workflow tool] resume cache is unreachable for nontrivial workflows because LLM dispatchers can't transcribe args byte-exactly
- Code review (Preview): "Add a repository" shows no results for private GitHub org repos
- [BUG] /context commands blows up context
- [Feature Request] Add precache expiry hook to enable proactive compaction before token eviction
- [BUG] Context indicator shows 0% at session start despite ~20K+ tokens already loaded
- [Feature Request] Add semantic search for --resume session history
- [Feature Request] Add session search, tagging, and filtering capabilities
- [BUG] Cowork Dispatch reports "desktop not available" on Windows 11 while standard Cowork works normally
- [Bug] Claude Code provides incorrect suggestions with high confidence despite errors
- defaultMode: acceptEdits silently overrides per-path permissions.ask rules for Write/Edit
- [FEATUR configurable tip interval (e.g. tipIntervalSeconds: 30 in settings)E]
- Plugin marketplace fails to load: schema rejects 'displayName' key (v2.1.153)
- claude agents: in-session copy uses broken OSC 52 path while overview correctly uses tmux buffer
- [BUG] Plugin agent descriptions (and custom agents) load unconditionally into context — no parity with disable-model-invocation for skills
- Crashed ultrareview consumed a free credit despite producing zero findings
- [Bug] Character rendering issue - invisible or missing text display
- [BUG] Cowork: processo Claude Code encerra com código 3 — .claude.json não contém token de autenticação (Windows 11 25H2)
- [BUG] 2.1.153 silently discards tools/list response from rmcp 0.12.0 HTTP MCP server (works in 2.1.152, wire-identical handshake)
- VS Code extension: option to auto-resume last session when reopening a workspace folder
- [Bug] Conversation continuation failure
- [BUG] Cowork crashes every time I start a new chat or attempt to continue an existing one in any project. The error displayed is: "Claude Code è andato in crash
- [Bug] Unannounced quota changes
- Native update/install fails with 'socket connection was closed unexpectedly' behind proxy — undici TLS incompatibility
- [BUG] Session name reverting after manual change
- [BUG] 非正常思考,上下文过长时,一直显示思考,点击interrupt按钮失效
- Honor `tools:` frontmatter when an agent is invoked via `@mention` — strip `Task` only when the agent did not declare it
- macOS TCC popup still recurring on v2.1.153 — "2.1.153" would like to access data from other apps
- Claude Code leaks pty handles — exhausts pseudo-terminals on macOS after long session
- [Bug] Agent fails to execute or respond to user input
- [BUG] Persistent "Expecting value: line 1 column 1 (char 0)" JSON parse error after tool execution
- [Feature Request] Implement proactive unit test coverage recommendations for recurring bugs
- VS Code panel lacks status line + terminal lacks image paste in Codespaces, forcing a tradeoff
- `/powerup` only shows ~10 lessons — allow viewing the full catalog
- [Bug] Context contamination after auto-compact with unrelated email draft of Tejo/Sado Basin
- [Bug] VSCode terminal output displays corrupted text with garbled symbols
- [Feature Request] Add LaTeX/KaTeX math rendering to TUI
- [Bug] Sub-agent PR review results not validated by orchestrating agent
- Subagents on Pro 1M tier: trivial probes pass, real workloads fail at first tool call (probe-vs-workload divergence)
- Path-scoped rules and subdirectory CLAUDE.md not loaded when creating new files matching the pattern
- AskUserQuestion: cancelling during extended thinking poisons the whole session with 400 'thinking blocks cannot be modified' (2.1.153); concurrent prompts overwrite each other
- Ideas Missing from Claude Cowork Menu (Windows)
- [BUG_BOUNTY_SAFE_POC_2026] Prompt Injection RCE Test - Command Execution Proof
- [BUG] Cowork scheduled task: execution history row not showing after successful run
- Resuming an extended-thinking session fails permanently with 400 "thinking blocks cannot be modified" (transcript stores thinking text as empty but keeps signature)
- [Bug] Plugin-registered CwdChanged and FileChanged hooks don't fire (settings.json works) — v2.1.153
- Auto-archive on PR merge / branch delete — clarify autoArchiveSessions semantics or add dedicated opt-out
- `claude mcp add` echoes Authorization header value verbatim to stdout, leaks bearer tokens to terminal and session transcripts
- [BUG] Bug report — /insights skill, Claude Code The /insights skill outputs a malformed file path.
- Plugin slash commands render with '*'-inline format instead of two-column, despite matching official plugin shape
- [Bug] Unexpected long text generation without user input or goal
- [Bug] Thinking blocks causing task progression blocked without user modification
- [BUG] (Critical!) contamination by an unknown session simirlar to the report => [Bug] Context contamination after auto-compact with unrelated email draft of Tejo/Sado Basin #63137
- [Critical] Opus 4.7 Korean output degeneration — Korean grammar itself collapses in long contexts
- [BUG] Title: Autocompact buffer persists across /clear — wastes tokens for irrelevant old context
- [Bug] Auto-Compact loses user input before processing in conversation history
- Feature: per-invocation effort parameter + runtime session-config introspection for skills
- Auto-mode classifier mislabels Azure DevOps vote -5 as "Reject" when denying PR vote actions
- [BUG] Claude Desktop and Claude Code CLI never re-register MCP tools after OAuth 2.1 handshake on a remote HTTP server
- [BUG] Workspace file tags leak across sessions
- [BUG] Ink renderer crashes on Windows 11 build 26200 (Canary) duplicate banners, terminal mode leaks, mid-operation aborts
- [BUG] Claude Code Desktop issue
- PTY master fd leak in Claude desktop app exhausts macOS kern.tty.ptmx_max after ~2-3 days
- [BUG] Claude Code — Session Management after Unexpected Interruption
- [Windows] Cowork OpenTelemetry exporter does not initialize - zero events emitted to any destination, including loopback
- [Bug] Opus 4.7: 400 `thinking blocks ... cannot be modified` on long extended-thinking sessions, triggered by history-altering events (scheduled prompts / parallel tool-call cancellation)
- [BUG] API Error: Server is temporarily limiting requests (not your usage limit) · Rate limited
- Multi-plugin custom marketplace: only first plugin registered in installed_plugins.json, skills don't load
- [BUG] Git push through the SDK's git proxy fan-outs into ~500 GitHub REST API calls, exhausting the 5,000/hour budget after a handful of pushes
- [BUG] Claude took liberties it really shouldn't with my global config
- [BUG] Agent window focus lost after navigating with arrow keys, causing scroll deadlock
- [BUG] `--model` flag silently ignored in interactive sessions (works in `--print` only)
- [BUG] Dispatch permanently shows "desktop appears offline" on Windows 11 - never worked on first use
- feat: support per-command enableWeakerNetworkIsolation as safer alternative to dangerouslyDisableSandbox
- /code-review outputs a raw JSON array instead of readable findings
- [BUG] Cowork — Additional allowed domains ignored on Team plan; same domain works on Pro plan
- Haiku
- [Bug] False positive blocking beneficial outcomes in tool execution
- 3P Bedrock SSO: credentials silently expire without triggering re-auth on day 2+
- CLAUDE_AUTOCOMPACT_PCT_OVERRIDE in settings.json env block silently ignored by autocompact logic
- Auto-compaction deletes main session JSONL before verifying summary completion, causing data loss
- [Bug] Claude Code not executing stated actions or producing expected results
- [FEATURE] Deferred Messages — Queue Input for End of Turn
- [BUG] Up/Down arrows in input box navigate history instead of moving cursor — regression in 2.1.149+
- Cancelling a parallel tool-call batch corrupts thinking blocks -> 400 "thinking blocks cannot be modified" permanently wedges the session
- Claude Code caused data loss, then contradicted itself about recovery (two incidents, one session)
- [Bug] Unclear error messages from Claude Code CLI
- [Bug] Agent tool rejecting due to context size limit exceeded
- claude agents: daemon and bg-spare processes spin at ~100% CPU when idle
- [BUG] Compaction fails with "context window limit" error even when context usage is low (e.g., 20%) — regression in v2.1.153
- Remote Control entitlement lost after May 27-28 incident — `Error: Remote Control is not yet enabled for your account` on active Max subscription
- PreToolUse hook exit code 2 does not block Write tool
- [Bug] Thinking blocks in latest assistant message are immutable
- GUI: dispatch file:// and custom-scheme clicks to OS shell handler
- Show current model in statusLine by default
- [Bug] Agent console becomes unresponsive to keyboard input after multiple agents initialized
- [FEATURE] PreToolUse hooks should have a way of updating the environment
- [Bug] Unable to start or use Claude Code CLI
- [BUG] Repository not visible in Claude Code web repo picker
- Session permanently wedged on 400 "thinking blocks cannot be modified" after parallel tool_results
- [Bug] @ autocomplete loses sibling repos after a file edit in multi-repo workspace
- Unclear error message when creating sub-agent without authentication
- [Bug] Anthropic API errors causing frequent failures and high token usage
- [BUG] @ mention file picker only shows packages, not individual files (desktop app - Code tab)
- [Bug] TUI panel footer remains sticky and consumes excessive terminal space
- PR-status polling exhausts GitHub GraphQL rate limit on repos with many open PRs
- [BUG] Windows: welcome panel not shown in some project folders (2.1.153)
- [Bug] Anthropic API Error: thinking blocks corrupted during context compaction with extended thinking enabled
- API 400 "thinking blocks cannot be modified" permanently bricks session during agent activation (interleaved thinking + tool use)
- Right-click Copy copies the whole message instead of the selection; pasted text retains dark background
- Mid-session model switch corrupts conversation when extended thinking is enabled (API 400: 'thinking blocks cannot be modified')
- [BUG] Markdown file links in chat output do not open files when clicked (VS Code extension)
- Stuck retry loop: `400 thinking blocks cannot be modified` on large interleaved-thinking turns using AskUserQuestion
- [FEATURE] Prompt user for approval before auto-compaction proceeds
- Custom MCP connectors not attachable to scheduled routines — no UUID discovery path
- [BUG] Claude in Chrome — Navigation blocked for teams.cloud.microsoft and outlook.cloud.microsoft after Microsoft domain migration**
- [BUG] Claude Desktop — Personal plugins panel renders list but is entirely non-interactive (macOS, v1.9255.2)
- [Bug] error when using Workflows
- [BUG] Persistent "update available" notification despite being on latest version
- [BUG] Sweep Agent from /code-review never completes
- [Bug] Tool calls not executing or returning results
- [FEATURE] Cloud-synced memory and settings across machines
- [Bug] Terminal UI freezes when Ctrl+O view exits during interactive prompt in plan mode
- Continuous api errors when using claude code with Opus 4.7 with thinking on low
- [Feature Request] Add support for installing and using previous Claude Code versions
- [Bug] Extended Thinking: Summarized thinking blocks fail signature validation when resent to API
- [Bug] Anthropic API Error: 'thinking' blocks cannot be modified
- [Bug] Anthropic API Error: Thinking blocks cannot be modified with extended thinking mode
- Feature request: Lazy/on-demand MCP server connections
- [Bug] Tool Arguments Parsed as String Instead of Object
- [Bug] Anthropic API Error: Insufficient context provided
- [Bug] Claude Opus occasionally uses moskovian(russian) orthography instead of Ukrainian in system-prompted responses
- Opus 4.8: backgrounded task completions (subagents AND Bash) crash with 400 "thinking blocks cannot be modified"
- [Bug] Opus 4.7 fabricates stable preferences ("my default") to rationalize arbitrary choices when challenged
- [Bug] Unable to update Claude Code CLI
- [BUG] Desktop app: /remote-control mints link + connects bridge (main.log) but in-chat link/QR panel never renders
- Feature: sessionColor and sessionName in .claude/settings.json
- [BUG] Anthropic API error: thinking blocks
- [FEATURE] Support Remote MCPs in Cowork as in Claude Code
- [Bug] Anthropic API Error: 400 Bad Request with Redacted Thinking - 0 4.7 & 4.8
- [Bug] Anthropic API Error: Cannot modify thinking blocks from different model versions
- Interleaved thinking + multi-tool turn corrupts thinking block (text blanked, signature kept) → permanent 400 'blocks must remain as they were'
- [BUG] Mode/permission changes mid-tool-loop (effortLevel: xhigh) poisons entire session
- Session failure log: Opus 4.6 ignores its own rules for an entire session
- [BUG] "400 Guardrail was enabled" error when using Claude Opus 4.8 with AWS Bedrock
- [Feature Request] Add subagent approach selection option to avoid accidental feedback
- Persistent 400 'thinking blocks in the latest assistant message cannot be modified' — interleaved thinking persisted with empty text + signature bricks sessions
- [BUG] DesktopvsApp
- [BUG] Opus 4.7 cache hit rate collapse after May 27 incident — Messages 1.1k→88.9k in 9 minutes, $630/session
- [Bug] Anthropic API Error: Invalid thinking block format
- [BUG] FUCK CLAUDE
- Opus 4.8 extended thinking: Stop hook block re-entry corrupts thinking blocks → 400
- [Bug] 4.8 Fails when accessing previous model history
- [Bug] Unintended File Modifications During Execution
- [DOCS] Model configuration docs omit lean system prompt default scope and model exceptions
- Add "Always allow globally" option to permission prompts
- Server-side model upgrade (Opus 4.7→4.8) wedges in-flight sessions with `thinking blocks cannot be modified` 400
- [DOCS] AskUserQuestion docs missing multiple-choice prompt decision threshold
- [DOCS] Agent view docs omit shell-command background session launch syntax
- [DOCS] Agent view dispatch input docs incorrectly imply `/logout` dispatches as a prompt
- [DOCS] Claude in Chrome docs omit connected-browser selection behavior
- [DOCS] Plugin docs omit `defaultEnabled: false` for opt-in plugins
- Feature Request: Customizable chat text colors for user and assistant messages
- [DOCS] `/plugin` Discover tab docs omit directory-based suggested plugin pins
- VSCode Chrome integration silently fails: 3 distinct bugs
- [DOCS] MCP stdio docs omit session environment variables
- [Bug] Anthropic API error on second request within session with Claude Opus 4.8
- Cowork emits a blank session "index" handoff on focus when a CLI session is paused awaiting input
- [DOCS] MCP docs omit `claude mcp list/get` pending-approval output for unapproved project servers
- [BUG] /compact fails with 400 error when last assistant turn contains thinking blocks
- [DOCS] `/claude-api` docs omit Opus 4.8 migration guidance
- [DOCS] Fast mode docs still recommend deprecated Opus 4.6 override variable
- [DOCS] Bash tool docs omit `$TMPDIR` consistency across sandboxed and unsandboxed commands
- [Bug] Anthropic API Error: 400 Bad Request on Extended Thinking
- [DOCS] Background session docs omit worktree-isolation behavior for spawned subagents
- Built-in mechanistic self-verification of verifiable claims (symmetric to the auto permission gate)
- [DOCS] Worktree docs do not clarify `worktree.baseRef: "head"` inside linked worktrees
- [BUG] Excessive RAM usage with multiple parallel chats (~10 sessions → 30 GB memory pressure, macOS OOM)
- [DOCS] Managed MCP policy docs omit invalid `allowedMcpServers`/`deniedMcpServers` entry behavior
- [DOCS] Effort docs omit `CLAUDE_CODE_ALWAYS_ENABLE_EFFORT` unsupported-model behavior
- Regression (2.1.147–2.1.150?): resuming an extended-thinking session after a CC update/model-switch → unrecoverable 400, session bricked
- [DOCS] Windows updater docs omit `claude.exe` in-use recovery guidance
- [DOCS] VS Code auto mode docs still tie mode-picker visibility to bypass-permissions setting
- [DOCS] MCP docs omit `/mcp` tool list and detail rendering behavior
- [DOCS] Fine-grained tool streaming docs still describe provider opt-in behavior
- bypassPermissions: session startup reads flat pref, GUI toggle writes per-account pref — they never sync
- [BUG] Claude Desktop Code tab causes disk write limit violation — 8.5GB in 11 min, macOS kills app (M5, v1.9659.1)
- Ultrareview v2.1.96: docs describe /tasks command + claude ultrareview --json subcommand that don't exist; findings hard to read after completion
- I'd be happy to help create a GitHub issue title, but I don't see the error message in your message. Could you please share the specific error you're encountering? That way I can generate an accurate and descriptive issue title for you.
- [BUG] Claude in Chrome `file_upload` rejects all scheduled-task sessions with misleading error (real cause: INVALID_SESSION)
- Extended thinking: signed thinking block 'cannot be modified' (400) permanently wedges session
- RTL text support for Hebrew (and Arabic) in Claude Code
- [Bug] Random errors occurring across multiple operations