Improve semantic reconciliation retries
This commit is contained in:
@@ -115,6 +115,16 @@ eligible producers. Deterministic skip, limit, and fallback outcomes carry no
|
||||
model candidate, so a later rejection applies terminal policy without spending
|
||||
an ineffective semantic retry.
|
||||
|
||||
When proposal assessment or typed group application rejects a structurally
|
||||
valid group, the normalizer may return its safe partial value with a
|
||||
module-requested retry. A feedback-capable directive supplies bounded
|
||||
model-facing correction guidance separately from operator diagnostics and
|
||||
retains the exact proposal response as its candidate. The shared stage retry
|
||||
mechanism appends that response and guidance to a fresh complete request. A
|
||||
structurally invalid completion has no valid candidate and therefore requests a
|
||||
feedback-free fresh attempt. On exhaustion, only the final safe fallback and
|
||||
its bounded process diagnostic advance to validation.
|
||||
|
||||
The core supplies a conservative generic prompt and the single private
|
||||
response schema. A domain prompt may substitute its semantic instructions but
|
||||
mounts the core-owned protocol and candidate/transcript presentation assets.
|
||||
|
||||
Reference in New Issue
Block a user