admin/Moltbot
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
9,919 Commits 1 Branch 0 Tags
83248f7603a35ff300fcdc2a5b2566a4c0900512
Commit Graph

5486 Commits

Author SHA1 Message Date
Peter Steinberger
83248f7603 Merge remote-tracking branch 'origin/main' 2026-02-14 13:30:22 +01:00
Peter Steinberger
af50b914a4 refactor(browser): centralize http auth 2026-02-14 13:30:11 +01:00
Peter Steinberger
a2b45e1c13 fix(gateway): relax http tool deny typing 2026-02-14 13:30:05 +01:00
Aldo
7b39543e8d fix(reply): honour explicit [[reply_to_*]] tags when replyToMode is off (#16174) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 778fc2559ade85a37209866c2edbe33bfc5bbb86
Co-authored-by: aldoeliacim <17973757+aldoeliacim@users.noreply.github.com>
Co-authored-by: steipete <58493+steipete@users.noreply.github.com>
Reviewed-by: @steipete
 2026-02-14 13:29:42 +01:00
Peter Steinberger
0af76f5f0e refactor(gateway): centralize node.invoke param sanitization 2026-02-14 13:27:45 +01:00
Peter Steinberger
c15946274e fix(gateway): allowlist system.run params 2026-02-14 13:27:45 +01:00
Peter Steinberger
a7af646fdf fix(gateway): bind approval ids to device identity 2026-02-14 13:27:45 +01:00
Peter Steinberger
318379cdba fix(gateway): bind system.run approvals to exec approvals 2026-02-14 13:27:45 +01:00
Peter Steinberger
233483d2b9 refactor(security): centralize dangerous tool lists 2026-02-14 13:27:05 +01:00
Peter Steinberger
0cfea46293 fix: wire minimax-api-key-cn onboarding (#15191) (thanks @liuy) 2026-02-14 13:25:54 +01:00
Liu Yuan
9bb099736b feat: add minimax-api-key-cn option for China API endpoint 
- Add 'minimax-api-key-cn' auth choice for Chinese users
- Reuse existing --minimax-api-key CLI option
- Use MINIMAX_CN_API_BASE_URL (https://api.minimaxi.com/anthropic)
- Similar to how moonshot supports moonshot-api-key-cn

Tested: build ✅, check ✅, test ✅
 2026-02-14 13:25:54 +01:00
Peter Steinberger
cd84885a4a test(browser): cover bridge auth registry fallback 2026-02-14 13:23:24 +01:00
Peter Steinberger
586176730c perf(gateway): optimize sessions/ws/routing 2026-02-14 12:21:44 +00:00
Peter Steinberger
c90b3e4d5e perf(cli): speed up startup 2026-02-14 12:21:44 +00:00
Peter Steinberger
a7a08b6650 test(gateway): cover tools allow/deny precedence 2026-02-14 13:18:49 +01:00
Peter Steinberger
153a7644ea fix(acp): tighten safe kind inference 2026-02-14 13:18:49 +01:00
Peter Steinberger
6dd6bce997 fix(security): enforce sandbox bridge auth 2026-02-14 13:17:41 +01:00
Peter Steinberger
eb4215d570 perf(test): speed up Vitest bootstrap 2026-02-14 12:13:27 +00:00
Nicholas
f8ba8f7699 fix(docs): update outdated hooks documentation URLs (#16165) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 8ed13fb02fae2cb6dd3cacdb3cd1ef37a5cdd4d8
Co-authored-by: nicholascyh <188132635+nicholascyh@users.noreply.github.com>
Co-authored-by: steipete <58493+steipete@users.noreply.github.com>
Reviewed-by: @steipete
 2026-02-14 13:05:37 +01:00
Peter Steinberger
4711a943e3 fix(browser): authenticate sandbox browser bridge server 2026-02-14 12:54:16 +01:00
Peter Steinberger
bb1c3dfe10 fix(acp): prompt for non-read/search permissions 2026-02-14 12:53:27 +01:00
Peter Steinberger
539689a2f2 feat(security): warn when gateway.tools.allow re-enables dangerous HTTP tools 2026-02-14 12:48:02 +01:00
Peter Steinberger
3b56a6252b chore!: remove moltbot legacy state/config support 2026-02-14 12:40:47 +01:00
Nick Taylor
1fb52b4d7b feat(gateway): add trusted-proxy auth mode (#15940) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 279d4b304f83186fda44dfe63a729406a835dafa
Co-authored-by: nickytonline <833231+nickytonline@users.noreply.github.com>
Co-authored-by: steipete <58493+steipete@users.noreply.github.com>
Reviewed-by: @steipete
 2026-02-14 12:32:17 +01:00
Peter Steinberger
6182d3ef85 test: increase live-model retry token budget for reasoning-first providers 2026-02-14 12:23:51 +01:00
Pejman Pour-Moezzi
9475791d98 fix: update remaining replyToMode "first" defaults to "off" 
- src/channels/dock.ts: core channel dock fallback
- src/auto-reply/reply/reply-routing.test.ts: test expectation
- docs/zh-CN/channels/telegram.md: Chinese docs reference

Comprehensive grep confirms no remaining Telegram-specific "first"
defaults after this commit.
 2026-02-13 23:31:17 -08:00
Pejman Pour-Moezzi
ad96c126ed fix(telegram): change default replyToMode from "first" to "off" 
In 2026.2.13, the combination of implicit reply threading (#14976) and
the existing Telegram default replyToMode="first" causes every bot
response in DMs to be sent as a native Telegram reply (quoted message
bubble), even for simple exchanges like "Hi" → "Hey".

This is a UX regression: prior to 2026.2.13, reply threading was less
consistent so the "first" default rarely produced visible quote bubbles
in DMs. Now that implicit threading works reliably, the default
effectively means every first message in a response gets quoted —
which feels noisy and unexpected in 1:1 conversations.

Changing the default to "off" restores the pre-2026.2.13 DM experience.
Users who want reply threading can still opt in via config:

  channels.telegram.replyToMode: "first" | "all"

Tested by toggling replyToMode on a live 2026.2.13 instance:
- replyToMode="first" → every response quotes the user message
- replyToMode="off" → clean responses without quote bubbles

No test changes needed: existing tests explicitly set replyToMode
rather than relying on the default.
 2026-02-13 23:31:17 -08:00
vignesh07
e38ed4f640 fix(memory): default qmd searchMode to search + scope search/vsearch to collections 2026-02-13 23:14:34 -08:00
Peter Steinberger
a50638eead perf(test): disable vector index in OpenAI batch tests 2026-02-14 05:25:40 +00:00
Peter Steinberger
0e5e72edb4 perf(test): shrink memory embedding batch fixtures 2026-02-14 05:25:40 +00:00
Peter Steinberger
98bb4225fd perf(test): minimize gateway startup in vitest 2026-02-14 05:25:40 +00:00
Peter Steinberger
d8beddc8b7 refactor(onboard): unify auth-choice aliases and provider flags 2026-02-14 05:58:26 +01:00
Peter Steinberger
2f4cef2021 perf(test): remove last-route polling in partial reply gating 2026-02-14 04:57:28 +00:00
Peter Steinberger
4335668d28 chore(test): fix cron every-jobs-fire unused import 2026-02-14 04:57:28 +00:00
Peter Steinberger
e6d5b5fb11 perf(test): remove slow port inspection and reconnect sleeps 2026-02-14 04:57:28 +00:00
Peter Steinberger
eab9dc538a refactor(onboard): unify auth-choice catalog for CLI help 2026-02-14 05:51:17 +01:00
Peter Steinberger
fdda261478 fix: align NVIDIA provider docs and model ids (#11606) 2026-02-14 05:48:40 +01:00
Gabriel
e0132514f6 fix: needed to use format:fix 2026-02-14 05:48:40 +01:00
Gabriel
3feb5d1f10 fix: LINT AGAIN 2026-02-14 05:48:40 +01:00
Gabriel
f90a39e984 fix: my mistakes 2026-02-14 05:48:40 +01:00
Gabriel
8f2884b986 fix: i am fixing all the changes that claude made. vibe coding is not there yet. anyways, i fixed the issues that the bot told me to fix 2026-02-14 05:48:40 +01:00
anthropic-code-agent[bot]
c640b5f86c feat: add NVIDIA API provider integration 
Add support for NVIDIA's API (https://integrate.api.nvidia.com/v1) with three models:
- nvidia/llama-3.1-nemotron-70b-instruct (default)
- nvidia/llama-3.3-70b-instruct
- nvidia/mistral-nemo-minitron-8b-8k-instruct

Users can configure via NVIDIA_API_KEY environment variable or auth profiles.

Co-authored-by: thesomewhatyou <162917831+thesomewhatyou@users.noreply.github.com>
 2026-02-14 05:48:40 +01:00
Peter Steinberger
2d4d32cb2d test(cron): await persistence before temp cleanup 2026-02-14 03:18:27 +00:00
青雲
89fa93ed75 feat: support freshness parameter for Perplexity web_search provider (#15343) 
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 01aba2bfba053c028f62970dcd153b19d00c5e3b
Co-authored-by: echoVic <16428813+echoVic@users.noreply.github.com>
Co-authored-by: sebslight <19554889+sebslight@users.noreply.github.com>
Reviewed-by: @sebslight
 2026-02-13 22:18:16 -05:00
Peter Steinberger
7f227fc8cc perf(test): avoid heavy browser barrels in pw-ai tests 2026-02-14 03:13:32 +00:00
Peter Steinberger
115444b37c perf(test): deflake and speed up qmd manager tests 2026-02-14 03:08:13 +00:00
Peter Steinberger
9126930363 test(cron): remove flaky real-timer polling 2026-02-14 03:00:06 +00:00
Peter Steinberger
72e9364bac perf(test): speed up hot test files 2026-02-14 02:55:39 +00:00
Peter Steinberger
dd08ca97bb perf(test): reduce import and fixture overhead in hot tests 2026-02-14 02:49:19 +00:00
Peter Steinberger
2583de5305 refactor(routing): normalize binding matching and harden qmd boot-update tests 2026-02-14 03:40:28 +01:00