Add sendTarget param to createFeishuReplyDispatcher that overrides
the to: field for visible sends. Fix streaming card delivery target
by stripping routing prefixes (user:, chat:) before the Feishu
streaming API call. Route streaming card reply metadata through
suppressed sendReplyToMessageId.
Closes#83730
* fix(slack): expose sender bot status in context
* fix(slack): expose sender bot status in context
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(googlechat): expose sender bot status in context
* fix(googlechat): expose sender bot status in context
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(discord): expose sender bot status in context
* fix(discord): expose sender bot status in context
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(memory-wiki): strip fenced code blocks before wikilink extraction
extractWikiLinks runs OBSIDIAN_LINK_PATTERN against full markdown
including fenced code blocks and inline code spans, causing false
positive 'Broken wikilink target' warnings for bash [[...]] test
syntax and Scala generics inside code blocks.
Strip fenced code blocks and inline code before running the wikilink
regex to eliminate code-block false positives while preserving real
wikilinks in prose.
Fixes#97945
* fix(memory-wiki): strip fenced code blocks before wikilink extraction
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
When a proxied Anthropic-Messages endpoint degrades a native tool_use block
into plain text, the assistant emits antml:namespaced XML tags
(<antml:invoke>, <antml:parameter>). These were not recognized by the
visible-text sanitizer, leaking tool-call XML into user-visible replies.
Added antml: (and mm:) namespace handling to:
- TOOL_CALL_QUICK_RE regex for fast pre-check
- TOOL_CALL_TAG_NAMES set for tag name recognition
- Tag name scanner to accept ':' in tag names
- TOOL_CALL_XML_PAYLOAD_START_RE for XML payload detection
- shouldDetectXmlPayload to include antml:invoke tags
Fixes#97750.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(agents): skip pre-prompt precheck when context engine owns compaction
When a context engine advertises ownsCompaction=true (e.g. lossless-claw),
skip the pre-prompt preemptive overflow precheck entirely. The engine
already manages the context budget through assemble() and its own
compaction lifecycle — the built-in precheck is redundant and causes
false-positive overflow errors for CJK-heavy sessions due to its
conservative token estimation formula.
Safety is preserved: if the model's actual context limit is exceeded,
the model API returns an error that the outer overflow-compaction retry
loop handles normally.
* fix(agents): assert non-null context engine in precheck skip log
* test(context-engine): cover owning precheck contract
* fix(agents): preserve precheck after context assembly failure
---------
Co-authored-by: Josh Lehman <josh@martian.engineering>
* test(globals): add unit tests for global CLI flag state helpers
Add unit tests for shouldLogVerbose, logVerbose, and logVerboseConsole
functions in src/globals.ts to verify verbose logging behavior.
Tests cover:
- shouldLogVerbose returns true when isVerbose is true
- shouldLogVerbose returns true when file log level is debug
- shouldLogVerbose returns false when both are false
- logVerbose does not log when shouldLogVerbose is false
- logVerbose logs to console when isVerbose is true
- logVerboseConsole does not log when isVerbose is false
- logVerboseConsole logs to console when isVerbose is true
* ci: trigger re-review
* test(globals): cover verbose logger behavior
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
Preserve shared reasoning suppression by default while letting Telegram opt into durable reasoning payloads only when it has a deliverable reasoning lane. Covers persistent /reasoning on, separate reasoning stream lanes, and progress-stream suppression.\n\nVerification:\n- node scripts/run-vitest.mjs src/auto-reply/reply/dispatch-from-config.test.ts extensions/telegram/src/bot-message-dispatch.test.ts\n- git diff --check upstream/main...HEAD\n- .agents/skills/autoreview/scripts/autoreview --mode branch --base upstream/main --stream-engine-output\n- CI run 28411526182 green, including QA Smoke CI and check-test-types\n- Real behavior proof run 28411676681 passed\n\nPR: #97875
