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.

View File

@@ -503,6 +503,22 @@ Check independent approved siblings, attempts/turn counts, actual branch
history and feedback, final-turn revalidation, and associated artifacts in
production coordination.
**Complete.** The runner checks repair capability before proposal dispatch.
Each proposal branch owns its history reference, attempt facts, and terminal
outcome. The section merges the returned evidence and approvals. Tests exercise
PromptKit coordination for independent histories, replacement prompts,
structural repair, final-turn revalidation, and retained siblings and
artifacts. The CLI build, full offline suite, and targeted race checks passed.
The three-correction CLI fixture used two repair branches and three repair
turns, with four revalidation requests and ten provider requests overall.
The default prompt sent 9,487, 13,385, and 9,483 repair request bytes in both
debug modes. Debug produced 39 files totaling 135,659 bytes in the observed
run, compared with zero files when disabled. The replacement prompt sent
6,303, 7,017, and 6,299 repair request bytes and produced 122,943 debug bytes
across 39 files. The fixture supplied no provider token usage. Temporary
measurement instrumentation was removed.
## Stage 15 — Give stage execution one commit boundary
Audit #14, #15 (evidence), #22 and #41 (failure facts).