Commit Graph

1441 Commits (aec41a588bb25c78cbff27fc8a4a69c8e6c19eaf)

Author SHA1 Message Date
chilu18 aec41a588b fix(hooks): backfill reset command hooks for native /new path 9 months ago
Vincent Koc 4b316c33db
Auto-reply: normalize stop matching and add multilingual triggers (#25103)
* Auto-reply tests: cover multilingual abort triggers

* Auto-reply: normalize multilingual abort triggers

* Gateway: route chat stop matching through abort parser

* Gateway tests: cover chat stop parsing variants

* Auto-reply tests: cover Russian and German stop words

* Auto-reply: add Russian and German abort triggers

* Gateway tests: include Russian and German stop forms

* Telegram tests: route Russian and German stop forms to control lane

* Changelog: note multilingual abort stop coverage

* Changelog: add shared credit for abort shortcut update
9 months ago
Peter Steinberger 31f2bf9519 test: fix gate regressions 9 months ago
User 7d76c241f8 fix: suppress reasoning payloads from generic channel dispatch path
When reasoningLevel is 'on', reasoning content was being sent as a
visible message to WhatsApp and other non-Telegram channels via two
paths:
1. Block reply: emitted via onBlockReply in handleMessageEnd
2. Final payloads: added to replyItems in buildEmbeddedRunPayloads

Telegram has its own dispatch path (bot-message-dispatch.ts) that
splits reasoning into a dedicated lane and handles suppression.
The generic dispatch-from-config.ts path used by WhatsApp, web, etc.
had no such filtering.

Fix:
- Add isReasoning?: boolean flag to ReplyPayload
- Tag reasoning payloads at both emission points
- Filter isReasoning payloads in dispatch-from-config.ts for both
  block reply and final reply paths

Telegram is unaffected: it uses its own deliver callback that detects
reasoning via the 'Reasoning:\n' prefix and routes to a separate lane.

Fixes #24954
9 months ago
Peter Steinberger aea28e26fb fix(auto-reply): expand standalone stop phrases 9 months ago
Peter Steinberger e578521ef4 fix(security): harden session export image data-url handling 9 months ago
Peter Steinberger f8524ec77a fix(security): harden exported session html rendering 9 months ago
Peter Steinberger 08e2aa44e7 fix(commands): restrict commands.allowFrom to sender principals 9 months ago
Peter Steinberger f97c0922e1 fix(security): harden account-key handling against prototype pollution 9 months ago
Peter Steinberger b9f01e8d3f test: consolidate directive behavior suites for faster runs 9 months ago
Peter Steinberger b8fc8e7e6d test: optimize directive behavior test scenarios 9 months ago
Peter Steinberger 31ca7fb277 test: consolidate directive behavior test scenarios 9 months ago
Peter Steinberger 75423a00d6 refactor: deduplicate shared helpers and test setup 9 months ago
Peter Steinberger cba8037d90 test: prune redundant trigger handling integration coverage 9 months ago
Peter Steinberger c88915b721 test: consolidate trigger handling suites 9 months ago
Peter Steinberger 7a40d99b1d refactor(cron): extract delivery dispatch + harden reset notices 9 months ago
Peter Steinberger 31e4c21b67 fix(auto-reply): move volatile inbound flags out of system metadata
Co-authored-by: aidiffuser <aidiffuser@users.noreply.github.com>
9 months ago
Peter Steinberger cf38339f25 fix(tools): improve session_status cache-aware usage reporting
Co-authored-by: Lucian Feraru <1ucian@users.noreply.github.com>
9 months ago
Peter Steinberger bf373eeb43 refactor: harden reset notice + cron delivery target flow 9 months ago
Peter Steinberger b9b77cea4e fix(reply): omit auth labels in /new and /reset 9 months ago
Peter Steinberger 445c7a65e6 test: simplify session reset and rawbody coverage 9 months ago
Peter Steinberger 783a9134d6 test: prune redundant trigger-handling scenarios 9 months ago
Peter Steinberger b81bce703c test: streamline trigger and session coverage 9 months ago
Peter Steinberger ddc67aa4ef test: collapse duplicate trigger command coverage 9 months ago
Vincent Koc f03ff39754
Providers: skip context1m beta for Anthropic OAuth tokens (#24620)
* Providers: skip context1m beta for Anthropic OAuth tokens

* Tests: cover OAuth context1m beta skip behavior

* Docs: note context1m OAuth incompatibility

* Agents: add context1m-aware context token resolver

* Agents: cover context1m context-token resolver

* Commands: apply context1m-aware context tokens in session store

* Commands: apply context1m-aware context tokens in status summary

* Status: resolve context tokens with context1m model params

* Status: test context1m status context display
9 months ago
Peter Steinberger fdd185cfaa test: merge inline trigger command and elevated coverage 9 months ago
Peter Steinberger f7e45ce947 test: consolidate trigger-handling status and heartbeat scenarios 9 months ago
LI SHANXIN c1b75ab8e2
fix(telegram): make reaction handling soft-fail and message-id resilient (#20236)
* Telegram: soft-fail reactions and fallback to inbound message id

* Telegram: soft-fail missing reaction message id

* Update CHANGELOG.md

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
9 months ago
Peter Steinberger 3f03cdea56 test: optimize redundant suites for faster runtime 9 months ago
Peter Steinberger 5196565f19 test: reduce trigger test redundancy and speed up model coverage 9 months ago
Nimrod Gutman 9d37654a90 fix(agents): gate auto reasoning by effective thinking level (openclaw#24335) thanks @Kay-051 9 months ago
Kay-051 42795b87a3 fix(agents): don't auto-enable reasoning when thinking is active (#24290)
When thinking is set (e.g. thinking=low), the model produces internal
thinking blocks. The reasoning auto-default (based on model capability)
was formatting these blocks as "Reasoning:" text and delivering them to
WhatsApp/Telegram, leaking internal content to users.

Skip auto-enabling reasoning when thinkLevel is already set — the two
features serve the same purpose and enabling both causes the model's
internal thinking to be exposed as visible chat messages.

Users who explicitly set /reasoning on still get reasoning output.

Closes #24290

Co-authored-by: Cursor <cursoragent@cursor.com>
9 months ago
Peter Steinberger 89a4695020 test: consolidate shard tests for faster trigger/directive suites 9 months ago
Peter Steinberger 67bccc1fa0 test: merge allow-from trigger shard and dedupe inline cases 9 months ago
Peter Steinberger f6ee1c99a7 test: merge thinking and queue directive shards 9 months ago
Peter Steinberger c9fbcf39ee test: merge fuzzy model directive shards 9 months ago
Peter Steinberger e048ed1efd test: merge elevated allowlist directive shard 9 months ago
Peter Steinberger 706c9ec729 test: consolidate directive behavior suites 9 months ago
Peter Steinberger fbdb1b3e73 test: merge elevated status directive shards 9 months ago
Peter Steinberger b11ff9f7dd test: collapse directive behavior shards 9 months ago
Peter Steinberger be422a9d18 test: merge model picker tests into native command suite 9 months ago
Ayaan Zaidi 2247b81219
fix(auto-reply): hide direct-chat metadata without sender-id sentinel (openclaw#24373) thanks @jd316
Co-authored-by: jd316 <138361777+jd316@users.noreply.github.com>
Co-authored-by: obviyus <22031114+obviyus@users.noreply.github.com>
9 months ago
边黎安 a4c373935f
fix(agents): fall back to agents.defaults.model when agent has no model config (#24210)
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 0f272b102763736001a82cfda23f35ff2ee9cac8
Co-authored-by: bianbiandashen <16240681+bianbiandashen@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
9 months ago
Glucksberg 36400df086
fix: pass agentDir to /compact command for agent-specific auth (#24133)
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 4bb10ca78ca064e05669ccb358cdff9efc0da6fc
Co-authored-by: Glucksberg <80581902+Glucksberg@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
9 months ago
Peter Steinberger 1c753ea786 test: dedupe fixtures and test harness setup 9 months ago
Peter Steinberger 9f508056d3 test: collapse remaining trigger command shards 9 months ago
Peter Steinberger d90e9f561f test: merge overlapping trigger-handling suites 9 months ago
Peter Steinberger af547ec52c test: consolidate trigger-handling suites 9 months ago
Peter Steinberger 382fe8009a refactor!: remove google-antigravity provider support 9 months ago
Tak Hoffman 5c9f9722af
Agent runner: align compaction floor guidance (#24059) 9 months ago