dev/nisse
2
1 Fork 0
Code Issues 23 Pull Requests Actions Packages Projects Releases 1 Wiki Activity

A model's safety-filter refusal is an error that says so, not an empty reply #165

Merged
dev-agent merged 2 commits from expert-refusal into main 2026-10-18 14:09:13 +00:00
Conversation 6 Commits 2 Files Changed 4
+100 -2
2 Commits
Author SHA1 Message Date
dongarandClaude Opus 5.5 369b6ed52f test_expert: a declined consult hands back the clients' real wording
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m40s
Details
CI / e2e (pull_request) Successful in 4m5s
Details 
The fake client raises _refused() from llm.py, and the test checks the
whole handback, so a change to the real message fails it (review on #165).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
 2026-10-18 14:01:15 +00:00
dongarandClaude Opus 5.5 9d2992c20a A model's safety-filter refusal is an error that says so, not an empty reply
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 2m25s
Details
CI / e2e (pull_request) Successful in 4m41s
Details 
Opus's provider filter declined one of nisse-review's ask_expert
questions (which repositories a Gitea token can list) every time. It came
back as a 200 with no text, and the expert reported "unparseable reply:
empty reply". Both LLM clients now raise ModelRefused for
finish_reason content_filter (chat route) and stop_reason refusal
(passthrough). The expert's handback says what happened and what to do
instead.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
 2026-10-18 13:39:26 +00:00