- Add waitIdentifier config (default: 👤) to DirigentConfig and plugin schema
- Prompt injection: tells agents to end with 👤 when they need a human reply,
warns to use sparingly (only when human is actively participating)
- Detection in before_message_write and message_sent hooks
- Turn manager: new waitingForHuman state
- checkTurn() blocks all agents when waiting
- onNewMessage() clears state on human message
- Non-human messages ignored while waiting
- resetTurn() also clears waiting state
- All agents routed to no-reply model during waiting state
- Update docs (FEAT.md, CHANGELOG.md, TASKLIST.md, README.md)
- Delete NEW_FEAT.md
- Create FEAT.md with complete feature documentation across all versions
- Update README.md to reflect individual tool names and add @mention override
Feature 1: Split dirigent_tools
- Replace monolithic dirigent_tools (9 actions) with 9 individual tools
- Discord: dirigent_channel_create, dirigent_channel_update, dirigent_member_list
- Policy: dirigent_policy_get, dirigent_policy_set, dirigent_policy_delete
- Turn: dirigent_turn_status, dirigent_turn_advance, dirigent_turn_reset
- Extract shared executeDiscordAction() helper
Feature 2: Human @mention override
- When humanList user @mentions agents, temporarily override turn order
- Only mentioned agents cycle, ordered by their turn order position
- Original order restores when cycle returns to first agent or all NO_REPLY
- New: setMentionOverride(), hasMentionOverride(), extractMentionedUserIds()
- New: buildUserIdToAccountIdMap() for reverse userId→accountId resolution
Bump version to 0.3.0
- Use import.meta.url instead of api.resolvePath('.') to get script directory
- Add debug logging for no-reply-api and moderator bot startup
- Copy no-reply-api to dist during installation
- Remove from plugins.allow BEFORE deleting plugins.entries.dirigent
- OpenClaw validates that allow[] entries must exist in entries{}
- New order: allow → entry → paths → provider
- Use openclaw config unset instead of get-modify-set
- Avoids triggering full plugins config validation
- Handles both added and replaced entries uniformly
- For uninstall, always delete plugins.entries.dirigent
- Don't try to restore old config (which may fail validation due to missing required fields)
- Provider restoration still works (replaced providers are restored)
- Replace import.meta.url with api.resolvePath('.') for reliable path resolution
- Fixes no-reply API not starting due to incorrect pluginDir calculation
- Repeat install = reinstall: auto-detect existing install, uninstall first, then install
- Repeat uninstall = no-op: if no install record found, exit 0 with message
- Uses spawnSync to re-exec uninstall phase during reinstall
- Install: add 'dirigent' to plugins.allow if not present, record in delta
- Uninstall: remove 'dirigent' from plugins.allow if it was added by us
- Delta tracking preserves other allowlist entries
- Rewrite install/uninstall to use delta-tracking (added/replaced/removed)
- Install records only what the plugin changed:
* added: plugin新增的配置（卸载时删除）
* replaced: plugin覆盖的旧配置（卸载时恢复）
- Uninstall only affects plugin-managed keys, preserving user changes elsewhere
- Remove install-dirigent-openclaw.sh to avoid confusion
- Added gateway_start hook: spawns no-reply API as child process, then starts moderator bot
- Added gateway_stop hook: kills no-reply API process, stops moderator bot
- No-reply API server.mjs is located relative to plugin dir via import.meta.url
- Moderator presence moved from register() to gateway_start for proper lifecycle
- Fix enableWhispergatePolicyTool → enableDirigentPolicyTool in config schema and example
- Fix whisper-gateway → dirigentway in install script
- Add v0.2.0 changelog entry
- Improve README with scheduling identifier docs and English text
- Clean up plugin README with moderator handoff format docs
- Reformat TASKLIST with cleaner done markers
- Task 1: Identity prompt now includes Discord userId
- Task 2: Added configurable schedulingIdentifier (default: ➡️)
- Task 3: Moderator handoff uses <@userId>+identifier instead of semantic messages
- Task 4: All prompts/comments/help text converted to English
- Task 5: Full project rename WhisperGate → Dirigent across all files
Breaking: config key changed from plugins.entries.whispergate to plugins.entries.dirigent
Breaking: channel policies file renamed to dirigent-channel-policies.json
Breaking: tool name changed from whispergate_tools to dirigent_tools
When a speaker finishes with an end symbol, the turn was only advanced
in the message_sent hook. But by that time, the message had already been
broadcast to other agents, whose before_model_resolve ran with the old
turn state, causing them to be blocked by the turn gate (forced no-reply).
Fix:
- Move turn advance for both NO_REPLY and end-symbol cases to
before_message_write, which fires before the message is broadcast.
- Guard 1: Only the current speaker can advance the turn (accountId check).
- Guard 2: Only process assistant messages (role check). before_message_write
fires for incoming user messages too, which contain end symbols from other
agents and would cause cascading turn advances.
- Use sessionTurnHandled set to prevent double-advancing in message_sent.
When a speaker finishes with an end symbol, the turn was only advanced
in the message_sent hook. But by that time, the message had already been
broadcast to other agents, whose before_model_resolve ran with the old
turn state, causing them to be blocked by the turn gate (forced no-reply).
Fix: Move turn advance for both NO_REPLY and end-symbol cases to
before_message_write, which fires before the message is broadcast.
Use sessionTurnHandled set to prevent double-advancing in message_sent.
