mirror of
https://github.com/openclaw/openclaw.git
synced 2026-09-29 17:19:00 +08:00
* fix(agents): keep spawned workers out of the current conversation Agent-spawned workers (sessions_spawn thread=true, native and ACP) may only bind a new child thread. Channels whose spawn placement is the current conversation (Telegram, Feishu, LINE, generic current-conversation bindings) now reject thread=true instead of handing the user's chat to the worker. Legacy spawn-created bindings on those channels are ignored by the binding service, so the conversation routes to its normal agent again. Discord/Matrix child-thread sessions and defaultSpawnContext are unchanged. * test(telegram): expect parent routing after worker-takeover upgrade * test(agents): refresh prompt snapshots for child-only thread spawns * test(telegram): keep parent-phase checkpoint codes in public upgrade evidence
Generated Docs Artifacts
Generated contract files are tracked drift-detection artifacts. Full pretty snapshots remain local inspection artifacts.
Tracked (committed to git):
config-baseline.sha256— hashes of config baseline JSON artifacts.config-baseline.counts.json— maximum entry counts for each config baseline kind.sqlite-session-transcript-schema-baseline.sha256— hash of the sessions/transcripts SQLite schema baseline.
Local only (gitignored):
config-baseline.json,config-baseline.core.json,config-baseline.channel.json,config-baseline.plugin.json.artifacts/sqlite-session-transcript-schema-baseline.sql
Do not edit any of these files by hand.
- Regenerate config baseline:
pnpm config:docs:gen - Validate config baseline:
pnpm config:docs:check - Regenerate SQLite sessions/transcripts schema baseline:
pnpm sqlite:sessions-schema:gen - Validate SQLite sessions/transcripts schema baseline:
pnpm sqlite:sessions-schema:check