romtuck/openclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
5,463 Commits 258 Branches 39 Tags 276 MiB
78627ce7c2
Commit Graph

2718 Commits

Author SHA1 Message Date
Peter Steinberger
17e6354383
Merge pull request #748 from myfunc/main 
fix(bash): use PowerShell on Windows to capture system utility output
 2026-01-12 02:50:30 +00:00
Gabriel Trigo
99877e8e63 fix: align /think default with model reasoning 2026-01-12 02:50:13 +00:00
Peter Steinberger
98337a14b3 fix: rename bash tool to exec (#748) (thanks @myfunc) 2026-01-12 02:49:55 +00:00
Peter Steinberger
76c8fc8697 fix(sandbox): canonicalize agent main alias 2026-01-12 02:23:02 +00:00
myfunc
b33bd6aaeb fix(bash): use PowerShell on Windows to capture system utility output 
Windows system utilities like ipconfig, systeminfo, etc. write directly to
the console via WriteConsole API instead of stdout. When Node.js spawns
cmd.exe with piped stdio, these utilities produce empty output.

Changes:
- Switch from cmd.exe to PowerShell on Windows (properly redirects output)
- Disable detached mode on Windows (PowerShell doesn't pipe stdout when detached)
- Add windowsHide option to prevent console window flashing
- Update tests to use PowerShell-compatible syntax (Start-Sleep, semicolons)
 2026-01-12 02:13:02 +00:00
Peter Steinberger
4ced7b886e docs: fix browser CLI docs link 2026-01-12 02:09:10 +00:00
Peter Steinberger
2941a7002d fix(subagents): align wait timeout with run timeout 2026-01-12 02:06:43 +00:00
Peter Steinberger
b518fb29c6 test(gateway): cover main alias resolve 2026-01-12 02:06:43 +00:00
Peter Steinberger
f504bfdde8 refactor(gateway): use canonical session store keys 2026-01-12 02:06:43 +00:00
Peter Steinberger
c1236e86fa test: fix windows nix config path assertion 2026-01-12 02:05:38 +00:00
Peter Steinberger
e3960cde3f test: add normalizeConfigPaths unit test 2026-01-12 01:55:55 +00:00
Peter Steinberger
ecc6243edc test: cover tilde path expansion 2026-01-12 01:53:42 +00:00
Peter Steinberger
328d47f1df fix: normalize ~ in path config 2026-01-12 01:53:42 +00:00
Peter Steinberger
28f97e6152 refactor(sandbox): normalize main session aliases 2026-01-12 01:37:56 +00:00
Peter Steinberger
23a0bf2abe fix(plugins): extract archives without system tar 2026-01-12 01:36:18 +00:00
Peter Steinberger
07b93e1d26 test: run npm pack via npm-cli.js 2026-01-12 01:31:26 +00:00
Peter Steinberger
5bdb9c0e99 style: format plugin install test 2026-01-12 01:27:01 +00:00
Peter Steinberger
6947ab18dc fix: load plugin packages from config dirs 2026-01-12 01:25:56 +00:00
Peter Steinberger
177ad3f06d test: pack plugin archives via npm 2026-01-12 01:25:40 +00:00
Peter Steinberger
58a12a757e fix(sandbox): avoid sandboxing main DM sessions 2026-01-12 01:24:44 +00:00
Peter Steinberger
f13ae50ff8 test: plugin install + docker e2e 2026-01-12 01:16:42 +00:00
Peter Steinberger
2f4a248314 feat: plugin system + voice-call 2026-01-12 01:16:39 +00:00
Peter Steinberger
9877733748 fix(gateway): canonicalize main session aliases 2026-01-12 01:05:43 +00:00
user
d4e9f23ee9 fix(gateway): normalize session key to canonical form before store writes 
Ensure 'main' alias is always stored as 'agent:main:main' to prevent
duplicate entries. Also update loadSessionEntry to check both forms
when looking up entries.

Fixes duplicate main sessions in session store.
 2026-01-12 00:53:20 +00:00
user
7d6f17d77f fix(subagent): make announce prompt more emphatic 
The previous prompt was too permissive about skipping announcements.
Updated to strongly encourage announcing results since the requester
is waiting for a response.

- Add 'You MUST announce your result' instruction
- Clarify ANNOUNCE_SKIP is only for complete failures
- Improve guidance on providing useful summaries
 2026-01-12 00:52:36 +00:00
user
0ed7ea698a fix(subagent): wait for completion before announce 
The previous immediate probe (timeoutMs: 0) only caught already-completed
runs. Cross-process spawns need to actually wait via agent.wait RPC for
the gateway to signal completion, then trigger the announce flow.

- Rename probeImmediateCompletion to waitForSubagentCompletion
- Use 10 minute wait timeout for agent.wait RPC
- Remove leftover debug console.log statements
 2026-01-12 00:52:36 +00:00
Peter Steinberger
74526645eb test: cover unset docker env vars 2026-01-12 00:46:55 +00:00
Peter Steinberger
cb095c8606 test: fix includes tests on windows 2026-01-12 00:39:14 +00:00
Peter Steinberger
9c8967ef5d style: biome fixes 2026-01-12 00:32:47 +00:00
Peter Steinberger
720b9dd116 fix: make codex keychain platform-aware 2026-01-12 00:32:47 +00:00
Peter Steinberger
9f9f6b75e7 test: expand include coverage 2026-01-12 00:30:26 +00:00
Peter Steinberger
26cbbafc86 fix: skip pnpm patch fallback 2026-01-12 00:28:34 +00:00
Peter Steinberger
67743325ee fix: reset session after compaction overflow 2026-01-12 00:28:16 +00:00
Peter Steinberger
32df2ef7bd fix: stabilize invalid-connect handshake response 2026-01-12 00:19:47 +00:00
Peter Steinberger
e3e3498a4b fix: guard config includes (#731) (thanks @pasogott) 2026-01-12 00:12:03 +00:00
sheeek
53d3134fe8 refactor(config): simplify includes with class-based processor 
- Replace free functions with IncludeProcessor class
- Simplify IncludeResolver interface: { readFile, parseJson }
- Break down loadFile into focused private methods
- Use reduce() for array include merging
- Cleaner separation of concerns
 2026-01-12 00:08:27 +00:00
sheeek
e6400b0b0f refactor(config): extract includes logic to separate module 
- Move $include resolution to src/config/includes.ts
- Simplify io.ts by importing from includes module
- Cleaner API: resolveConfigIncludes(obj, configPath, resolver?)
- Re-export errors from io.ts for backwards compatibility
- Rename test file to match module name
 2026-01-12 00:08:27 +00:00
sheeek
15d286b617 feat(config): add $include directive for modular configs 
Adds support for splitting clawdbot.json into multiple files using the
$include directive. This enables:

- Single file includes: { "$include": "./agents.json5" }
- Multiple file merging: { "$include": ["./a.json5", "./b.json5"] }
- Nested includes (up to 10 levels deep)
- Sibling key merging with includes

Features:
- Relative paths resolved from including file
- Absolute paths supported
- Circular include detection
- Clear error messages with resolved paths

Use case: Per-client agent configs for isolated sandboxed environments
(e.g., legal case management with strict data separation).
 2026-01-12 00:08:27 +00:00
Peter Steinberger
4b51c96e4e fix: apply model extra params without overwriting stream (#732) (thanks @peschee) 2026-01-12 00:03:48 +00:00
Peter Siska
d9960d83c1 style: fix formatting (biome) 2026-01-12 00:03:25 +00:00
Peter Siska
32affaee02 feat: wire up model extraParams (temperature, maxTokens) to pi agent 
- Use resolveExtraParams() which was defined but unused
- Create streamFn wrapper that injects config-driven params
- Apply to both compaction and run sessions

Config path: agents.defaults.models["provider/model"].params.temperature

Example:
  agents.defaults.models["anthropic/claude-sonnet-4"].params.temperature = 0.7
  agents.defaults.models["openai/gpt-4"].params.maxTokens = 8192
 2026-01-12 00:03:24 +00:00
Peter Steinberger
60430fcd2e chore: harden installer and add smoke ci 2026-01-12 00:00:54 +00:00
Peter Steinberger
55e55c8825 fix: preserve handshake close code and test truncation 2026-01-11 23:57:37 +00:00
Peter Steinberger
146f7ab433 fix: surface handshake reasons 2026-01-11 23:46:20 +00:00
Peter Steinberger
1f95d7fc8b fix: read codex keychain credentials 2026-01-11 23:39:10 +00:00
Peter Steinberger
3a8bfc0a5d
Merge pull request #733 from AbhisekBasu1/patch-1 
Readme Fix: Update section title from 'macOS app' to 'Apps'
 2026-01-11 23:38:38 +00:00
Peter Steinberger
26cc2bd384 fix: land PR #733 (thanks @AbhisekBasu1) 2026-01-11 23:37:44 +00:00
Peter Steinberger
248c731e78 test: expand voice-call coverage 2026-01-11 23:35:47 +00:00
Peter Steinberger
4181e72977 fix: strip markup heartbeat acks 2026-01-11 23:26:51 +00:00
Peter Steinberger
367baaca20 feat: implement voice-call plugin 2026-01-11 23:23:14 +00:00
Ayaan Zaidi
f082f1e06e fix: add discord channel actions 2026-01-11 22:32:17 +05:30
Ayaan Zaidi
0d9a1009ff fix: format discord parentId 2026-01-11 22:28:05 +05:30
Ayaan Zaidi
33aaccd1c3
Merge pull request #728 from pkrmf/feature/dm-history-limit 
feat: add configurable DM history limits with per-chat overrides
 2026-01-11 22:25:12 +05:30
Ayaan Zaidi
a4385dc920 fix: skip dm history limit for non-dm sessions 2026-01-11 22:18:15 +05:30
Nicholas Spisak
d63eae528c
feat(discord): expose channel management actions via message tool 
Add channel-create, channel-edit, channel-delete, channel-move,
category-create, category-edit, and category-delete actions to the
unified message tool. These actions were already implemented in the
Discord-specific handler but weren't accessible via the pi_message tool.

Changes:
- Add 7 new channel/category management actions to MessageActionSchema
- Add parameters: name, type, parentId, topic, position, nsfw,
  rateLimitPerUser, categoryId
- Gate actions behind discord.actions.channels (disabled by default)
- Add execute handlers routing to existing Discord action handlers
- Update Discord skill SKILL.md with documentation

Channel types: 0=text, 2=voice, 4=category
 2026-01-11 10:01:32 -06:00
Ayaan Zaidi
68f6f3f0bd fix: normalize telegram command mentions 2026-01-11 21:06:04 +05:30
Marc Terns
23717c5036 test: add comprehensive per-DM override tests for all providers 2026-01-11 08:55:32 -06:00
Marc Terns
54abf4b0d7 feat: add per-DM history limit overrides 2026-01-11 08:53:50 -06:00
Marc Terns
ab9ea827a4 refactor: move dmHistoryLimit to provider-level config 2026-01-11 08:38:19 -06:00
Marc Terns
a005a97fef feat: add configurable DM history limit 2026-01-11 08:21:14 -06:00
Peter Steinberger
933c157092 test: add plugin docker e2e 2026-01-11 12:21:45 +00:00
Peter Steinberger
cf0c72a557 feat: add plugin architecture 2026-01-11 12:11:12 +00:00
Peter Steinberger
7acd26a2fc
Move provider to a plugin-architecture (#661) 
* refactor: introduce provider plugin registry

* refactor: move provider CLI to plugins

* docs: add provider plugin implementation notes

* refactor: shift provider runtime logic into plugins

* refactor: add plugin defaults and summaries

* docs: update provider plugin notes

* feat(commands): add /commands slash list

* Auto-reply: tidy help message

* Auto-reply: fix status command lint

* Tests: align google shared expectations

* Auto-reply: tidy help message

* Auto-reply: fix status command lint

* refactor: move provider routing into plugins

* test: align agent routing expectations

* docs: update provider plugin notes

* refactor: route replies via provider plugins

* docs: note route-reply plugin hooks

* refactor: extend provider plugin contract

* refactor: derive provider status from plugins

* refactor: unify gateway provider control

* refactor: use plugin metadata in auto-reply

* fix: parenthesize cron target selection

* refactor: derive gateway methods from plugins

* refactor: generalize provider logout

* refactor: route provider logout through plugins

* refactor: move WhatsApp web login methods into plugin

* refactor: generalize provider log prefixes

* refactor: centralize default chat provider

* refactor: derive provider lists from registry

* refactor: move provider reload noops into plugins

* refactor: resolve web login provider via alias

* refactor: derive CLI provider options from plugins

* refactor: derive prompt provider list from plugins

* style: apply biome lint fixes

* fix: resolve provider routing edge cases

* docs: update provider plugin refactor notes

* fix(gateway): harden agent provider routing

* refactor: move provider routing into plugins

* refactor: move provider CLI to plugins

* refactor: derive provider lists from registry

* fix: restore slash command parsing

* refactor: align provider ids for schema

* refactor: unify outbound target resolution

* fix: keep outbound labels stable

* feat: add msteams to cron surfaces

* fix: clean up lint build issues

* refactor: localize chat provider alias normalization

* refactor: drive gateway provider lists from plugins

* docs: update provider plugin notes

* style: format message-provider

* fix: avoid provider registry init cycles

* style: sort message-provider imports

* fix: relax provider alias map typing

* refactor: move provider routing into plugins

* refactor: add plugin pairing/config adapters

* refactor: route pairing and provider removal via plugins

* refactor: align auto-reply provider typing

* test: stabilize telegram media mocks

* docs: update provider plugin refactor notes

* refactor: pluginize outbound targets

* refactor: pluginize provider selection

* refactor: generalize text chunk limits

* docs: update provider plugin notes

* refactor: generalize group session/config

* fix: normalize provider id for room detection

* fix: avoid provider init in system prompt

* style: formatting cleanup

* refactor: normalize agent delivery targets

* test: update outbound delivery labels

* chore: fix lint regressions

* refactor: extend provider plugin adapters

* refactor: move elevated/block streaming defaults to plugins

* refactor: defer outbound send deps to plugins

* docs: note plugin-driven streaming/elevated defaults

* refactor: centralize webchat provider constant

* refactor: add provider setup adapters

* refactor: delegate provider add config to plugins

* docs: document plugin-driven provider add

* refactor: add plugin state/binding metadata

* refactor: build agent provider status from plugins

* docs: note plugin-driven agent bindings

* refactor: centralize internal provider constant usage

* fix: normalize WhatsApp targets for groups and E.164 (#631) (thanks @imfing)

* refactor: centralize default chat provider

* refactor: centralize WhatsApp target normalization

* refactor: move provider routing into plugins

* refactor: normalize agent delivery targets

* chore: fix lint regressions

* fix: normalize WhatsApp targets for groups and E.164 (#631) (thanks @imfing)

* feat: expand provider plugin adapters

* refactor: route auto-reply via provider plugins

* fix: align WhatsApp target normalization

* fix: normalize WhatsApp targets for groups and E.164 (#631) (thanks @imfing)

* refactor: centralize WhatsApp target normalization

* feat: add /config chat config updates

* docs: add /config get alias

* feat(commands): add /commands slash list

* refactor: centralize default chat provider

* style: apply biome lint fixes

* chore: fix lint regressions

* fix: clean up whatsapp allowlist typing

* style: format config command helpers

* refactor: pluginize tool threading context

* refactor: normalize session announce targets

* docs: note new plugin threading and announce hooks

* refactor: pluginize message actions

* docs: update provider plugin actions notes

* fix: align provider action adapters

* refactor: centralize webchat checks

* style: format message provider helpers

* refactor: move provider onboarding into adapters

* docs: note onboarding provider adapters

* feat: add msteams onboarding adapter

* style: organize onboarding imports

* fix: normalize msteams allowFrom types

* feat: add plugin text chunk limits

* refactor: use plugin chunk limit fallbacks

* feat: add provider mention stripping hooks

* style: organize provider plugin type imports

* refactor: generalize health snapshots

* refactor: update macOS health snapshot handling

* docs: refresh health snapshot notes

* style: format health snapshot updates

* refactor: drive security warnings via plugins

* docs: note provider security adapter

* style: format provider security adapters

* refactor: centralize provider account defaults

* refactor: type gateway client identity constants

* chore: regen gateway protocol swift

* fix: degrade health on failed provider probe

* refactor: centralize pairing approve hint

* docs: add plugin CLI command references

* refactor: route auth and tool sends through plugins

* docs: expand provider plugin hooks

* refactor: document provider docking touchpoints

* refactor: normalize internal provider defaults

* refactor: streamline outbound delivery wiring

* refactor: make provider onboarding plugin-owned

* refactor: support provider-owned agent tools

* refactor: move telegram draft chunking into telegram module

* refactor: infer provider tool sends via extractToolSend

* fix: repair plugin onboarding imports

* refactor: de-dup outbound target normalization

* style: tidy plugin and agent imports

* refactor: data-drive provider selection line

* fix: satisfy lint after provider plugin rebase

* test: deflake gateway-cli coverage

* style: format gateway-cli coverage test

* refactor(provider-plugins): simplify provider ids

* test(pairing-cli): avoid provider-specific ternary

* style(macos): swiftformat HealthStore

* refactor(sandbox): derive provider tool denylist

* fix(sandbox): avoid plugin init in defaults

* refactor(provider-plugins): centralize provider aliases

* style(test): satisfy biome

* refactor(protocol): v3 providers.status maps

* refactor(ui): adapt to protocol v3

* refactor(macos): adapt to protocol v3

* test: update providers.status v3 fixtures

* refactor(gateway): map provider runtime snapshot

* test(gateway): update reload runtime snapshot

* refactor(whatsapp): normalize heartbeat provider id

* docs(refactor): update provider plugin notes

* style: satisfy biome after rebase

* fix: describe sandboxed elevated in prompt

* feat(gateway): add agent image attachments + live probe

* refactor: derive CLI provider options from plugins

* fix(gateway): harden agent provider routing

* fix(gateway): harden agent provider routing

* refactor: align provider ids for schema

* fix(protocol): keep agent provider string

* fix(gateway): harden agent provider routing

* fix(protocol): keep agent provider string

* refactor: normalize agent delivery targets

* refactor: support provider-owned agent tools

* refactor(config): provider-keyed elevated allowFrom

* style: satisfy biome

* fix(gateway): appease provider narrowing

* style: satisfy biome

* refactor(reply): move group intro hints into plugin

* fix(reply): avoid plugin registry init cycle

* refactor(providers): add lightweight provider dock

* refactor(gateway): use typed client id in connect

* refactor(providers): document docks and avoid init cycles

* refactor(providers): make media limit helper generic

* fix(providers): break plugin registry import cycles

* style: satisfy biome

* refactor(status-all): build providers table from plugins

* refactor(gateway): delegate web login to provider plugin

* refactor(provider): drop web alias

* refactor(provider): lazy-load monitors

* style: satisfy lint/format

* style: format status-all providers table

* style: swiftformat gateway discovery model

* test: make reload plan plugin-driven

* fix: avoid token stringification in status-all

* refactor: make provider IDs explicit in status

* feat: warn on signal/imessage provider runtime errors

* test: cover gateway provider runtime warnings in status

* fix: add runtime kind to provider status issues

* test: cover health degradation on probe failure

* fix: keep routeReply lightweight

* style: organize routeReply imports

* refactor(web): extract auth-store helpers

* refactor(whatsapp): lazy login imports

* refactor(outbound): route replies via plugin outbound

* docs: update provider plugin notes

* style: format provider status issues

* fix: make sandbox scope warning wrap-safe

* refactor: load outbound adapters from provider plugins

* docs: update provider plugin outbound notes

* style(macos): fix swiftformat lint

* docs: changelog for provider plugins

* fix(macos): satisfy swiftformat

* fix(macos): open settings via menu action

* style: format after rebase

* fix(macos): open Settings via menu action

---------

Co-authored-by: LK <luke@kyohere.com>
Co-authored-by: Luke K (pr-0f3t) <2609441+lc0rp@users.noreply.github.com>
Co-authored-by: Xin <xin@imfing.com>
 2026-01-11 11:45:25 +00:00
Peter Steinberger
23eec7d841 fix: update heartbeat prompt 2026-01-11 11:35:52 +00:00
Peter Steinberger
a3747b1ee3 fix: add compaction headroom for memory writes 2026-01-11 11:25:15 +00:00
Peter Steinberger
96e4fdb443 test: skip codex refresh token reuse 2026-01-11 11:24:25 +00:00
Peter Steinberger
6b46217d19 fix: route subagent transcripts and keep tool action enums (#708) (thanks @xMikeMickelson) 2026-01-11 11:19:38 +00:00
user
dc3c733612 fix(agent): use session key agentId for transcript path 
Cross-agent subagent spawns wrote transcripts to the spawner's agent
directory instead of the target agent's directory. For example, when
main spawned a codex subagent with session key agent:codex:subagent:...,
the transcript went to agents/main/sessions/ instead of agents/codex/sessions/.

Pass sessionAgentId to resolveSessionFilePath so transcripts are written
to the correct agent's session directory.
 2026-01-11 11:11:43 +00:00
Peter Steinberger
580791088c test: cover messaging tool error fallback (#717) 2026-01-11 11:10:03 +00:00
Chris Taylor
fb1fc5feee fix(message-tool): strip reply/media tags from content in send/thread-reply actions 2026-01-11 11:04:07 +00:00
Chris Taylor
3da3e201de Agents: harden message tool sends 2026-01-11 11:04:07 +00:00
Peter Steinberger
2ebad5af1c test: cover cron cli model overrides 2026-01-11 10:56:46 +00:00
Peter Steinberger
0590365683 style: format cleanup commands 2026-01-11 10:54:33 +00:00
Peter Steinberger
8e3f7c45d2
Merge pull request #711 from mjrussell/feat/cron-model-override 
feat(cron): add --model flag to cron add/edit commands
 2026-01-11 10:53:42 +00:00
Peter Steinberger
a8a4993ffd fix: trim cron model overrides and doc guidance (#711) (thanks @mjrussell) 2026-01-11 10:52:40 +00:00
Matthew Russell
314e075df2 feat(cron): add --model flag to cron add/edit commands 
Expose the existing model override capability via CLI flags:
- Add --model to cron add and cron edit commands
- Document model and thinking overrides in cron-jobs.md
- Add CLI example showing model/thinking usage

The backend already supported model in agentTurn payloads;
this change exposes it through the CLI interface.
 2026-01-11 10:49:34 +00:00
Peter Steinberger
0ef07bc142 test: extend discord tool-result timeout 2026-01-11 10:48:49 +00:00
Peter Steinberger
4a166cf227 fix: add update env regression test (#713) (thanks @danielz1z) 2026-01-11 10:48:46 +00:00
danielz1z
4570e1db7d fix(update): merge custom env with process.env in spawn 
When the update runner passes custom env vars (like CLAWDBOT_UPDATE_IN_PROGRESS),
the current code uses `env ?? process.env` which replaces the entire environment
instead of merging — losing PATH, HOME, etc.

This causes the doctor step to fail with 'node: No such file or directory'.

Fix: merge custom env with process.env instead of replacing it.
 2026-01-11 10:39:07 +00:00
Peter Steinberger
11a3b5aac9 style: biome fixes 2026-01-11 10:35:16 +00:00
Peter Steinberger
11c8db14a1 feat: add reset/uninstall commands 2026-01-11 10:23:52 +00:00
Peter Steinberger
323200b551 test(live): harden gateway probes 2026-01-11 04:46:30 +00:00
Peter Steinberger
dbe156e881 fix(agents): sanitize transcripts for strict tool APIs 2026-01-11 04:46:18 +00:00
Peter Steinberger
f00038b383 fix(testing): stabilize live model runs 2026-01-11 04:22:35 +00:00
Peter Steinberger
343b6ac31b feat: add onboard reset option 2026-01-11 05:04:36 +01:00
Peter Steinberger
9046296ed3 fix: clarify sub-agent sandbox limits 2026-01-11 05:04:14 +01:00
Peter Steinberger
b4e9a0c975 style: add blank line after note imports 2026-01-11 05:01:50 +01:00
Peter Steinberger
71791d5a6a fix: restore ZAI provider preference 2026-01-11 04:58:37 +01:00
Peter Steinberger
7acdaad04e style: fix note import spacing 2026-01-11 04:54:19 +01:00
Peter Steinberger
b7ac9095e6 fix: skip tool-only reasoning replay 2026-01-11 04:52:16 +01:00
Peter Steinberger
30348e41c6 test: stabilize doctor + sandbox tests 2026-01-11 04:45:04 +01:00
Peter Steinberger
7343597075 chore: keep gate green 2026-01-11 04:42:44 +01:00
Peter Steinberger
50e62122bb chore: format sandbox skills test 2026-01-11 04:39:42 +01:00
Peter Steinberger
eeae5ce7fd fix: stabilize notes and reasoning replay 2026-01-11 04:37:06 +01:00
Peter Steinberger
57e6a9a762 fix: clamp z.ai developer role 2026-01-11 04:28:30 +01:00
Peter Steinberger
7660a78330 fix: mirror skills for read-only sandbox 2026-01-11 04:24:19 +01:00
Peter Steinberger
29884f8d6f fix: wrap clack notes for cleaner boxes 2026-01-11 04:23:43 +01:00
Peter Steinberger
76c5bff7d6 test: cover whoami command 2026-01-11 04:20:34 +01:00
Peter Steinberger
38604acd94 fix: tighten WhatsApp ack reactions and migrate config (#629) (thanks @pasogott) 2026-01-11 04:11:04 +01:00
sheeek
c928df7237 fix: remove any casts in backward compat code 2026-01-11 04:10:43 +01:00
sheeek
30b4c14296 style: fix biome linting in ack-reaction tests 2026-01-11 04:10:43 +01:00
sheeek
2daead27cf feat(whatsapp): redesign ack-reaction as whatsapp-specific feature 
- Move config from messages.ackReaction to whatsapp.ackReaction
- New structure: {emoji, direct, group} with granular control
- Support per-account overrides in whatsapp.accounts.*.ackReaction
- Add Zod schema validation for new config
- Maintain backward compatibility with old messages.ackReaction format
- Update tests to new config structure (14 tests, all passing)
- Add comprehensive documentation in docs/providers/whatsapp.md
- Timing: reactions sent immediately upon message receipt (before bot reply)

Breaking changes:
- Config moved from messages.ackReaction to whatsapp.ackReaction
- Scope values changed: 'all'/'direct'/'group-all'/'group-mentions'
  → direct: boolean + group: 'always'/'mentions'/'never'
- Old config still supported via fallback for smooth migration
 2026-01-11 04:10:43 +01:00
sheeek
d38b232724 chore: fix linting issues in ack-reaction feature 
- Remove unused mock variables in tests
- Remove unused ackReactionScope variables in simple test cases
- Fix line length for ackReactionScope declaration
- All lint checks passing (0 warnings, 0 errors)
- All tests passing (8/8)
 2026-01-11 04:10:43 +01:00
sheeek
c3587d6cae fix(whatsapp): ack reaction logic for group activation 'always' mode 
- Fix bug where ack reaction was not sent when group activation is 'always'
- When requireMention=false (activation: always), always send reaction
- Add test case for activation='always' scenario
- Update inline comments for clarity
 2026-01-11 04:10:43 +01:00
sheeek
b3b507c6ea feat(whatsapp): add ack reaction support after successful replies 
- Add automatic emoji reactions on inbound WhatsApp messages
- Support all ackReactionScope modes: all, direct, group-all, group-mentions
- Reaction is sent AFTER successful reply (unlike Telegram/Discord)
- Errors are logged with proper context
- Add comprehensive test suite for ack reaction logic

Config usage:
  messages:
    ackReaction: "👀"
    ackReactionScope: "group-mentions"  # default

Closes: WhatsApp ack-reaction feature request
 2026-01-11 04:10:42 +01:00
Peter Steinberger
579b00503f style: format onboard providers 2026-01-11 04:08:26 +01:00
Peter Steinberger
36a21ae9b0 fix: improve telegram configuration safety 2026-01-11 03:57:52 +01:00
Peter Steinberger
11f897b7df fix(gateway): show connect vs RPC status 2026-01-11 03:57:52 +01:00
Peter Steinberger
1f9b4e3af6 fix: send heartbeat reasoning (#694) (thanks @antons) 2026-01-11 03:51:51 +01:00
Peter Steinberger
4ce2e73521 fix: improve provider issue formatting 2026-01-11 03:51:51 +01:00
Anton Sotkov
c7caa9a87d fix: deliver reasoning alongside HEARTBEAT_OK 2026-01-11 03:51:51 +01:00
Anton Sotkov
7a518166bb fix: persist reasoning across session resets 2026-01-11 03:51:51 +01:00
Peter Steinberger
9d802abd9a test: cover docker setup env plumbing 2026-01-11 03:45:45 +01:00
Peter Steinberger
480bf916e2 fix(status): simplify footer guidance 2026-01-11 03:44:28 +01:00
Peter Steinberger
9a4021a277
Merge pull request #703 from mteam88/openrouter-auth-config 
Openrouter auth config (AI)
 2026-01-11 02:44:24 +00:00
Peter Steinberger
2b07a2a8ab fix: stabilize onboarding auth tests (#703) (thanks @mteam88) 2026-01-11 03:42:27 +01:00
Matthew
77bc11f91c chore: format OpenRouter auth edits 2026-01-11 03:35:45 +01:00
Matthew
7890bd7369 CLI: reuse OpenRouter credentials 2026-01-11 03:35:45 +01:00
Matthew
b6982236a6 CLI: add OpenRouter auth choice 2026-01-11 03:35:45 +01:00
Peter Steinberger
494f41d575 docs(status): make status first-step 2026-01-11 03:34:33 +01:00
Peter Steinberger
20b4e2b859 fix: stabilize live probes and docs 2026-01-11 02:26:39 +00:00
Peter Steinberger
6668805aca fix(agents): enforce single-writer session files 2026-01-11 02:25:45 +00:00
Peter Steinberger
3a113b7752 fix: stabilize cli runner output 2026-01-11 02:25:45 +00:00
Peter Steinberger
9b6bc0e66b fix: reset unsigned launchd overrides (#695) (thanks @jeffersonwarrior) 2026-01-11 03:19:24 +01:00
Peter Steinberger
5ec3663748 fix: guard update spinner output (#701) (thanks @bjesuiter) 2026-01-11 03:03:09 +01:00
Benjamin Jesuiter
f3bd6e4957 fix(update): use git status --porcelain for dirty check cross-platform 2026-01-11 03:00:43 +01:00
Benjamin Jesuiter
6cb55eaaa7 feat(update): show stderr for failed steps 2026-01-11 03:00:43 +01:00
Benjamin Jesuiter
3f27b23d5a fix(update): remove command hint from step labels 2026-01-11 03:00:43 +01:00
Benjamin Jesuiter
4102e2f1b8 refactor(update): simplify progress with proper exit codes 2026-01-11 03:00:43 +01:00
Benjamin Jesuiter
35d42be828 fix(update): show skipped status with warning indicator for dirty repo 2026-01-11 03:00:43 +01:00
Benjamin Jesuiter
6a2b8328df fix(update): restore reason in summary 2026-01-11 03:00:43 +01:00
Benjamin Jesuiter
cc8e6e00a0 fix(update): hide steps in summary when shown live, fix command hint 2026-01-11 03:00:43 +01:00
Benjamin Jesuiter
6e0c1cb051 fix(update): show each step with spinner as it runs 2026-01-11 03:00:43 +01:00
Benjamin Jesuiter
8f9aa3e8c5 fix(progress): start spinner immediately when delayMs is 0 2026-01-11 03:00:43 +01:00
Benjamin Jesuiter
88c404bcfc feat(update): add progress spinner during update steps 2026-01-11 03:00:43 +01:00
Peter Steinberger
4759633df1 fix(cli): keep build/lint green 2026-01-11 02:44:24 +01:00
Peter Steinberger
e824b3514b fix(status): improve diagnostics and output 2026-01-11 02:42:24 +01:00
Peter Steinberger
02270abc87 feat: add codex cli backend 2026-01-11 01:39:30 +00:00
Peter Steinberger
2d74119a08 test: cover auto-reply command gating 2026-01-11 02:27:16 +01:00
Peter Steinberger
e0bf86f06c feat: improve gateway services and auto-reply commands 2026-01-11 02:27:16 +01:00
Peter Steinberger
a32021dc3e fix: inject image paths for cli backends 2026-01-11 00:55:22 +00:00
Peter Steinberger
4cf3e84b39 test: add CLI backend image probe 2026-01-11 00:55:22 +00:00
Peter Steinberger
24c3ab6fe0 fix: unblock claude-cli live runs 2026-01-11 00:55:22 +00:00
Peter Steinberger
d8f1124d59 feat: add CLI backend fallback 2026-01-11 00:55:22 +00:00
Peter Steinberger
07be761779 feat: add sandbox browser control allowlists 2026-01-11 01:52:32 +01:00
Peter Steinberger
b0b4b33b6b fix: update gateway auth docs and clients 2026-01-11 01:51:24 +01:00
Peter Steinberger
d33285a9cd fix: harden gateway auth defaults 2026-01-11 01:51:24 +01:00
Peter Steinberger
3e6d27ac4e fix(status): show gateway auth when reachable 2026-01-11 01:46:37 +01:00
Peter Steinberger
506cc9e7a1 chore(release): 2026.1.11-3 2026-01-11 01:38:15 +01:00
Peter Steinberger
b339097179 style: format browser tool wiring 2026-01-11 01:34:45 +01:00
Peter Steinberger
07eed3de56 docs(status): add diagnostics commands 2026-01-11 01:31:56 +01:00
Peter Steinberger
326fb04d12 feat: add browser target selection for sandboxed agents 2026-01-11 01:31:56 +01:00
Peter Steinberger
362fc3e235
Merge pull request #692 from peschee/fix/whatsapp-lid-mention-detection 
fix(whatsapp): pass authDir to jidToE164 for LID mention detection
 2026-01-11 00:16:03 +00:00
Peter Steinberger
6444258ad3 fix: handle WhatsApp LID mentions (#692) (thanks @peschee) 2026-01-11 01:14:57 +01:00
Peter Steinberger
318f59ec3e fix(status): show token previews 2026-01-11 01:11:46 +01:00
Peter Steinberger
57dafec0ec docs(status): add troubleshooting footer 2026-01-11 01:06:58 +01:00
Peter Steinberger
518dfd4e42 fix(status): provider setup vs warn 2026-01-11 01:05:06 +01:00
Peter Siska
9cb1bfa1c1 fix(whatsapp): pass authDir to jidToE164 for LID mention detection 
WhatsApp group mentions using the new Linked ID format (@lid) were not
being detected because jidToE164() was called without the authDir needed
to find the LID reverse mapping files.

Now isBotMentioned() and debugMention() accept an optional authDir
parameter, which is passed through from account.authDir.
 2026-01-11 01:04:10 +01:00
Peter Steinberger
5fa3ac1e01 fix(status): full-width tables + better diagnosis 2026-01-11 00:54:27 +01:00
Peter Steinberger
7c76561569 fix: dedupe inbound messages across providers 2026-01-11 00:12:25 +01:00
Peter Steinberger
1d9199b529 style(test): format update-cli test 2026-01-10 23:46:11 +01:00
Peter Steinberger
eff092268a fix(test): avoid update-cli import timeout 2026-01-10 23:40:27 +01:00
Peter Steinberger
621f710d60 fix(mac): add tailnet discovery fallback and debug CLI 2026-01-10 23:39:27 +01:00
Shadow
c731a87d07
Discord: add fetch message action 2026-01-10 16:38:20 -06:00
Peter Steinberger
786eac1d6f test(cli): avoid update-cli import timeout 2026-01-10 23:35:04 +01:00
Peter Steinberger
1eb50ffac4 feat(status): improve status output 2026-01-10 23:32:07 +01:00
Peter Steinberger
3166cc911b
Heartbeat: optional reasoning delivery (#690) 
* feat: expose heartbeat reasoning output

* docs(changelog): mention heartbeat reasoning toggle
 2026-01-10 22:26:20 +00:00
Peter Steinberger
4d0e74ab6c fix: cover extra thinking tags (#688) (thanks @theglove44) 2026-01-10 23:23:23 +01:00
Chris Taylor
a580639abf fix(agents): strip <thought> and <antthinking> tags from output 2026-01-10 23:19:58 +01:00
Peter Steinberger
494743a4e5 feat: run doctor after restart 2026-01-10 23:14:55 +01:00
Jonathan Wilkins
0afa370869 fix: add 'usage limit' to rate limit detection patterns 
OpenAI/ChatGPT returns "You have hit your ChatGPT usage limit (plus plan)"
when users exceed their plan quota. This error wasn't being recognized as a
rate limit, so fallback to alternative models wasn't triggering.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-10 23:11:06 +01:00
Peter Steinberger
08cc8f2281 refactor(agents): extract transcript repair module 2026-01-10 22:07:25 +00:00
Peter Steinberger
708f04b02f fix: keep mock openai responses requests 2026-01-10 22:56:08 +01:00
Peter Steinberger
1c257f170a
Gateway: disable OpenAI HTTP chat completions by default (#686) 
* feat(gateway): disable OpenAI chat completions HTTP by default

* test(gateway): deflake mock OpenAI tool-calling

* docs(changelog): note OpenAI HTTP endpoint default-off
 2026-01-10 21:55:54 +00:00
Peter Steinberger
06052640e8
Merge pull request #685 from carlulsoe/fix/daemon-restart-feedback 
fix(cli): improve daemon restart feedback [AI-assisted]
 2026-01-10 21:53:00 +00:00
Peter Steinberger
fa61699f9a fix: polish restart feedback + stabilize tests (#685) (thanks @carlulsoe) 2026-01-10 22:52:09 +01:00
Peter Steinberger
98377c7c6b fix(agents): harden tool transcript repair 2026-01-10 21:45:15 +00:00
Peter Steinberger
805a29252e test: add setup-token live smoke 2026-01-10 21:45:15 +00:00
Kit
f699dc3777 fix(cli): improve daemon restart feedback 
- runDaemonRestart() now returns Promise<boolean> indicating success
- update command only shows success when restart actually happened
- Fixes missing reasoningLevel type in compactEmbeddedPiSession

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Carl Ulsøe Christensen <carlulsoe@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-10 22:44:31 +01:00
Peter Steinberger
ad17966e2f fix(doctor): warn on opencode overrides 2026-01-10 22:44:31 +01:00
Peter Steinberger
1110d96769 feat(gateway): add config toggle for chat completions endpoint 2026-01-10 22:39:06 +01:00
Peter Steinberger
050c1c5391 fix(agents): include reasoningLevel in compaction params 2026-01-10 22:39:06 +01:00
Ruby
a6a9930a34
fix: enable block streaming for all providers (#684) 2026-01-10 15:25:55 -06:00
Peter Steinberger
6d70524aa8 fix: add reasoning visibility hint 2026-01-10 22:24:22 +01:00
Peter Steinberger
aa30995aa1 test(live): add provider filters + google skip rules 2026-01-10 21:16:59 +00:00
Peter Steinberger
0d00d6dfd4 style(gateway): format openai-http 2026-01-10 22:11:15 +01:00
Peter Steinberger
6546a1a23a feat(gateway): allow agent via model 2026-01-10 22:11:12 +01:00
Peter Steinberger
dafa8a2881 feat(gateway): add OpenAI-compatible HTTP endpoint 2026-01-10 22:11:04 +01:00
Peter Steinberger
ab314a22e0 chore: refresh pi-ai patch repro note 2026-01-10 20:55:57 +00:00
Peter Steinberger
9790b39d80 feat(gateway): add agent image attachments + live probe 2026-01-10 20:44:23 +00:00
Peter Steinberger
b9b1bc2726 test: relax reasoning replay expectations 2026-01-10 21:43:52 +01:00
Peter Steinberger
8a194b4abc fix: align opencode-zen provider setup 2026-01-10 21:38:18 +01:00
Peter Steinberger
46e00ad5e7 fix: describe sandboxed elevated in prompt 2026-01-10 21:37:15 +01:00
Peter Steinberger
3389231ecb feat(doctor): offer update first 2026-01-10 21:34:59 +01:00
Peter Steinberger
d772ff06c8 test: update openai responses reasoning replay 2026-01-10 21:20:26 +01:00
Peter Steinberger
686b3f884c fix: expose WhatsApp sender ids in group context 2026-01-10 21:09:08 +01:00
Peter Steinberger
0ef429f532 feat: color docs search output 2026-01-10 21:02:27 +01:00
Peter Steinberger
1bd5500832 feat: add colored CLI docs links 2026-01-10 20:51:03 +01:00
Peter Steinberger
cf192f8551 style: biome format 2026-01-10 19:47:17 +00:00
Peter Steinberger
afede929b3 test: harden gateway tool probes 2026-01-10 19:46:13 +00:00
Peter Steinberger
d44bb41d27 fix: replay OpenAI reasoning for tool calls 2026-01-10 19:46:13 +00:00
Peter Steinberger
fa346d7b78 fix: accept Z_AI_API_KEY for zai 2026-01-10 19:46:13 +00:00
Peter Steinberger
ec1047583a
Merge pull request #640 from mcinteerj/fix/whatsapp-group-reactions 
fix(whatsapp): enable reactions in group chats
 2026-01-10 19:44:05 +00:00
Peter Steinberger
7e6fa94720 fix: update WhatsApp history assertions (#640) (thanks @mcinteerj) 2026-01-10 20:41:30 +01:00
Jake
4933113252 fix(whatsapp): preserve group message IDs and normalize reaction participants 2026-01-10 20:36:32 +01:00
Peter Steinberger
4c4c167416 fix(update): harden root selection 2026-01-10 20:33:02 +01:00
Claude
777fb6b7bb CLI: add clawdbot update command and --update flag 2026-01-10 20:33:02 +01:00
Peter Steinberger
9f9098406c feat(sandbox): add sandbox explain inspector 2026-01-10 20:28:43 +01:00
Peter Steinberger
4533dd6e5d test: add image attachment regression coverage 2026-01-10 20:25:38 +01:00
Peter Steinberger
212b13b099 fix: repair tool-use history for anthropic 2026-01-10 19:15:57 +00:00
Peter Steinberger
193ebba657 fix: sniff chat attachment mime (#670) (thanks @cristip73) 2026-01-10 20:06:33 +01:00
cristip73
c4e76eb635 fix: enable image attachments in chat messages for Claude API 
Images were previously converted to markdown data URLs which Claude API
treats as plain text, not as actual images.

Changes:
- Add parseMessageWithAttachments() that returns {message, images[]}
- Pass images through the stack to session.prompt() as content blocks
- Filter null/empty attachments before parsing
- Strip data URL prefix if client sends it

This enables iOS and other clients to send images that Claude can actually see.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-10 20:00:25 +01:00
Peter Steinberger
0279f09459 fix: avoid duplicate cli banners 2026-01-10 19:57:24 +01:00
Peter Steinberger
7947059884 test(gateway): deflake temp HOME cleanup 2026-01-10 19:53:04 +01:00
Peter Steinberger
1fe9f648b1 feat(hooks): allow gmail tailscale target URLs 2026-01-10 19:19:43 +01:00
Peter Steinberger
b1664ec9c7 test: rename signal reaction-only test (#637) 2026-01-10 19:19:05 +01:00
Peter Steinberger
82f71d25e5 refactor: centralize history context wrapping 2026-01-10 19:16:26 +01:00
Peter Steinberger
b977ae19af chore: fix lint and typing 2026-01-10 19:16:25 +01:00
Peter Steinberger
d41372b9d9 feat: unify provider history context 2026-01-10 19:16:25 +01:00
Peter Steinberger
8c1d39064d test: adjust tool id sanitization 2026-01-10 18:15:15 +00:00
Peter Steinberger
7c925aa5a0 style: format helper 2026-01-10 18:15:15 +00:00
Peter Steinberger
651a9e9be4 fix: restore minimax tool calling 2026-01-10 18:15:15 +00:00
Peter Steinberger
8dbb22cc93 fix: signal handle dataMessage.reaction safely (#637) (thanks @neist) 2026-01-10 19:13:23 +01:00
Kasper Neist Christjansen
59e6064006 fix(signal): handle reactions in dataMessage.reaction format (#1) 
* fix(signal): handle reactions inside dataMessage.reaction

Signal reactions can arrive in two formats:
1. envelope.reactionMessage (already handled)
2. envelope.dataMessage.reaction (now handled)

The signal-cli SSE events use the second format, which was being
misinterpreted as a message with attachments, leading to 'broken
media / attachments' errors.

Changes:
- Add reaction property to SignalDataMessage type
- Check both envelope.reactionMessage and dataMessage.reaction
- Improve body content detection to properly identify reaction-only messages
- Add test for dataMessage.reaction format

* fix(signal): reaction notifications work when account is phone number

When reactionNotifications mode is 'own', notifications would never fire
because resolveSignalReactionTarget() returned a UUID but
shouldEmitSignalReactionNotification() compared it against the account
phone number, which never matched.

The fix:
- Add optional 'phone' field to SignalReactionTarget type
- Extract phone number first in resolveSignalReactionTarget(), include
  it even when UUID is present
- In shouldEmitSignalReactionNotification() 'own' mode, check phone
  match first before falling back to UUID comparison

This ensures reactions to your own messages are properly detected when
the Signal account is configured as a phone number and the reaction
event contains both targetAuthor (phone) and targetAuthorUuid.

* fix(signal): include phone in reaction target for own-mode matching

When targetAuthorUuid is present, also store targetAuthor phone number
in the reaction target. This allows own-mode reaction notifications to
match when comparing account phone against UUID-based targets.
 2026-01-10 19:10:39 +01:00
Anton Sotkov
26ce65995f fix(gmail): keep tailscale serve path at root 
The default Gmail hook path configured by `clawdbot hooks gmail setup` is `/gmail-pubsub`. Tailscale strips the mount path before proxying, so the request lands on `/` and the hook 404s under the default configuration.

When Tailscale is enabled, always listen on `/` internally and keep the public URL on the configured path (defaulting to `/gmail-pubsub`). This makes default and custom paths work reliably.

Alternative (not implemented here): call tailscale with a full target URL so the backend keeps the path, e.g. `tailscale funnel --set-path /gmail-pubsub http://127.0.0.1:8788/gmail-pubsub`. We did not take this path because it requires changing the CLI invocation to pass URLs (not ports) plus extra validation, which is a larger behavior change.
 2026-01-10 18:51:12 +01:00
Peter Steinberger
7dd0899856 fix: voicewake respects state dir override (#666) (thanks @roshanasingh4) 2026-01-10 18:32:09 +01:00
Peter Steinberger
f1a1032cd6 fix: serialize telegram media-group processing 2026-01-10 18:31:36 +01:00
Peter Steinberger
b383fbeed3 fix: cron wakeMode now waits for heartbeat (#666) (thanks @roshanasingh4) 2026-01-10 18:31:35 +01:00
Roshan Singh
91c870a0c4 fix(cron): wait for heartbeat to complete when wakeMode is "now" 
Fixes #652

When cron jobs with sessionTarget:"main" have wakeMode:"now",
they were being marked as completed immediately without waiting for the
agent to actually process the system event.

The issue was that requestHeartbeatNow() is fire-and-forget and
doesn't wait for the heartbeat to complete. The job would finish
with durationMs: 0 before the agent had a chance to run.

This fix:
- Adds runHeartbeatOnce to CronServiceDeps
- Wires it up in gateway/server.ts to load config and pass runtime
- Modifies executeJob() to call runHeartbeatOnce when wakeMode:"now"
- Waits for heartbeat to complete and maps status to cron result:
  * "ran" → "ok"
  * "skipped" → "skipped"
  * "failed" → "error"
- Falls back to old behavior for wakeMode:"next-heartbeat" or if
  runHeartbeatOnce is not available (backward compatibility)

Benefits:
- Jobs now have accurate durationMs reflecting actual processing time
- Jobs are correctly marked with "error" status if heartbeat fails
- Prevents race condition where job completes before agent runs

[AI-assisted] - Generated with z.ai GLM-4.7
[Tested: Lightly tested - Logic validated with test scenarios, code quality checks passed, integration testing requires live Clawdbot instance]
 2026-01-10 18:31:35 +01:00
Peter Steinberger
5a57cbe571
Merge pull request #667 from rubyrunsstuff/fix/discord-forwarded-snapshots 
Discord: include forwarded message snapshots
 2026-01-10 17:31:26 +00:00
Peter Steinberger
6480ef369f fix: telegram draft chunking defaults (#667) (thanks @rubyrunsstuff) 2026-01-10 18:30:06 +01:00
Peter Steinberger
2d105d16f8 fix(opencode-zen): keep legacy aliases + rationale (#669) (thanks @magimetal) 2026-01-10 18:25:43 +01:00
Ruby
7a836c9ff0 Discord: include forwarded message snapshots 2026-01-10 18:23:30 +01:00
Magi Metal
738269eb74 feat(opencode-zen): update models with sensible defaults 
- Replace model catalog with 11 current models: gpt-5.1-codex, claude-opus-4-5,
  gemini-3-pro, alpha-glm-4.7, gpt-5.1-codex-mini, gpt-5.1, glm-4.7-free,
  gemini-3-flash, gpt-5.1-codex-max, minimax-m2.1-free, gpt-5.2
- Add accurate per-token costs from OpenCode Zen pricing
- Add accurate context windows and output limits
- Update aliases for new model families (codex, glm, minimax)
- Remove deprecated models (sonnet, haiku, o-series, gemini-2.5)
 2026-01-10 18:22:26 +01:00
Peter Steinberger
9b5ce2530a
Merge pull request #665 from sebslight/fix/cloud-code-assist-schema-and-tool-ids 
fix(agents): harden Cloud Code Assist compatibility
 2026-01-10 17:07:58 +00:00
Peter Steinberger
38d6930fbe
Merge pull request #664 from azade-c/fix/use-state-dir-for-nodes-voicewake 
fix: use resolveStateDir() for node-pairing and voicewake storage
 2026-01-10 17:07:28 +00:00
Peter Steinberger
0d98e93253 fix: harden cloud code assist tool schema sanitizing (#665) (thanks @sebslight) 2026-01-10 18:07:26 +01:00
Sebastian Barrios
64babcac7a fix(agents): harden Cloud Code Assist compatibility 
- Expand schema scrubber to strip additional constraint keywords rejected
  by Cloud Code Assist (examples, minLength, maxLength, minimum, maximum,
  multipleOf, pattern, format, minItems, maxItems, uniqueItems,
  minProperties, maxProperties)
- Extend tool call ID sanitization to cover toolUse and toolCall block
  types (previously only functionCall was sanitized)
- Update pi-tools test to include 'examples' in unsupported keywords

Fixes 400 errors when using google-antigravity/claude-opus-4-5-thinking:
- tools.N.custom.input_schema: JSON schema is invalid
- messages.N.content.N.tool_use.id: String should match pattern
 2026-01-10 18:06:35 +01:00
Peter Steinberger
464f0645a8 fix: stabilize telegram media tests (#664) (thanks @azade-c) 2026-01-10 18:06:05 +01:00
Peter Steinberger
ef08c3f038 fix(agents): stabilize cli creds cache + bash cwd 2026-01-10 18:02:21 +01:00
Azade
48ad3bbbe6 fix: use resolveStateDir() for node-pairing and voicewake storage 
Both node-pairing.ts and voicewake.ts were using a local defaultBaseDir()
that hardcoded ~/.clawdbot, ignoring CLAWDBOT_STATE_DIR.

This caused nodes/paired.json and settings/voicewake.json to be stored
in ~/.clawdbot instead of the configured state directory.

Fixes the bug where paired nodes config was stored in a different
location than the rest of the gateway state.
 2026-01-10 17:55:30 +01:00
Peter Steinberger
843ff5f2d4 fix(sessions): tolerate ENOENT during lock 2026-01-10 17:50:53 +01:00
Peter Steinberger
60bf349201 fix(sessions): lock store saves; wait for bash close 2026-01-10 17:47:12 +01:00
Peter Steinberger
a54706a063 fix: throttle cli credential sync 2026-01-10 17:44:03 +01:00
Peter Steinberger
12722acb55 feat: wizard model picker (#611, thanks @jonasjancarik) 2026-01-10 16:32:59 +00:00
Jonáš Jančařík
687a10b8cc fix: map opencode-zen preferred provider 2026-01-10 16:32:59 +00:00
Jonáš Jančařík
9f80d8ec7c fix: skip model picker when auth choice preset 2026-01-10 16:32:59 +00:00
Jonáš Jančařík
dcc41e932d feat: add shared model picker to configure/onboarding 2026-01-10 16:32:59 +00:00
Peter Steinberger
e3cd431551 fix(auto-reply): RawBody commands + locked session updates (#643) 2026-01-10 17:32:31 +01:00
Peter Steinberger
e2ea02160d test: add workspace path regressions 2026-01-10 17:28:43 +01:00
Peter Steinberger
a1533a17f7 fix(gateway): harden chat abort semantics 2026-01-10 17:23:27 +01:00
Peter Steinberger
84d64f9395
Merge pull request #446 from tony-freedomology/feat/human-delay 
feat(agent): add human-like delay between block replies
 2026-01-10 16:16:52 +00:00
Peter Steinberger
fb03149df4 fix: finalize human delay config typing (#446) (thanks @tony-freedomology) 2026-01-10 17:15:27 +01:00
Lloyd
ab994d2c63 feat(agent): add human-like delay between block replies 
Adds `agent.humanDelay` config option to create natural rhythm between
streamed message bubbles. When enabled, introduces a random delay
(default 800-2500ms) between block replies, making multi-message
responses feel more like natural human texting.

Config example:
```json
{
  "agent": {
    "blockStreamingDefault": "on",
    "humanDelay": {
      "enabled": true,
      "minMs": 800,
      "maxMs": 2500
    }
  }
}
```

- First message sends immediately
- Subsequent messages wait a random delay before sending
- Works with iMessage, Signal, and Discord providers

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-10 17:12:50 +01:00
Muhammed Mukhthar CM
de5b75eff6 fix(tools): resolve Read/Write/Edit paths against workspace directory 
Previously, Read/Write/Edit tools used the global tool instances from
pi-coding-agent which had process.cwd() baked in at import time. Since
the gateway starts from /root/dev/ai/clawdbot, relative paths like
'SOUL.md' would incorrectly resolve there instead of the agent's
workspace (/root/clawd).

This fix:
- Adds workspaceDir option to createClawdbotCodingTools
- Creates fresh Read/Write/Edit tools bound to workspaceDir
- Adds cwd option to Bash tool defaults for consistency
- Passes effectiveWorkspace from pi-embedded-runner

Absolute paths and ~/... paths are unaffected. Sandboxed sessions
continue to use sandbox root as before.

Includes tests for Read/Write/Edit workspace path resolution.
 2026-01-10 17:08:56 +01:00
Peter Steinberger
d1943a9337 chore: format reply session 2026-01-10 17:03:17 +01:00
Peter Steinberger
d781508952 fix: make chat.send non-blocking 2026-01-10 17:02:28 +01:00
Peter Steinberger
b7fdc266ad test(auto-reply): cover native /model session routing 2026-01-10 16:50:32 +01:00
Peter Steinberger
b99eb4c9f3 fix(auto-reply): apply native commands to target session 2026-01-10 16:48:53 +01:00
Peter Steinberger
8978ac425e fix: harden cli credential sync 2026-01-10 16:37:54 +01:00
Peter Steinberger
81f9093c3c fix(pairing): accept positional provider args 2026-01-10 16:36:43 +01:00
Peter Steinberger
41c8bdfada feat: add ZAI auth choice 2026-01-10 16:32:21 +01:00
Peter Steinberger
8b47368167 fix: harden cli credential sync 2026-01-10 16:25:40 +01:00
Peter Steinberger
e60c3fc1b3 fix: doctor ignore install dir in legacy workspace check 2026-01-10 16:23:35 +01:00
Peter Steinberger
78532d76bd test: clean up lint warnings 2026-01-10 16:17:02 +01:00
Peter Steinberger
53a0c966a5 refactor: unify configure auth choice 2026-01-10 16:14:49 +01:00
Peter Steinberger
43b530ca1c fix(agents): suppress partial replies with reasoning 2026-01-10 16:03:17 +01:00
Peter Steinberger
44564df028 refactor(sessions): add mergeSessionEntry 2026-01-10 16:03:17 +01:00
Peter Steinberger
70c1732dd1 refactor: centralize messaging dedupe helpers 2026-01-10 16:02:56 +01:00
Peter Steinberger
5a93447294 fix: prevent claude-cli oauth downgrade (#654) (thanks @radek-paclt) 2026-01-10 15:50:25 +01:00
Radek Paclt
a39951d463 fix(auth): enable OAuth refresh for Claude CLI credentials 
When Claude CLI credentials (anthropic:claude-cli) expire, automatically
refresh using the stored refresh token instead of failing with
"No credentials found" error.

Changes:
- Read refreshToken from Claude CLI and store as OAuth credential type
- Implement bidirectional sync: after refresh, write new tokens back to
  Claude Code storage (file on Linux/Windows, Keychain on macOS)
- Prefer OAuth over Token credentials (enables auto-refresh capability)
- Maintain backward compatibility for credentials without refreshToken

This enables long-running agents to operate autonomously without manual
re-authentication when OAuth tokens expire.

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-01-10 15:40:27 +01:00
Peter Steinberger
1281c1d155
Merge pull request #655 from antons/fix/reasoning-imsg 
Fix reasoning in iMessage
 2026-01-10 14:39:14 +00:00
Peter Steinberger
236f8560b3 fix: reasoning iMessage sessions + final reply (#655) (thanks @antons) 2026-01-10 15:31:57 +01:00
Peter Steinberger
ae3711bfbd
Merge pull request #659 from mickahouan/fix/dedupe-message-tool 
Fix: avoid duplicate replies when message tool sends
 2026-01-10 14:30:02 +00:00
Peter Steinberger
449bee9645 fix: bundle node runtime for mac app 2026-01-10 15:28:37 +01:00
Peter Steinberger
4d146ea2f5 fix: dedupe message tool replies (#659) (thanks @mickahouan) 2026-01-10 15:28:13 +01:00
Anton Sotkov
3b5149ca39 fix: send only final answer with reasoning 
When reasoning is enabled on non‑block providers, we now ignore interim streaming chunks and send only the final assistant answer at completion, so replies aren’t partial or duplicated.
 2026-01-10 15:28:04 +01:00
Anton Sotkov
4c86da044e fix(sessions): persist reasoning/elevated across DMs 2026-01-10 15:28:04 +01:00
Mickaël Ahouansou
d01e06f09a Fix: dedupe message tool sends 2026-01-10 15:25:20 +01:00
Peter Steinberger
65c2532cd5 fix: minimax apiKey optional for providers (#656) (thanks @mneves75) 2026-01-10 15:08:12 +01:00
mneves75
3e2e3eb023 Config: add MiniMax direct API authentication option 
Makes apiKey optional in ModelProviderConfig so MiniMax can use auth
profiles or environment variables (MINIMAX_API_KEY) instead of requiring
explicit config.

Changes:
- src/config/types.ts: apiKey changed from required to optional
- src/config/zod-schema.ts: use z.string().min(1).optional() for validation
- src/commands/configure.ts: add minimax-api auth choice in wizard
- src/commands/onboard-auth.ts: MiniMax provider omits apiKey (uses env/auth)
- patches/@mariozechner__pi-ai@0.42.1.patch: map minimax → MINIMAX_API_KEY

Auth Resolution Order (unchanged):
1. Auth profiles (highest priority)
2. Environment variables (MINIMAX_API_KEY, etc.)
3. Custom provider apiKey from models.json (lowest priority)
 2026-01-10 10:57:09 -03:00
Peter Steinberger
920b3880c1 test: add elevated mode regressions 2026-01-10 05:31:48 +01:00
Peter Steinberger
66db6c749d fix: persist elevated off override 2026-01-10 05:23:46 +01:00
Peter Steinberger
2045395ccb test(live): add optional write/bash probes 2026-01-10 04:14:39 +00:00
Peter Steinberger
d3674f4d6c test(onboard): cover remote + lan token flows 2026-01-10 04:14:39 +00:00
Peter Steinberger
cdb915d527 chore: normalize Clawdbot naming 2026-01-10 05:14:09 +01:00
Peter Steinberger
a7c8341452 feat: show more session flags 2026-01-10 05:14:07 +01:00
Peter Steinberger
7b392ca74b test(onboard): gateway token auth flow 2026-01-10 03:54:29 +00:00
Peter Steinberger
eee04fa2ce fix(onboard): persist gateway token in config 2026-01-10 03:54:25 +00:00
Peter Steinberger
4fac94f259 test(gateway): add wizard e2e + isolate live suite 2026-01-10 03:44:21 +00:00
Peter Steinberger
0f409cb99d test(telegram): force real timers for media groups 2026-01-10 03:44:21 +00:00
Peter Steinberger
241bc737cf test(telegram): deflake media groups on windows 2026-01-10 04:43:04 +01:00
Peter Steinberger
2a0d8f6e38 test(gateway): avoid real OpenAI in mock test 2026-01-10 03:25:45 +00:00
Peter Steinberger
056c4ae622 test(telegram): harden media tests 2026-01-10 04:18:05 +01:00
Peter Steinberger
6274adce3a fix(tools): keep canonical tool names for oauth 2026-01-10 04:18:00 +01:00
Peter Steinberger
4f79122068 test: stabilize gateway mock + lint 2026-01-10 03:14:13 +00:00
Peter Steinberger
7376d1e6c9 feat: improve tui status output 2026-01-10 04:07:15 +01:00
Peter Steinberger
782863ea6c test(gateway): add offline tool-calling regression 2026-01-10 03:06:02 +00:00
Peter Steinberger
cc1c5f800f fix(tools): harden schemas and oauth tool names 2026-01-10 03:05:56 +00:00
Peter Steinberger
f241859c98 fix: relax fetch typing for Bun 2026-01-10 04:01:06 +01:00