fix/no-reply-empty-content-detection #18

hzhang · 2026-03-09T21:49:54Z

hzhang commented

2026-03-09 21:49:54 +00:00

No description provided.

hzhang added 3 commits 2026-03-09 21:49:55 +00:00

fix: stop treating empty content as NO_REPLY, detect tool calls 1f846fa7aa

Problems fixed:
1. before_message_write treated empty content (isEmpty) as NO_REPLY.
   Tool-call-only assistant messages (thinking + toolCall, no text)
   had empty extracted text, causing false NO_REPLY detection.
   In single-agent channels this immediately set turn to dormant,
   blocking all subsequent responses for the entire model run.

2. Added explicit toolCall/tool_call/tool_use detection in
   before_message_write — skip turn processing for intermediate
   tool-call messages entirely.

3. no-reply-api/server.mjs: default model name changed from
   'dirigent-no-reply-v1' to 'no-reply' to match the configured
   model id in openclaw.json, fixing model list discovery.

Changes:
- plugin/hooks/before-message-write.ts: toolCall detection + remove isEmpty
- plugin/hooks/message-sent.ts: remove isEmpty from wasNoReply
- no-reply-api/server.mjs: fix default model name
- dist/dirigent/index.ts: same fixes applied to monolithic build
- dist/no-reply-api/server.mjs: same model name fix

fix: add no-reply model to agents.defaults.models allowlist bddc7798d8

Changes:
- Change default provider ID from 'dirigentway' to 'dirigent'
- Add no-reply model to agents.defaults.models allowlist during install
- Fix no-reply-api server default model name from 'dirigent-no-reply-v1' to 'no-reply'

This fixes the issue where dirigent/no-reply model was not showing in
'openclaw models list' and was being rejected as 'not allowed'.

fix: skip rules-based no-reply override when turn manager allows agent 08f42bfd92

When the turn manager determines it's an agent's turn (checkTurn.allowed),
the rules engine's evaluateDecision() could still override the model to
no-reply with reason 'rule_match_no_end_symbol'. This happened because:

1. The sender of the triggering message (another agent) was not in the
   humanList, so the rules fell through to the end-symbol check.
2. getLastChar() operates on the full prompt (including system content
   like Runtime info), so it never found the end symbol even when the
   actual message ended with one.

Fix: return early from before_model_resolve after the turn check passes,
skipping the rules-based no-reply override entirely. The turn manager is
the authoritative source for multi-agent turn coordination.

Tested: 3-agent counting chain ran successfully (3→11) with correct
NO_REPLY handling when count exceeded threshold.

hzhang merged commit 13d5b95081 into main

2026-03-09 21:49:59 +00:00

hzhang deleted branch fix/no-reply-empty-content-detection

2026-03-09 21:49:59 +00:00

hzhang referenced this issue from a commit

2026-03-09 21:50:00 +00:00

Merge pull request 'fix/no-reply-empty-content-detection' (#18) from fix/no-reply-empty-content-detection into main

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: nav/Dirigent#18