Give each correction repair branch its own outcome

This commit is contained in:
2026-11-16 14:36:07 +00:00
parent a0c70e8dce
commit e2710d869e
11 changed files with 309 additions and 233 deletions

View File

@@ -22,8 +22,9 @@ the CLI identifies the role, profile, and environment variable using the native
diagnostic. See the [integration contract](../integrations/openai-compatible-llm.md)
for failure behavior and the [configuration reference](../config.md) for sources.
When correction repair is enabled, the proposal call captures a native immutable
PromptKit exchange. Each actionable correction starts an independent
When correction repair is enabled, the runner checks the module's repair prompt
and coordinator before submitting proposal work. The proposal call captures a
native immutable PromptKit exchange. Each actionable correction starts an independent
`Engine.Coordinate` branch from that exchange. PromptKit assembles continuation
history, owns the additional-turn budget, and delivers the last permitted response
for assessment. Follow-ups select the repair prompt, profile, and output schema
@@ -36,7 +37,8 @@ Prepared requests and terminal output travel in the returned response for an
optional interaction artifact. Logical call notifications carry metadata.
Audita owns actionable rejection, revision decoding, withdrawal, current previews,
and full revalidation. Accepted siblings remain independent. Requesting more work
and full revalidation. Each branch returns its attempt facts and final approval
to the section runner. Accepted siblings remain independent. Requesting more work
at the budget boundary produces exhaustion without allocating another logical call.
A canceled, undelivered response supplies diagnostic evidence only; it cannot enter
the approved set. Repair disabled in configuration bypasses coordination entirely.