Merge pull request #1360 from SocialNerd42069/fix/duplicate-assistant-texts

fix: prevent duplicate assistant texts from whitespace differences
2026-01-21 06:31:01 +00:00
parent 32edaad823 65dd73b4c3
commit ab97c6880b
11 changed files with 376 additions and 227 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,192 +2,226 @@

 Docs: https://docs.clawd.bot

-## 2026.1.20
-
-### Highlights
- Nostr: add the Nostr channel plugin with profile management + onboarding defaults. (#1323) https://docs.clawd.bot/channels/nostr
- Gateway: add the OpenResponses-compatible `/v1/responses` endpoint. (#1229) https://docs.clawd.bot/gateway/openresponses-http-api
- Matrix: migrate to matrix-bot-sdk with E2EE support. (#1298) https://docs.clawd.bot/channels/matrix
- TUI: session picker shows derived titles, fuzzy search, relative times, and last message preview. (#1271) https://docs.clawd.bot/tui
- Control UI: add copy-as-markdown with error feedback. (#1345) https://docs.clawd.bot/web/control-ui
- Memory: add native Gemini embeddings provider for memory search. (#1151) https://docs.clawd.bot/concepts/memory
+## 2026.1.19-3

 ### Changes
- Commands: add `/allowlist` slash command for listing and editing channel allowlists.
- Control UI: add copy-as-markdown with error feedback. (#1345) https://docs.clawd.bot/web/control-ui
- Control UI: drop the legacy list view. (#1345) https://docs.clawd.bot/web/control-ui
- TUI: add syntax highlighting for code blocks. (#1200) https://docs.clawd.bot/tui
- TUI: session picker shows derived titles, fuzzy search, relative times, and last message preview. (#1271) https://docs.clawd.bot/tui
- TUI: add a searchable model picker for quicker model selection. (#1198) https://docs.clawd.bot/tui
- TUI: add input history (up/down) for submitted messages. (#1348) https://docs.clawd.bot/tui
- ACP: add `clawdbot acp` for IDE integrations. https://docs.clawd.bot/cli/acp
- ACP: add `clawdbot acp client` interactive harness for debugging. https://docs.clawd.bot/cli/acp
- Skills: add download installs with OS-filtered options. https://docs.clawd.bot/tools/skills
- Skills: add the local sherpa-onnx-tts skill. https://docs.clawd.bot/tools/skills
- Memory: add hybrid BM25 + vector search (FTS5) with weighted merging and fallback. https://docs.clawd.bot/concepts/memory
- Memory: add SQLite embedding cache to speed up reindexing and frequent updates. https://docs.clawd.bot/concepts/memory
- Memory: add OpenAI batch indexing for embeddings when configured. https://docs.clawd.bot/concepts/memory
- Memory: enable OpenAI batch indexing by default for OpenAI embeddings. https://docs.clawd.bot/concepts/memory
- Memory: allow parallel OpenAI batch indexing jobs (default concurrency: 2). https://docs.clawd.bot/concepts/memory
- Memory: render progress immediately, color batch statuses in verbose logs, and poll OpenAI batch status every 2s by default. https://docs.clawd.bot/concepts/memory
- Memory: add `--verbose` logging for memory status + batch indexing details. https://docs.clawd.bot/concepts/memory
- Memory: add native Gemini embeddings provider for memory search. (#1151) https://docs.clawd.bot/concepts/memory
- Browser: allow config defaults for efficient snapshots in the tool/CLI. (#1336) https://docs.clawd.bot/tools/browser
- Nostr: add the Nostr channel plugin with profile management + onboarding defaults. (#1323) https://docs.clawd.bot/channels/nostr
- Matrix: migrate to matrix-bot-sdk with E2EE support, location handling, and group allowlist upgrades. (#1298) https://docs.clawd.bot/channels/matrix
- Slack: add HTTP webhook mode via Bolt HTTP receiver. (#1143) https://docs.clawd.bot/channels/slack
- Telegram: enrich forwarded-message context with normalized origin details + legacy fallback. (#1090) https://docs.clawd.bot/channels/telegram
- Discord: fall back to `/skill` when native command limits are exceeded. (#1287)
- Discord: expose `/skill` globally. (#1287)
- Zalouser: add channel dock metadata, config schema, setup wiring, probe, and status issues. (#1219) https://docs.clawd.bot/plugins/zalouser
- Plugins: require manifest-embedded config schemas with preflight validation warnings. (#1272) https://docs.clawd.bot/plugins/manifest
- Plugins: move channel catalog metadata into plugin manifests. (#1290) https://docs.clawd.bot/plugins/manifest
- Plugins: align Nextcloud Talk policy helpers with core patterns. (#1290) https://docs.clawd.bot/plugins/manifest
- Plugins/UI: let channel plugin metadata drive UI labels/icons and cron channel options. (#1306) https://docs.clawd.bot/web/control-ui
- Plugins: add plugin slots with a dedicated memory slot selector. https://docs.clawd.bot/plugins/agent-tools
- Plugins: ship the bundled BlueBubbles channel plugin (disabled by default). https://docs.clawd.bot/channels/bluebubbles
- Plugins: migrate bundled messaging extensions to the plugin SDK and resolve plugin-sdk imports in the loader.
- Plugins: migrate the Zalo plugin to the shared plugin SDK runtime. https://docs.clawd.bot/channels/zalo
- Plugins: migrate the Zalo Personal plugin to the shared plugin SDK runtime. https://docs.clawd.bot/plugins/zalouser
- Plugins: allow optional agent tools with explicit allowlists and add the plugin tool authoring guide. https://docs.clawd.bot/plugins/agent-tools
- Plugins: auto-enable bundled channel/provider plugins when configuration is present.
- Plugins: sync plugin sources on channel switches and update npm-installed plugins during `clawdbot update`.
- Plugins: share npm plugin update logic between `clawdbot update` and `clawdbot plugins update`.
- Gateway/API: add `/v1/responses` (OpenResponses) with item-based input + semantic streaming events. (#1229)
- Gateway/API: expand `/v1/responses` to support file/image inputs, tool_choice, usage, and output limits. (#1229)
- Usage: add `/usage cost` summaries and macOS menu cost charts. https://docs.clawd.bot/reference/api-usage-costs
- Security: warn when <=300B models run without sandboxing while web tools are enabled. https://docs.clawd.bot/cli/security
- Exec: add host/security/ask routing for gateway + node exec. https://docs.clawd.bot/tools/exec
- Exec: add `/exec` directive for per-session exec defaults (host/security/ask/node). https://docs.clawd.bot/tools/exec
- Exec approvals: migrate approvals to `~/.clawdbot/exec-approvals.json` with per-agent allowlists + skill auto-allow toggle, and add approvals UI + node exec lifecycle events. https://docs.clawd.bot/tools/exec-approvals
- Nodes: add headless node host (`clawdbot node start`) for `system.run`/`system.which`. https://docs.clawd.bot/cli/node
- Nodes: add node daemon service install/status/start/stop/restart. https://docs.clawd.bot/cli/node
- Bridge: add `skills.bins` RPC to support node host auto-allow skill bins.
- Sessions: add daily reset policy with per-type overrides and idle windows (default 4am local), preserving legacy idle-only configs. (#1146) https://docs.clawd.bot/concepts/session
- Sessions: allow `sessions_spawn` to override thinking level for sub-agent runs. https://docs.clawd.bot/tools/subagents
- Channels: unify thread/topic allowlist matching + command/mention gating helpers across core providers. https://docs.clawd.bot/concepts/groups
- Models: add Qwen Portal OAuth provider support. (#1120) https://docs.clawd.bot/providers/qwen
- Onboarding: add allowlist prompts and username-to-id resolution across core and extension channels. https://docs.clawd.bot/start/onboarding
- Docs: clarify allowlist input types and onboarding behavior for messaging channels. https://docs.clawd.bot/start/onboarding
- Docs: refresh Android node discovery docs for the Gateway WS service type. https://docs.clawd.bot/platforms/android
- Docs: surface Amazon Bedrock in provider lists and clarify Bedrock auth env vars. (#1289) https://docs.clawd.bot/bedrock
- Docs: clarify WhatsApp voice notes. https://docs.clawd.bot/channels/whatsapp
- Docs: clarify Windows WSL portproxy LAN access notes. https://docs.clawd.bot/platforms/windows
- Docs: refresh bird skill install metadata and usage notes. (#1302) https://docs.clawd.bot/tools/browser-login
- Agents: add local docs path resolution and include docs/mirror/source/community pointers in the system prompt.
- Agents: clarify node_modules read-only guidance in agent instructions.
- Config: stamp last-touched metadata on write and warn if the config is newer than the running build.
- macOS: hide usage section when usage is unavailable instead of showing provider errors.
- Android: migrate node transport to the Gateway WebSocket protocol with TLS pinning support + gateway discovery naming.
- Android: send structured payloads in node events/invokes and include user-agent metadata in gateway connects.
 - Android: remove legacy bridge transport code now that nodes use the gateway protocol.
- Android: bump okhttp + dnsjava to satisfy lint dependency checks.
- Build: update workspace + core/plugin deps.
- Build: use tsgo for dev/watch builds by default (opt out with `CLAWDBOT_TS_COMPILER=tsc`).
- Repo: remove the Peekaboo git submodule now that the SPM release is used.
- macOS: switch PeekabooBridge integration to the tagged Swift Package Manager release.
- macOS: stop syncing Peekaboo in postinstall.
- Swabble: use the tagged Commander Swift package release.
-
-### Breaking
- **BREAKING:** Reject invalid/unknown config entries and refuse to start the gateway for safety. Run `clawdbot doctor --fix` to repair, then update plugins (`clawdbot plugins update`) if you use any.
+- Android: send structured payloads in node events/invokes and include user-agent metadata in gateway connects.
+
+### Fixes
+- Slack: respect verbose tool summaries and keep tool notifications threaded. (#1360) — thanks @SocialNerd42069.
+
+## 2026.1.19-2
+
+### Changes
+- Android: migrate node transport to the Gateway WebSocket protocol with TLS pinning support + gateway discovery naming.
+- Android: bump okhttp + dnsjava to satisfy lint dependency checks.
+- Docs: refresh Android node discovery docs for the Gateway WS service type.

 ### Fixes
- Discovery: shorten Bonjour DNS-SD service type to `_clawdbot-gw._tcp` and update discovery clients/docs.
- Diagnostics: export OTLP logs, correct queue depth tracking, and document message-flow telemetry.
- Diagnostics: emit message-flow diagnostics across channels via shared dispatch. (#1244)
- Diagnostics: gate heartbeat/webhook logging. (#1244)
- Gateway: strip inbound envelope headers from chat history messages to keep clients clean.
- Gateway: clarify unauthorized handshake responses with token/password mismatch guidance.
- Gateway: allow mobile node client ids for iOS + Android handshake validation. (#1354)
- Gateway: clarify connect/validation errors for gateway params. (#1347)
- Gateway: preserve restart wake routing + thread replies across restarts. (#1337)
- Gateway: reschedule per-agent heartbeats on config hot reload without restarting the runner.
- Gateway: require authorized restarts for SIGUSR1 (restart/apply/update) so config gating can't be bypassed.
- Cron: auto-deliver isolated agent output to explicit targets without tool calls. (#1285)
- Agents: preserve subagent announce thread/topic routing + queued replies across channels. (#1241)
- Agents: propagate accountId into embedded runs so sub-agent announce routing honors the originating account. (#1058)
- Agents: avoid treating timeout errors with "aborted" messages as user aborts, so model fallback still runs. (#1137)
- Agents: sanitize oversized image payloads before send and surface image-dimension errors.
- Sessions: fall back to session labels when listing display names. (#1124)
- Compaction: include tool failure summaries in safeguard compaction to prevent retry loops. (#1084)
- Config: log invalid config issues once per run and keep invalid-config errors stackless.
- Config: allow Perplexity as a web_search provider in config validation. (#1230)
- Config: allow custom fields under `skills.entries.<name>.config` for skill credentials/config. (#1226)
- Doctor: clarify plugin auto-enable hint text in the startup banner.
- Doctor: canonicalize legacy session keys in session stores to prevent stale metadata. (#1169)
- Docs: make docs:list fail fast with a clear error if the docs directory is missing.
- Plugins: add Nextcloud Talk manifest for plugin config validation. (#1297)
- Plugins: surface plugin load/register/config errors in gateway logs with plugin/source context.
- CLI: preserve cron delivery settings when editing message payloads. (#1322)
- CLI: keep `clawdbot logs` output resilient to broken pipes while preserving progress output.
- CLI: avoid duplicating --profile/--dev flags when formatting commands.
- CLI: centralize CLI command registration to keep fast-path routing and program wiring in sync. (#1207)
- CLI: keep banners on routed commands, restore config guarding outside fast-path routing, and tighten fast-path flag parsing while skipping console capture for extra speed. (#1195)
- CLI: skip runner rebuilds when dist is fresh. (#1231)
- CLI: add WSL2/systemd unavailable hints in daemon status/doctor output.
- Status: route native `/status` to the active agent so model selection reflects the correct profile. (#1301)
- Status: show both usage windows with reset hints when usage data is available. (#1101)
- UI: keep config form enums typed, preserve empty strings, protect sensitive defaults, and deepen config search. (#1315)
- UI: preserve ordered list numbering in chat markdown. (#1341)
- UI: allow Control UI to read gatewayUrl from URL params for remote WebSocket targets. (#1342)
- UI: prevent double-scroll in Control UI chat by locking chat layout to the viewport. (#1283)
- UI: enable shell mode for sync Windows spawns to avoid `pnpm ui:build` EINVAL. (#1212)
- TUI: keep thinking blocks ordered before content during streaming and isolate per-run assembly. (#1202)
- TUI: align custom editor initialization with the latest pi-tui API. (#1298)
- TUI: show generic empty-state text for searchable pickers. (#1201)
- TUI: highlight model search matches and stabilize search ordering.
- Configure: hide OpenRouter auto routing model from the model picker. (#1182)
- Memory: show total file counts + scan issues in `clawdbot memory status`.
- Memory: fall back to non-batch embeddings after repeated batch failures.
- Memory: apply OpenAI batch defaults even without explicit remote config.
- Memory: index atomically so failed reindex preserves the previous memory database. (#1151)
- Memory: avoid sqlite-vec unique constraint failures when reindexing duplicate chunk ids. (#1151)
- Memory: retry transient 5xx errors (Cloudflare) during embedding indexing.
- Memory: parallelize embedding indexing with rate-limit retries.
- Memory: split overly long lines to keep embeddings under token limits.
- Memory: skip empty chunks to avoid invalid embedding inputs.
- Memory: split embedding batches to avoid OpenAI token limits during indexing.
- Memory: probe sqlite-vec availability in `clawdbot memory status`.
- Exec approvals: enforce allowlist when ask is off.
- Exec approvals: prefer raw command for node approvals/events.
- Tools: show exec elevated flag before the command and keep it outside markdown in tool summaries.
- Tools: return a companion-app-required message when node exec is requested with no paired node.
- Tools: return a companion-app-required message when `system.run` is requested without a supporting node.
- Exec: default gateway/node exec security to allowlist when unset (sandbox stays deny).
- Exec: prefer bash when fish is default shell, falling back to sh if bash is missing. (#1297)
- Exec: merge login-shell PATH for host=gateway exec while keeping daemon PATH minimal. (#1304)
- Streaming: emit assistant deltas for OpenAI-compatible SSE chunks. (#1147)
- Discord: make resolve warnings avoid raw JSON payloads on rate limits.
- Discord: process message handlers in parallel across sessions to avoid event queue blocking. (#1295)
- Discord: stop reconnecting the gateway after aborts to prevent duplicate listeners.
- Discord: only emit slow listener warnings after 30s.
- Discord: inherit parent channel allowlists for thread slash commands and reactions. (#1123)
- Telegram: honor pairing allowlists for native slash commands.
- Telegram: preserve hidden text_link URLs by expanding entities in inbound text. (#1118)
- Slack: resolve Bolt import interop for Bun + Node. (#1191)
- Web search: infer Perplexity base URL from API key source (direct vs OpenRouter).
- Web fetch: harden SSRF protection with shared hostname checks and redirect limits. (#1346)
- Browser: register AI snapshot refs for act commands. (#1282)
- Voice call: include request query in Twilio webhook verification when publicUrl is set. (#864)
- Anthropic: default API prompt caching to 1h with configurable TTL override.
- Anthropic: ignore TTL for OAuth.
- Auth profiles: keep auto-pinned preference while allowing rotation on failover. (#1138)
- Auth profiles: user pins stay locked. (#1138)
- Model catalog: avoid caching import failures, log transient discovery errors, and keep partial results. (#1332)
 - Tests: stabilize Windows gateway/CLI tests by skipping sidecars, normalizing argv, and extending timeouts.
- Tests: stabilize plugin SDK resolution and embedded agent timeouts.
- Windows: install gateway scheduled task as the current user.
- Windows: show friendly guidance instead of failing on access denied.
+- CLI: skip runner rebuilds when dist is fresh. (#1231) — thanks @mukhtharcm, @thewilloftheshadow.
+
+## 2026.1.19-1
+
+### Breaking
+- **BREAKING:** Reject invalid/unknown config entries and refuse to start the gateway for safety; run `clawdbot doctor --fix` to repair. 
+
+### Changes
+- Usage: add `/usage cost` summaries and macOS menu cost submenu with daily charting.
+- Agents: clarify node_modules read-only guidance in agent instructions.
+- TUI: add syntax highlighting for code blocks. (#1200) — thanks @vignesh07.
+
+### Fixes
+- UI: enable shell mode for sync Windows spawns to avoid `pnpm ui:build` EINVAL. (#1212) — thanks @longmaba.
+- Agents: add `clawdbot agents set-identity` helper and update bootstrap guidance for multi-agent setups. (#1222) — thanks @ThePickle31.
+- Plugins: surface plugin load/register/config errors in gateway logs with plugin/source context.
+- Agents: propagate accountId into embedded runs so sub-agent announce routing honors the originating account. (#1058)
+- Compaction: include tool failure summaries in safeguard compaction to prevent retry loops. (#1084)
+- Daemon: include HOME in service environments to avoid missing HOME errors. (#1214) — thanks @ameno-.
+- TUI: show generic empty-state text for searchable pickers. (#1201) — thanks @vignesh07.
+- Doctor: canonicalize legacy session keys in session stores to prevent stale metadata. (#1169)
+- CLI: centralize CLI command registration to keep fast-path routing and program wiring in sync. (#1207) — thanks @gumadeiras.
+
+## 2026.1.18-5
+
+### Changes
+- Dependencies: update core + plugin deps (grammy, vitest, openai, Microsoft agents hosting, etc.).
+- Onboarding: add allowlist prompts and username-to-id resolution across core and extension channels.
+- TUI: add searchable model picker for quicker model selection. (#1198) — thanks @vignesh07.
+- Docs: clarify allowlist input types and onboarding behavior for messaging channels.
+
+### Fixes
+- Configure: hide OpenRouter auto routing model from the model picker. (#1182) — thanks @zerone0x.
+- Docs: make docs:list fail fast with a clear error if the docs directory is missing.
 - macOS: load menu session previews asynchronously so items populate while the menu is open.
 - macOS: use label colors for session preview text so previews render in menu subviews.
 - macOS: suppress usage error text in the menubar cost view.
- macOS: Doctor repairs LaunchAgent bootstrap issues for Gateway + Node when listed but not loaded. (#1166)
- macOS: avoid touching launchd in Remote over SSH so quitting the app no longer disables the remote gateway. (#1105)
- macOS: bundle Textual resources in packaged app builds to avoid code block crashes. (#1006)
- Daemon: include HOME in service environments to avoid missing HOME errors. (#1214)
+- Telegram: honor pairing allowlists for native slash commands.
+- TUI: highlight model search matches and stabilize search ordering.
+- CLI: keep banners on routed commands, restore config guarding outside fast-path routing, and tighten fast-path flag parsing while skipping console capture for extra speed. (#1195) — thanks @gumadeiras.
+- Slack: resolve Bolt import interop for Bun + Node. (#1191) — thanks @CoreyH.
+- Gateway: require authorized restarts for SIGUSR1 (restart/apply/update) so config gating can't be bypassed.
+- Discord: stop reconnecting the gateway after aborts to prevent duplicate listeners.

-Thanks @AlexMikhalev, @CoreyH, @John-Rood, @KrauseFx, @MaudeBot, @Nachx639, @NicholaiVogel, @RyanLisse, @ThePickle31, @VACInc, @Whoaa512, @YuriNachos, @aaronveklabs, @abdaraxus, @alauppe, @ameno-, @artuskg, @austinm911, @bradleypriest, @cheeeee, @dougvk, @fogboots, @gnarco, @gumadeiras, @jdrhyne, @joelklabo, @longmaba, @mukhtharcm, @odysseus0, @oscargavin, @rhjoh, @sebslight, @sibbl, @sleontenko, @steipete, @suminhthanh, @thewilloftheshadow, @tyler6204, @vignesh07, @visionik, @ysqander, @zerone0x.
+## 2026.1.18-4
+
+### Changes
+- macOS: switch PeekabooBridge integration to the tagged Swift Package Manager release (no submodule).
+- macOS: stop syncing Peekaboo as a git submodule in postinstall.
+- Swabble: use the tagged Commander Swift package release.
+- CLI: add `clawdbot acp client` interactive ACP harness for debugging.
+- Plugins: route command detection/text chunking helpers through the plugin runtime and drop runtime exports from the SDK.
+- Plugins: auto-enable bundled channel/provider plugins when configuration is present.
+- Config: stamp last-touched metadata on write and warn if the config is newer than the running build.
+- macOS: hide usage section when usage is unavailable instead of showing provider errors.
+- Memory: add native Gemini embeddings provider for memory search. (#1151)
+- Agents: add local docs path resolution and include docs/mirror/source/community pointers in the system prompt.
+- Slack: add HTTP webhook mode via Bolt HTTP receiver for Events API deployments. (#1143) — thanks @jdrhyne.
+
+### Fixes
+- Auth profiles: keep auto-pinned preference while allowing rotation on failover; user pins stay locked. (#1138) — thanks @cheeeee.
+- Agents: sanitize oversized image payloads before send and surface image-dimension errors.
+- macOS: Doctor repairs LaunchAgent bootstrap issues for Gateway + Node when listed but not loaded. (#1166) — thanks @AlexMikhalev.
+- macOS: avoid touching launchd in Remote over SSH so quitting the app no longer disables the remote gateway. (#1105)
+- Memory: index atomically so failed reindex preserves the previous memory database. (#1151)
+- Memory: avoid sqlite-vec unique constraint failures when reindexing duplicate chunk ids. (#1151)
+
+## 2026.1.18-3
+
+### Changes
+- Exec: add host/security/ask routing for gateway + node exec.
+- Exec: add `/exec` directive for per-session exec defaults (host/security/ask/node).
+- macOS: migrate exec approvals to `~/.clawdbot/exec-approvals.json` with per-agent allowlists and skill auto-allow toggle.
+- macOS: add approvals socket UI server + node exec lifecycle events.
+- Nodes: add headless node host (`clawdbot node start`) for `system.run`/`system.which`.
+- Nodes: add node daemon service install/status/start/stop/restart.
+- Bridge: add `skills.bins` RPC to support node host auto-allow skill bins.
+- Slash commands: replace `/cost` with `/usage off|tokens|full` to control per-response usage footer; `/usage` no longer aliases `/status`. (Supersedes #1140) — thanks @Nachx639.
+- Sessions: add daily reset policy with per-type overrides and idle windows (default 4am local), preserving legacy idle-only configs. (#1146) — thanks @austinm911.
+- Agents: auto-inject local image references for vision models and avoid reloading history images. (#1098) — thanks @tyler6204.
+- Docs: refresh exec/elevated/exec-approvals docs for the new flow. https://docs.clawd.bot/tools/exec-approvals
+- Docs: add node host CLI + update exec approvals/bridge protocol docs. https://docs.clawd.bot/cli/node
+- ACP: add experimental ACP support for IDE integrations (`clawdbot acp`). Thanks @visionik.
+- Tools: allow `sessions_spawn` to override thinking level for sub-agent runs.
+- Channels: unify thread/topic allowlist matching + command/mention gating helpers across core providers.
+- Models: add Qwen Portal OAuth provider support. (#1120) — thanks @mukhtharcm.
+- Memory: add `--verbose` logging for memory status + batch indexing details.
+- Memory: allow parallel OpenAI batch indexing jobs (default concurrency: 2).
+- macOS: add per-agent exec approvals with allowlists, skill CLI auto-allow, and settings UI.
+- Docs: add exec approvals guide and link from tools index. https://docs.clawd.bot/tools/exec-approvals
+- macOS: add exec-host IPC for node service `system.run` with HMAC + peer UID checks.
+
+### Fixes
+- Exec approvals: enforce allowlist when ask is off; prefer raw command for node approvals/events.
+- Tools: return a companion-app-required message when node exec is requested with no paired node.
+- Streaming: emit assistant deltas for OpenAI-compatible SSE chunks. (#1147) — thanks @alauppe.
+- Model fallback: treat timeout aborts as failover while preserving user aborts. (#1137) — thanks @cheeeee.
+
+## 2026.1.18-2
+
+### Fixes
+- Tests: stabilize plugin SDK resolution and embedded agent timeouts.
+
+## 2026.1.18-1
+
+### Changes
+- Tools: allow `sessions_spawn` to override thinking level for sub-agent runs.
+- Channels: unify thread/topic allowlist matching + command/mention gating helpers across core providers.
+- Models: add Qwen Portal OAuth provider support. (#1120) — thanks @mukhtharcm.
+- Memory: add `--verbose` logging for memory status + batch indexing details.
+- Memory: allow parallel OpenAI batch indexing jobs (default concurrency: 2).
+- macOS: add per-agent exec approvals with allowlists, skill CLI auto-allow, and settings UI.
+- Docs: add exec approvals guide and link from tools index. https://docs.clawd.bot/tools/exec-approvals
+
+### Fixes
+- Memory: apply OpenAI batch defaults even without explicit remote config.
+- macOS: bundle Textual resources in packaged app builds to avoid code block crashes. (#1006)
+- Tools: return a companion-app-required message when `system.run` is requested without a supporting node.
+- Discord: only emit slow listener warnings after 30s.
+
+## 2026.1.17-6
+
+### Changes
+- Plugins: add exclusive plugin slots with a dedicated memory slot selector.
+- Memory: ship core memory tools + CLI as the bundled `memory-core` plugin.
+- Docs: document plugin slots and memory plugin behavior.
+- Plugins: add the bundled BlueBubbles channel plugin (disabled by default).
+- Plugins: migrate bundled messaging extensions to the plugin SDK; resolve plugin-sdk imports in loader.
+- Plugins: migrate the Zalo plugin to the shared plugin SDK runtime.
+- Plugins: migrate the Zalo Personal plugin to the shared plugin SDK runtime.
+
+## 2026.1.17-5
+
+### Changes
+- Memory: add hybrid BM25 + vector search (FTS5) with weighted merging and fallback.
+- Memory: add SQLite embedding cache to speed up reindexing and frequent updates.
+- CLI: surface FTS + embedding cache state in `clawdbot memory status`.
+- Memory: render progress immediately, color batch statuses in verbose logs, and poll OpenAI batch status every 2s by default.
+- Plugins: allow optional agent tools with explicit allowlists and add plugin tool authoring guide. https://docs.clawd.bot/plugins/agent-tools
+- Tools: centralize plugin tool policy helpers.
+- Commands: add `/subagents info` and show sub-agent counts in `/status`.
+- Docs: clarify plugin agent tool configuration. https://docs.clawd.bot/plugins/agent-tools
+
+### Fixes
+- Voice call: include request query in Twilio webhook verification when publicUrl is set. (#864)
+
+## 2026.1.18-1
+
+### Changes
+- Tools: allow `sessions_spawn` to override thinking level for sub-agent runs.
+- Channels: unify thread/topic allowlist matching + command/mention gating helpers across core providers.
+- Models: add Qwen Portal OAuth provider support. (#1120) — thanks @mukhtharcm.
+- Memory: add `--verbose` logging for memory status + batch indexing details.
+- Memory: allow parallel OpenAI batch indexing jobs (default concurrency: 2).
+- macOS: add per-agent exec approvals with allowlists, skill CLI auto-allow, and settings UI.
+- Docs: add exec approvals guide and link from tools index. https://docs.clawd.bot/tools/exec-approvals
+
+### Fixes
+- Memory: apply OpenAI batch defaults even without explicit remote config.
+- macOS: bundle Textual resources in packaged app builds to avoid code block crashes. (#1006)
+- Tools: return a companion-app-required message when `system.run` is requested without a supporting node.
+- Discord: only emit slow listener warnings after 30s.
+## 2026.1.17-3
+
+### Changes
+- Memory: add OpenAI Batch API indexing for embeddings when configured.
+- Memory: enable OpenAI batch indexing by default for OpenAI embeddings.
+
+### Fixes
+- Memory: retry transient 5xx errors (Cloudflare) during embedding indexing.
+
+## 2026.1.17-2
+
+### Changes
+
+### Fixes
+- Tools: show exec elevated flag before the command and keep it outside markdown in tool summaries.
+- Memory: parallelize embedding indexing with rate-limit retries.
+- Memory: split overly long lines to keep embeddings under token limits.
+- Memory: skip empty chunks to avoid invalid embedding inputs.
+- Sessions: fall back to session labels when listing display names. (#1124) — thanks @abdaraxus.
+- Discord: inherit parent channel allowlists for thread slash commands and reactions. (#1123) — thanks @thewilloftheshadow.
+
+## 2026.1.17-1
+
+### Changes
+- Telegram: enrich forwarded message context with normalized origin details + legacy fallback. (#1090) — thanks @sleontenko.
+- macOS: strip prerelease/build suffixes when parsing gateway semver patches. (#1110) — thanks @zerone0x.
+- macOS: keep CLI install pinned to the full build suffix. (#1111) — thanks @artuskg.
+- CLI: surface update availability in `clawdbot status`.
+- CLI: add `clawdbot memory status --deep/--index` probes.
+- CLI: add playful update completion quips.
+
+### Fixes
+- Doctor: avoid re-adding WhatsApp ack reaction config when only legacy auth files exist. (#1087) — thanks @YuriNachos.
+- Hooks: parse multi-line/YAML frontmatter metadata blocks (JSON5-friendly). (#1114) — thanks @sebslight.
+- CLI: add WSL2/systemd unavailable hints in daemon status/doctor output.
+- Windows: install gateway scheduled task as the current user; show friendly guidance instead of failing on access denied.
+- Status: show both usage windows with reset hints when usage data is available. (#1101) — thanks @rhjoh.
+- Memory: probe sqlite-vec availability in `clawdbot memory status`.
+- Memory: split embedding batches to avoid OpenAI token limits during indexing.
+- Telegram: preserve hidden text_link URLs by expanding entities in inbound text. (#1118) — thanks @sleontenko.

 ## 2026.1.16-2

--- a/skills/coding-agent/SKILL.md
+++ b/skills/coding-agent/SKILL.md
@@ -76,7 +76,7 @@ bash pty:true workdir:~/project background:true command:"codex exec --full-auto
 # Monitor progress
 process action:log sessionId:XXX

-# Check if done  
+# Check if done
 process action:poll sessionId:XXX

 # Send input (if agent asks a question)
@@ -217,15 +217,55 @@ git worktree remove /tmp/issue-99

 ## ⚠️ Rules

-1. **Always use pty:true** — coding agents need a terminal!
-2. **Respect tool choice** — if user asks for Codex, use Codex. NEVER offer to build it yourself!
-3. **Be patient** — don't kill sessions because they're "slow"
-4. **Monitor with process:log** — check progress without interfering
-5. **--full-auto for building** — auto-approves changes
-6. **vanilla for reviewing** — no special flags needed
-7. **Parallel is OK** — run many Codex processes at once for batch work
-8. **NEVER start Codex in ~/clawd/** — it'll read your soul docs and get weird ideas about the org chart!
-9. **NEVER checkout branches in ~/Projects/clawdbot/** — that's the LIVE Clawdbot instance!
+1. **Always use pty:true** - coding agents need a terminal!
+2. **Respect tool choice** - if user asks for Codex, use Codex.
+   - Orchestrator mode: do NOT hand-code patches yourself.
+   - If an agent fails/hangs, respawn it or ask the user for direction, but don't silently take over.
+3. **Be patient** - don't kill sessions because they're "slow"
+4. **Monitor with process:log** - check progress without interfering
+5. **--full-auto for building** - auto-approves changes
+6. **vanilla for reviewing** - no special flags needed
+7. **Parallel is OK** - run many Codex processes at once for batch work
+8. **NEVER start Codex in ~/clawd/** - it'll read your soul docs and get weird ideas about the org chart!
+9. **NEVER checkout branches in ~/Projects/clawdbot/** - that's the LIVE Clawdbot instance!
+
+---
+
+## Progress Updates (Critical)
+
+When you spawn coding agents in the background, keep the user in the loop.
+
+- Send 1 short message when you start (what's running + where).
+- Then only update again when something changes:
+  - a milestone completes (build finished, tests passed)
+  - the agent asks a question / needs input
+  - you hit an error or need user action
+  - the agent finishes (include what changed + where)
+- If you kill a session, immediately say you killed it and why.
+
+This prevents the user from seeing only "Agent failed before reply" and having no idea what happened.
+
+---
+
+## Auto-Notify on Completion
+
+For long-running background tasks, append a wake trigger to your prompt so Clawdbot gets notified immediately when the agent finishes (instead of waiting for the next heartbeat):
+
+```
+... your task here.
+
+When completely finished, run this command to notify me:
+clawdbot gateway wake --text "Done: [brief summary of what was built]" --mode now
+```
+
+**Example:**
+```bash
+bash pty:true workdir:~/project background:true command:"codex --yolo exec 'Build a REST API for todos.
+
+When completely finished, run: clawdbot gateway wake --text \"Done: Built todos REST API with CRUD endpoints\" --mode now'"
+```
+
+This triggers an immediate wake event — Skippy gets pinged in seconds, not 10 minutes.

 ---

--- a/src/agents/pi-embedded-subscribe.handlers.types.ts
+++ b/src/agents/pi-embedded-subscribe.handlers.types.ts
@@ -39,6 +39,10 @@ export type EmbeddedPiSubscribeState = {
  lastStreamedAssistant?: string;
  lastStreamedReasoning?: string;
  lastBlockReplyText?: string;
+  assistantMessageIndex: number;
+  lastAssistantTextMessageIndex: number;
+  lastAssistantTextNormalized?: string;
+  lastAssistantTextTrimmed?: string;
  assistantTextBaseline: number;
  suppressBlockChunks: boolean;
  lastReasoningSent?: string;
--- a/src/agents/pi-embedded-subscribe.subscribe-embedded-pi-session.does-not-emit-duplicate-block-replies-text.test.ts
+++ b/src/agents/pi-embedded-subscribe.subscribe-embedded-pi-session.does-not-emit-duplicate-block-replies-text.test.ts
@@ -86,6 +86,35 @@ describe("subscribeEmbeddedPiSession", () => {

    expect(subscription.assistantTexts).toEqual(["Hello world"]);
  });
+  it("does not duplicate assistantTexts when message_end repeats with trailing whitespace changes", () => {
+    let handler: SessionEventHandler | undefined;
+    const session: StubSession = {
+      subscribe: (fn) => {
+        handler = fn;
+        return () => {};
+      },
+    };
+
+    const subscription = subscribeEmbeddedPiSession({
+      session: session as unknown as Parameters<typeof subscribeEmbeddedPiSession>[0]["session"],
+      runId: "run",
+    });
+
+    const assistantMessageWithNewline = {
+      role: "assistant",
+      content: [{ type: "text", text: "Hello world\n" }],
+    } as AssistantMessage;
+
+    const assistantMessageTrimmed = {
+      role: "assistant",
+      content: [{ type: "text", text: "Hello world" }],
+    } as AssistantMessage;
+
+    handler?.({ type: "message_end", message: assistantMessageWithNewline });
+    handler?.({ type: "message_end", message: assistantMessageTrimmed });
+
+    expect(subscription.assistantTexts).toEqual(["Hello world"]);
+  });
  it("does not duplicate assistantTexts when message_end repeats with reasoning blocks", () => {
    let handler: SessionEventHandler | undefined;
    const session: StubSession = {
--- a/src/agents/pi-embedded-subscribe.ts
+++ b/src/agents/pi-embedded-subscribe.ts
@@ -48,6 +48,10 @@ export function subscribeEmbeddedPiSession(params: SubscribeEmbeddedPiSessionPar
    lastStreamedAssistant: undefined,
    lastStreamedReasoning: undefined,
    lastBlockReplyText: undefined,
+    assistantMessageIndex: 0,
+    lastAssistantTextMessageIndex: -1,
+    lastAssistantTextNormalized: undefined,
+    lastAssistantTextTrimmed: undefined,
    assistantTextBaseline: 0,
    suppressBlockChunks: false, // Avoid late chunk inserts after final text merge.
    lastReasoningSent: undefined,
@@ -84,9 +88,36 @@ export function subscribeEmbeddedPiSession(params: SubscribeEmbeddedPiSessionPar
    state.lastStreamedReasoning = undefined;
    state.lastReasoningSent = undefined;
    state.suppressBlockChunks = false;
+    state.assistantMessageIndex += 1;
+    state.lastAssistantTextMessageIndex = -1;
+    state.lastAssistantTextNormalized = undefined;
+    state.lastAssistantTextTrimmed = undefined;
    state.assistantTextBaseline = nextAssistantTextBaseline;
  };

+  const rememberAssistantText = (text: string) => {
+    state.lastAssistantTextMessageIndex = state.assistantMessageIndex;
+    state.lastAssistantTextTrimmed = text.trimEnd();
+    const normalized = normalizeTextForComparison(text);
+    state.lastAssistantTextNormalized = normalized.length > 0 ? normalized : undefined;
+  };
+
+  const shouldSkipAssistantText = (text: string) => {
+    if (state.lastAssistantTextMessageIndex !== state.assistantMessageIndex) return false;
+    const trimmed = text.trimEnd();
+    if (trimmed && trimmed === state.lastAssistantTextTrimmed) return true;
+    const normalized = normalizeTextForComparison(text);
+    if (normalized.length > 0 && normalized === state.lastAssistantTextNormalized) return true;
+    return false;
+  };
+
+  const pushAssistantText = (text: string) => {
+    if (!text) return;
+    if (shouldSkipAssistantText(text)) return;
+    assistantTexts.push(text);
+    rememberAssistantText(text);
+  };
+
  const finalizeAssistantTexts = (args: {
    text: string;
    addedDuringMessage: boolean;
@@ -103,16 +134,15 @@ export function subscribeEmbeddedPiSession(params: SubscribeEmbeddedPiSessionPar
          assistantTexts.length - state.assistantTextBaseline,
          text,
        );
+        rememberAssistantText(text);
      } else {
-        const last = assistantTexts.at(-1);
-        if (!last || last !== text) assistantTexts.push(text);
+        pushAssistantText(text);
      }
      state.suppressBlockChunks = true;
    } else if (!addedDuringMessage && !chunkerHasBuffered && text) {
      // Non-streaming models (no text_delta): ensure assistantTexts gets the final
      // text when the chunker has nothing buffered to drain.
-      const last = assistantTexts.at(-1);
-      if (!last || last !== text) assistantTexts.push(text);
+      pushAssistantText(text);
    }

    state.assistantTextBaseline = assistantTexts.length;
@@ -338,8 +368,11 @@ export function subscribeEmbeddedPiSession(params: SubscribeEmbeddedPiSessionPar
      return;
    }

+    if (shouldSkipAssistantText(chunk)) return;
+
    state.lastBlockReplyText = chunk;
    assistantTexts.push(chunk);
+    rememberAssistantText(chunk);
    if (!params.onBlockReply) return;
    const splitResult = parseReplyDirectives(chunk);
    const {
--- a/src/auto-reply/reply/agent-runner-helpers.ts
+++ b/src/auto-reply/reply/agent-runner-helpers.ts
@@ -16,19 +16,21 @@ export const createShouldEmitToolResult = (params: {
  storePath?: string;
  resolvedVerboseLevel: VerboseLevel;
 }): (() => boolean) => {
+  // Normalize verbose values from session store/config so false/"false" still means off.
+  const fallbackVerbose = normalizeVerboseLevel(String(params.resolvedVerboseLevel ?? "")) ?? "off";
  return () => {
    if (!params.sessionKey || !params.storePath) {
-      return params.resolvedVerboseLevel !== "off";
+      return fallbackVerbose !== "off";
    }
    try {
      const store = loadSessionStore(params.storePath);
      const entry = store[params.sessionKey];
-      const current = normalizeVerboseLevel(entry?.verboseLevel);
+      const current = normalizeVerboseLevel(String(entry?.verboseLevel ?? ""));
      if (current) return current !== "off";
    } catch {
      // ignore store read failures
    }
-    return params.resolvedVerboseLevel !== "off";
+    return fallbackVerbose !== "off";
  };
 };

@@ -37,19 +39,21 @@ export const createShouldEmitToolOutput = (params: {
  storePath?: string;
  resolvedVerboseLevel: VerboseLevel;
 }): (() => boolean) => {
+  // Normalize verbose values from session store/config so false/"false" still means off.
+  const fallbackVerbose = normalizeVerboseLevel(String(params.resolvedVerboseLevel ?? "")) ?? "off";
  return () => {
    if (!params.sessionKey || !params.storePath) {
-      return params.resolvedVerboseLevel === "full";
+      return fallbackVerbose === "full";
    }
    try {
      const store = loadSessionStore(params.storePath);
      const entry = store[params.sessionKey];
-      const current = normalizeVerboseLevel(entry?.verboseLevel);
+      const current = normalizeVerboseLevel(String(entry?.verboseLevel ?? ""));
      if (current) return current === "full";
    } catch {
      // ignore store read failures
    }
-    return params.resolvedVerboseLevel === "full";
+    return fallbackVerbose === "full";
  };
 };

--- a/src/auto-reply/reply/route-reply.test.ts
+++ b/src/auto-reply/reply/route-reply.test.ts
@@ -209,6 +209,22 @@ describe("routeReply", () => {
    expect(mocks.sendMessageSlack).toHaveBeenCalledWith("channel:C123", "hi", expect.any(Object));
  });

+  it("uses threadId for Slack when replyToId is missing", async () => {
+    mocks.sendMessageSlack.mockClear();
+    await routeReply({
+      payload: { text: "hi" },
+      channel: "slack",
+      to: "channel:C123",
+      threadId: "456.789",
+      cfg: {} as never,
+    });
+    expect(mocks.sendMessageSlack).toHaveBeenCalledWith(
+      "channel:C123",
+      "hi",
+      expect.objectContaining({ threadTs: "456.789" }),
+    );
+  });
+
  it("passes thread id to Telegram sends", async () => {
    mocks.sendMessageTelegram.mockClear();
    await routeReply({
--- a/src/channels/plugins/outbound/slack.ts
+++ b/src/channels/plugins/outbound/slack.ts
@@ -5,19 +5,23 @@ export const slackOutbound: ChannelOutboundAdapter = {
  deliveryMode: "direct",
  chunker: null,
  textChunkLimit: 4000,
-  sendText: async ({ to, text, accountId, deps, replyToId }) => {
+  sendText: async ({ to, text, accountId, deps, replyToId, threadId }) => {
    const send = deps?.sendSlack ?? sendMessageSlack;
+    // Use threadId fallback so routed tool notifications stay in the Slack thread.
+    const threadTs = replyToId ?? (threadId != null ? String(threadId) : undefined);
    const result = await send(to, text, {
-      threadTs: replyToId ?? undefined,
+      threadTs,
      accountId: accountId ?? undefined,
    });
    return { channel: "slack", ...result };
  },
-  sendMedia: async ({ to, text, mediaUrl, accountId, deps, replyToId }) => {
+  sendMedia: async ({ to, text, mediaUrl, accountId, deps, replyToId, threadId }) => {
    const send = deps?.sendSlack ?? sendMessageSlack;
+    // Use threadId fallback so routed tool notifications stay in the Slack thread.
+    const threadTs = replyToId ?? (threadId != null ? String(threadId) : undefined);
    const result = await send(to, text, {
      mediaUrl,
-      threadTs: replyToId ?? undefined,
+      threadTs,
      accountId: accountId ?? undefined,
    });
    return { channel: "slack", ...result };
--- a/src/cli/update-cli.ts
+++ b/src/cli/update-cli.ts
@@ -17,6 +17,7 @@ import {
  runGatewayUpdate,
  type UpdateRunResult,
  type UpdateStepInfo,
+  type UpdateStepResult,
  type UpdateStepProgress,
  type UpdateStepResult,
 } from "../infra/update-runner.js";
--- a/src/slack/monitor/message-handler/prepare.ts
+++ b/src/slack/monitor/message-handler/prepare.ts
@@ -476,10 +476,11 @@ export async function prepareSlackMessage(params: {
    Surface: "slack" as const,
    MessageSid: message.ts,
    ReplyToId: message.thread_ts ?? message.ts,
+    // Preserve thread context for routed tool notifications (thread replies only).
+    MessageThreadId: isThreadReply ? threadTs : undefined,
    ParentSessionKey: threadKeys.parentSessionKey,
    ThreadStarterBody: threadStarterBody,
    ThreadLabel: threadLabel,
-    MessageThreadId: isThreadReply ? threadTs : undefined,
    Timestamp: message.ts ? Math.round(Number(message.ts) * 1000) : undefined,
    WasMentioned: isRoomish ? effectiveWasMentioned : undefined,
    MediaPath: media?.path,
--- a/src/slack/monitor/provider.ts
+++ b/src/slack/monitor/provider.ts
@@ -1,6 +1,6 @@
 import type { IncomingMessage, ServerResponse } from "node:http";

-import SlackBoltDefault, * as SlackBoltModule from "@slack/bolt";
+import SlackBolt from "@slack/bolt";

 import { resolveTextChunkLimit } from "../../auto-reply/chunk.js";
 import { DEFAULT_GROUP_HISTORY_LIMIT } from "../../auto-reply/reply/history.js";
@@ -26,24 +26,14 @@ import { normalizeAllowList } from "./allow-list.js";

 import type { MonitorSlackOpts } from "./types.js";

-type SlackBoltNamespace = typeof import("@slack/bolt");
-type SlackBoltDefault = SlackBoltNamespace | SlackBoltNamespace["App"];
-
-const slackBoltDefaultImport = SlackBoltDefault as SlackBoltDefault | undefined;
-const slackBoltModuleDefault = (SlackBoltModule as { default?: SlackBoltDefault }).default;
-const slackBoltDefault = slackBoltDefaultImport ?? slackBoltModuleDefault;
-const slackBoltNamespace =
-  typeof slackBoltDefault === "object" && slackBoltDefault
-    ? (slackBoltDefault as SlackBoltNamespace)
-    : typeof slackBoltModuleDefault === "object" && slackBoltModuleDefault
-      ? (slackBoltModuleDefault as SlackBoltNamespace)
-      : undefined;
-// Bun allows named imports from CJS; Node ESM doesn't. Resolve default/module shapes for compatibility.
-const App = ((typeof slackBoltDefault === "function" ? slackBoltDefault : undefined) ??
-  slackBoltNamespace?.App ??
-  SlackBoltModule.App) as SlackBoltNamespace["App"];
-const HTTPReceiver = (slackBoltNamespace?.HTTPReceiver ??
-  SlackBoltModule.HTTPReceiver) as SlackBoltNamespace["HTTPReceiver"];
+const slackBoltModule = SlackBolt as typeof import("@slack/bolt") & {
+  default?: typeof import("@slack/bolt");
+};
+// Bun allows named imports from CJS; Node ESM doesn't. Use default+fallback for compatibility.
+// Fix: Check if module has App property directly (Node 25.x ESM/CJS compat issue)
+const slackBolt =
+  (slackBoltModule.App ? slackBoltModule : slackBoltModule.default) ?? slackBoltModule;
+const { App, HTTPReceiver } = slackBolt;
 function parseApiAppIdFromAppToken(raw?: string) {
  const token = raw?.trim();
  if (!token) return undefined;
@@ -133,13 +123,6 @@ export async function monitorSlackProvider(opts: MonitorSlackOpts = {}) {
  const mediaMaxBytes = (opts.mediaMaxMb ?? slackCfg.mediaMaxMb ?? 20) * 1024 * 1024;
  const removeAckAfterReply = cfg.messages?.removeAckAfterReply ?? false;

-  if (!App) {
-    throw new Error("Slack Bolt App export missing; check @slack/bolt installation.");
-  }
-  if (slackMode === "http" && !HTTPReceiver) {
-    throw new Error("Slack Bolt HTTPReceiver export missing; check @slack/bolt installation.");
-  }
-
  const receiver =
    slackMode === "http"
      ? new HTTPReceiver({