Commit Graph

3256 Commits

Author SHA1 Message Date
Peter Steinberger
fa4670c5fe feat: improve agent auth guidance 2026-01-15 04:51:21 +00:00
Peter Steinberger
edd8c613d6 feat(security): add audit --fix 2026-01-15 04:50:06 +00:00
Peter Steinberger
0a7f5bf6a5 test(gateway): fix config.patch baseHash fixtures 2026-01-15 04:50:06 +00:00
Peter Steinberger
eb3e865f15 fix(build): restore tool policy typing 2026-01-15 04:50:06 +00:00
Roshan Singh
1baa55c145 Structured subagent announce output + include run outcome (#835)
* docs: clarify subagent announce status

* Make subagent announce structured and include run outcome

* fix: stabilize sub-agent announce status (#835) (thanks @roshanasingh4)

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-01-15 04:48:07 +00:00
Sebastian
6ef3837e73 Remove debug logging for responsePrefix template resolution 2026-01-14 23:36:47 -05:00
Sebastian
e7167e35ed debug: use console.log instead of logVerbose for always-visible logging 2026-01-14 23:29:17 -05:00
Peter Steinberger
2e0325e3bf feat: add web search hint to onboarding 2026-01-15 04:25:19 +00:00
Sebastian
56b3b44342 debug: add responsePrefix template logging 2026-01-14 23:23:21 -05:00
Sebastian
113eea5047 fix: mutate prefixContext object instead of reassigning for closure correctness 2026-01-14 23:20:19 -05:00
Sebastian
7b04e6ac42 debug: add prefix template resolution logging 2026-01-14 23:15:46 -05:00
Peter Steinberger
f275cc180b feat: add web tools 2026-01-15 04:07:40 +00:00
Peter Steinberger
31d3aef8d6 fix: prevent config clobbering 2026-01-15 04:06:11 +00:00
Sebastian
d0a4cce41e feat: add dynamic template variables to messages.responsePrefix (#923)
Adds support for template variables in `messages.responsePrefix` that
resolve dynamically at runtime with the actual model used (including
after fallback).

Supported variables (case-insensitive):
- {model} - short model name (e.g., "claude-opus-4-5", "gpt-4o")
- {modelFull} - full model identifier (e.g., "anthropic/claude-opus-4-5")
- {provider} - provider name (e.g., "anthropic", "openai")
- {thinkingLevel} or {think} - thinking level ("high", "low", "off")
- {identity.name} or {identityName} - agent identity name

Example: "[{model} | think:{thinkingLevel}]" → "[claude-opus-4-5 | think:high]"

Variables show the actual model used after fallback, not the intended
model. Unresolved variables remain as literal text.

Implementation:
- New module: src/auto-reply/reply/response-prefix-template.ts
- Template interpolation in normalize-reply.ts via context provider
- onModelSelected callback in agent-runner-execution.ts
- Updated all 6 provider message handlers (web, signal, discord,
  telegram, slack, imessage)
- 27 unit tests covering all variables and edge cases
- Documentation in docs/gateway/configuration.md and JSDoc

Fixes #923
2026-01-14 23:05:08 -05:00
Peter Steinberger
429f973280 test: cover browser snapshot labels and efficient mode 2026-01-15 04:04:30 +00:00
Peter Steinberger
6320f739d4 refactor: centralize whatsapp auth detection 2026-01-15 04:01:06 +00:00
Peter Steinberger
1732932c57 fix: unblock launchctl stub on windows 2026-01-15 03:58:32 +00:00
Peter Steinberger
1c737f88fe test: cover provider tool policies 2026-01-15 03:55:20 +00:00
Peter Steinberger
fa8d9b9189 feat: add provider-specific tool policies 2026-01-15 03:55:20 +00:00
Peter Steinberger
1078d178d7 fix: doctor ack reaction migration (#927)
Thanks @grp06.

Co-authored-by: George Pickett <gpickett00@gmail.com>
2026-01-15 03:51:55 +00:00
Peter Steinberger
a6e780b2f6 feat: add browser snapshot modes 2026-01-15 03:50:57 +00:00
Peter Steinberger
dfea2991c9 fix(daemon): clear launchd disabled state before bootstrap (#849) (thanks @ndraiman) 2026-01-15 03:35:24 +00:00
Netanel Draiman
d51a9ebb0e fix(daemon): enable launchd service before bootstrap
When a launchd service is uninstalled via bootout, macOS marks it as
disabled in /var/db/com.apple.xpc.launchd/disabled.*.plist. This persists
across reboots and plist recreation. Future bootstrap calls fail with
error 5 (I/O error) because the service is still marked disabled.

Fix: Call 'launchctl enable' before 'launchctl bootstrap' to clear the
disabled state, matching the fix already applied to the macOS Swift app
in GatewayLaunchAgentManager.swift.

Related: #306
2026-01-15 03:31:52 +00:00
Peter Steinberger
5c52dbf661 style: oxfmt fixes (#925) (thanks @grp06) 2026-01-15 03:22:54 +00:00
George Pickett
8f797f213e Logging: tolerate EIO console writes 2026-01-15 03:20:48 +00:00
Peter Steinberger
aa74e28112 fix(telegram): aggregate split inbound messages 2026-01-15 03:04:59 +00:00
Peter Steinberger
e569f15631 fix: scrub tuple items schemas for Gemini tools (#926) — thanks @grp06
Co-authored-by: George Pickett <gpickett00@gmail.com>
2026-01-15 02:59:35 +00:00
Peter Steinberger
eaace34233 fix: restore docker binds and PATH in sandbox exec (#873)
Thanks @akonyer.

Co-authored-by: Aaron Konyer <aaronk@gomodular.ca>
2026-01-15 02:58:20 +00:00
Peter Steinberger
1b24b6a02b fix: add plugin runtime registry 2026-01-15 02:44:45 +00:00
Peter Steinberger
2b4a68e276 feat: load channel plugins 2026-01-15 02:42:44 +00:00
Peter Steinberger
2fb2035dbf fix: normalize Claude CLI auth mode to oauth (#855)
Thanks @sebslight.

Co-authored-by: Sebastian <sebslight@gmail.com>
2026-01-15 02:29:43 +00:00
Peter Steinberger
765196d5c3 style(slack): satisfy oxfmt (#850) 2026-01-15 02:23:22 +00:00
Jonathan Wilkins
09ce6ff99e fix(slack): respect top-level requireMention config
The `channels.slack.requireMention` setting was defined in the schema
but never passed to `resolveSlackChannelConfig()`, which always
defaulted to `true`. This meant setting `requireMention: false` at the
top level had no effect—channels still required mentions.

Pass `slackCfg.requireMention` as `defaultRequireMention` to the
resolver and use it as the fallback instead of hardcoded `true`.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-15 02:17:27 +00:00
Peter Steinberger
6ffd7111a6 fix: add TUI status spinner 2026-01-15 02:11:12 +00:00
Peter Steinberger
7904a14af1 fix: render TUI pickers as overlays 2026-01-15 01:59:05 +00:00
Peter Steinberger
1b79730db8 style: apply oxfmt fixes 2026-01-15 01:53:14 +00:00
Peter Steinberger
ad8799522c feat(config): gate channel config writes 2026-01-15 01:41:15 +00:00
Peter Steinberger
f65668cb5f fix: suppress raw API error payloads (#924) (thanks @grp06)
Co-authored-by: George Pickett <gpickett00@gmail.com>
2026-01-15 01:34:19 +00:00
George Pickett
393d21d86c Format: fix report + telegram formatting 2026-01-15 01:27:16 +00:00
George Pickett
232c512502 Format: apply oxfmt fixes 2026-01-15 01:27:16 +00:00
George Pickett
8c1e6a82b2 Tests: add Gemini thoughtSignature for tool-call ids 2026-01-15 01:27:16 +00:00
George Pickett
2d54efe851 Embedded runner: suppress raw API error payloads (#919) 2026-01-15 01:27:16 +00:00
Peter Steinberger
c2a4f256c8 feat: add security audit + onboarding checkpoint 2026-01-15 01:25:11 +00:00
Peter Steinberger
326d4049da fix(telegram): migrate group config on supergroup IDs (#906)
Thanks @sleontenko.

Co-authored-by: Stan <sleontenko@users.noreply.github.com>
2026-01-15 01:10:30 +00:00
sleontenko
9b7c4b3884 feat(telegram): auto-migrate group config on supergroup migration
When a Telegram group is upgraded to a supergroup, the chat ID changes
(e.g., -123456 → -100123456). This causes the bot to lose its group
configuration since it's keyed by chat ID.

This change:
- Adds handler for `message:migrate_to_chat_id` event
- Logs the migration (old_id → new_id) for visibility
- If the old chat ID has config in channels.telegram.groups, automatically:
  - Copies the config to the new chat ID
  - Removes the old chat ID entry
  - Saves the updated config file

This eliminates the need to manually update clawdbot.json when groups
migrate to supergroups.
2026-01-15 01:10:30 +00:00
Peter Steinberger
bcde09ae91 feat: add /context prompt breakdown 2026-01-15 01:06:35 +00:00
Peter Steinberger
e5c8abab9e fix: preserve markdown code fences 2026-01-15 00:31:07 +00:00
Peter Steinberger
9f1a8be2bf refactor: unify markdown formatting pipeline 2026-01-15 00:31:07 +00:00
Peter Steinberger
bd7d362d3b refactor: unify markdown formatting pipeline 2026-01-15 00:31:07 +00:00
Peter Steinberger
0d0b77ded6 fix(telegram): wire delete action for message tool (#903) - thanks @sleontenko
Co-authored-by: Stan <sleontenko@users.noreply.github.com>
2026-01-15 00:29:53 +00:00