romtuck/openclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
5,518 Commits 258 Branches 39 Tags 276 MiB
36725ce153
Commit Graph

764 Commits

Author SHA1 Message Date
Peter Steinberger
8afdf75e2b fix: honor copilot config and profiles (#705) (thanks @TAGOOZ) 2026-01-12 16:55:47 +00:00
Peter Steinberger
5a3eb5ad62 test: cover models.json apiKey fill 2026-01-12 16:52:43 +00:00
Peter Steinberger
79beb20ba2 fix: make models.json generation fill apiKey 2026-01-12 16:52:43 +00:00
Mustafa Tag Eldeen
3da1afed68 feat: add GitHub Copilot provider 
Copilot device login + onboarding option; model list auth detection.
 2026-01-12 16:52:15 +00:00
Peter Steinberger
bf11a42c37 feat: add memory vector search 2026-01-12 11:23:44 +00:00
Peter Steinberger
3c7a8579ad test: cover minimax env provider injection 2026-01-12 11:05:08 +00:00
Peter Steinberger
f5a9421b10 fix: auto-add minimax provider from auth 2026-01-12 11:05:08 +00:00
Peter Steinberger
fadad6e061 feat: role snapshot refs for browser 2026-01-12 08:55:02 +00:00
Peter Steinberger
6711eaf8a5 fix: finalize tool param aliasing (#768) (thanks @hsrvc) 2026-01-12 08:49:11 +00:00
hsrvc
71fdc829e6 Agents: add Claude Code parameter aliasing for read/write/edit tools 2026-01-12 08:49:11 +00:00
Peter Steinberger
252841ab13 fix: enforce final tag gating (#754) (thanks @mcinteerj) 2026-01-12 08:45:23 +00:00
Keith the Silly Goose
a7cb270999 fix(agent): buffer streaming output until <final> tag appears 
- Enforces strict buffering when enforceFinalTag is enabled.
- Prevents 'thinking out loud' planning steps (e.g. '*Locating Manulife*') from leaking to WhatsApp.
- Hardens <final> tag stripping to remove nested/hallucinated tags.
 2026-01-12 08:34:06 +00:00
Keith the Silly Goose
efdf874407 fix(agent): correctly strip <final> tags from reasoning providers 
- Added src/utils/provider-utils.ts to track reasoning provider logic
- Updated isReasoningTagProvider to loosely match 'google-antigravity' (fixes sub-models)
- Enabled enforceFinalTag in reply.ts when provider matches
- Verified <final> tag stripping logic in pi-embedded-subscribe.ts
- Updated pi-embedded-runner to use consistent provider check for prompt hints
 2026-01-12 08:34:06 +00:00
Peter Steinberger
60823fd9bd feat(model): fuzzy /model matching 2026-01-12 07:57:53 +00:00
Peter Steinberger
484a33f348 fix: cap ai snapshots for tool calls (#763) (thanks @thesash) 2026-01-12 07:40:34 +00:00
Sash Catanzarite
d5d8c01dc7 Browser: cap AI snapshots to avoid context overflow 2026-01-12 07:40:34 +00:00
Peter Steinberger
f00667ea25 fix: clean up lint + guardCancel typing 2026-01-12 07:07:27 +00:00
Peter Steinberger
1850013cae fix: modernize live tests and gemini ids 2026-01-12 07:05:33 +00:00
Peter Steinberger
496bad8b98 feat: add Moonshot auth choice 2026-01-12 06:48:06 +00:00
Peter Steinberger
46a6d79784 fix: sender fallback for command auth (#755) (thanks @juanpablodlc) 2026-01-12 06:28:53 +00:00
Peter Steinberger
e388334127 test: cover pi session jsonl ordering 2026-01-12 06:19:58 +00:00
Peter Steinberger
2da2057a37 feat(model): add /model picker 2026-01-12 06:02:39 +00:00
Peter Steinberger
7dbb21be8e feat: add pre-compaction memory flush 2026-01-12 05:29:18 +00:00
Peter Steinberger
cc8a2457c0 fix: persist first Pi user message in JSONL 2026-01-12 05:18:05 +00:00
Peter Steinberger
87f270df23 test: respect openai max tokens floor 2026-01-12 04:04:04 +00:00
Peter Steinberger
8b4bdaa8a4 feat: add apply_patch tool (exec-gated) 2026-01-12 03:42:56 +00:00
Peter Steinberger
1fa7a587d6 fix: flush block reply buffers on tool boundaries (#750) (thanks @sebslight) 2026-01-12 02:54:57 +00:00
The Admiral
c64bcd047b fix: flush block reply coalescer on tool boundaries 
When block streaming is enabled with verbose=off, tool blocks are hidden
but their boundary information was lost. Text segments before and after
tool execution would get coalesced into a single message because the
coalescer had no signal that a tool had executed between them.

This adds an onBlockReplyFlush callback that fires on tool_execution_start,
allowing the block reply pipeline to flush pending text before the tool
runs. This preserves natural message boundaries even when tools are hidden.

Fixes the issue where:
  text → [hidden tool] → text → rendered as one merged message

Now correctly renders as:
  text → [hidden tool] → text → two separate messages

Co-diagnosed-by: Krill (Discord assistant)
 2026-01-12 02:52:48 +00:00
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
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
2941a7002d fix(subagents): align wait timeout with run timeout 2026-01-12 02:06:43 +00:00
Peter Steinberger
28f97e6152 refactor(sandbox): normalize main session aliases 2026-01-12 01:37:56 +00:00
Peter Steinberger
58a12a757e fix(sandbox): avoid sandboxing main DM sessions 2026-01-12 01:24:44 +00:00
Peter Steinberger
2f4a248314 feat: plugin system + voice-call 2026-01-12 01:16:39 +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
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
67743325ee fix: reset session after compaction overflow 2026-01-12 00:28:16 +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
1f95d7fc8b fix: read codex keychain credentials 2026-01-11 23:39:10 +00:00
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
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
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
a3747b1ee3 fix: add compaction headroom for memory writes 2026-01-11 11:25:15 +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
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
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
9046296ed3 fix: clarify sub-agent sandbox limits 2026-01-11 05:04:14 +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
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
1f9b4e3af6 fix: send heartbeat reasoning (#694) (thanks @antons) 2026-01-11 03:51:51 +01:00
Peter Steinberger
2b07a2a8ab fix: stabilize onboarding auth tests (#703) (thanks @mteam88) 2026-01-11 03:42:27 +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
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
a32021dc3e fix: inject image paths for cli backends 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
b339097179 style: format browser tool wiring 2026-01-11 01:34:45 +01:00
Peter Steinberger
326fb04d12 feat: add browser target selection for sandboxed agents 2026-01-11 01:31:56 +01:00
Shadow
c731a87d07
Discord: add fetch message action 2026-01-10 16:38:20 -06:00
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
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
Peter Steinberger
050c1c5391 fix(agents): include reasoningLevel in compaction params 2026-01-10 22:39:06 +01:00
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
ab314a22e0 chore: refresh pi-ai patch repro note 2026-01-10 20:55:57 +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
cf192f8551 style: biome format 2026-01-10 19:47:17 +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
9f9098406c feat(sandbox): add sandbox explain inspector 2026-01-10 20:28:43 +01:00
Peter Steinberger
212b13b099 fix: repair tool-use history for anthropic 2026-01-10 19:15:57 +00:00
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
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
2d105d16f8 fix(opencode-zen): keep legacy aliases + rationale (#669) (thanks @magimetal) 2026-01-10 18:25:43 +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
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
ef08c3f038 fix(agents): stabilize cli creds cache + bash cwd 2026-01-10 18:02:21 +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
e2ea02160d test: add workspace path regressions 2026-01-10 17:28:43 +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
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
8978ac425e fix: harden cli credential sync 2026-01-10 16:37:54 +01:00
Peter Steinberger
8b47368167 fix: harden cli credential sync 2026-01-10 16:25:40 +01:00
Peter Steinberger
43b530ca1c fix(agents): suppress partial replies with reasoning 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
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
Mickaël Ahouansou
d01e06f09a Fix: dedupe message tool sends 2026-01-10 15:25:20 +01:00
Peter Steinberger
cdb915d527 chore: normalize Clawdbot naming 2026-01-10 05:14:09 +01:00
Peter Steinberger
6274adce3a fix(tools): keep canonical tool names for oauth 2026-01-10 04:18:00 +01:00
Peter Steinberger
cc1c5f800f fix(tools): harden schemas and oauth tool names 2026-01-10 03:05:56 +00:00
Peter Steinberger
8466e53b5d fix: restore Anthropic OAuth tool dispatch 2026-01-10 04:01:00 +01:00
Peter Steinberger
2dc7872ad1 feat: auto-start sandbox browser 2026-01-10 02:06:21 +00:00
Peter Steinberger
f28a4a34ad refactor: unify inline directives and media fetch 2026-01-10 03:01:04 +01:00
Peter Steinberger
a29f5dda2e test(live): gateway smoke across profile-key models 2026-01-10 01:09:41 +00:00
Peter Steinberger
623d1e11f1 refactor: centralize session agent resolution 2026-01-10 01:57:54 +01:00
Peter Steinberger
f4b3869f45
Merge pull request #490 from jarvis-medmatic/feat/audio-as-voice-tag 
feat(telegram): `[[audio_as_voice]]` tag support
 2026-01-10 00:52:02 +00:00
Peter Steinberger
c56b2f4bc1 fix: honor audio_as_voice streaming + parse tests (#490) (thanks @jarvis-medmatic) 2026-01-10 01:50:33 +01:00
Peter Steinberger
cb10682d3e fix(openai): avoid invalid reasoning replay 2026-01-10 00:45:10 +00:00
Jarvis
5fedfd8d15 chore: format audioAsVoice updates 
Co-authored-by: Manuel Hettich <17690367+ManuelHettich@users.noreply.github.com>
 2026-01-10 01:44:57 +01:00
Jarvis
8c7d1781bc fix(pi): preserve audio_as_voice tag 
- Allow flag-only chunks so audio_as_voice propagates
- Keep reply item scan aware of empty audio tag blocks

Co-authored-by: Manuel Hettich <17690367+ManuelHettich@users.noreply.github.com>
 2026-01-10 01:43:51 +01:00
Jarvis
2f036f7173 fix(audio): preserve audioAsVoice propagation 
- Keep audioAsVoice-only payloads from being filtered out
- Allow empty payloads through when they carry the flag
- Remove temporary debug logs around audioAsVoice buffering

Co-authored-by: Manuel Hettich <17690367+ManuelHettich@users.noreply.github.com>
 2026-01-10 01:42:09 +01:00
Jarvis
05a99aa49b feat(telegram): buffer audio blocks for [[audio_as_voice]] tag support 
- Add [[audio_as_voice]] detection to splitMediaFromOutput()
- Pass audioAsVoice through onBlockReply callback chain
- Buffer audio blocks during streaming, flush at end with correct flag
- Non-audio media still streams immediately
- Fix: emit payloads with audioAsVoice flag even if text is empty

Co-authored-by: Manuel Hettich <17690367+ManuelHettich@users.noreply.github.com>
 2026-01-10 01:41:18 +01:00
Peter Steinberger
43975a39dc fix: gate heartbeat prompt to default agent sessions (#630) (thanks @adam91holt) 2026-01-10 01:32:58 +01:00
Adam Holt
c91ec2aab7 fix: only inject heartbeat prompt for default agent 
The heartbeat prompt from agents.defaults.heartbeat.prompt was being
injected into the system prompt for ALL agents, causing non-default
agents to read the default agent's identity files and adopt its persona.

Now the heartbeat prompt is only included when the session's agent ID
matches the configured default agent. Other agents receive no heartbeat
section in their system prompt.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-10 01:32:30 +01:00
Peter Steinberger
5898304fa0 fix: abort runs between tool calls 2026-01-10 01:26:25 +01:00
Peter Steinberger
53ec8e36cb refactor: centralize failover error parsing 2026-01-10 01:26:06 +01:00
Peter Steinberger
20d4773f14 fix(agents): require raw for gateway config.apply (#566) (thanks @sircrumpet) 2026-01-10 00:21:15 +00:00
Peter Steinberger
52565864d1
Merge pull request #619 from rubyrunsstuff/fix/telegram-block-streaming 
fix: enable block streaming for Telegram when streamMode is 'block'
 2026-01-10 00:16:04 +00:00