eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Simplify references and output instructions in LLM prompts

Browse Source
This commit is contained in:
Eric Rakestraw
2026-09-25 12:38:23 +00:00
parent 325c4ea7d3
commit 011b021d47
31 changed files with 248 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
docs/internal/validators.md
View File

@@ -63,12 +63,14 @@ Oversized single inputs are rejected with a consolidated
model failures make only their batch candidates unavailable while other
batches continue. PromptKit validates each complete response against the
validator-decision JSON Schema and performs configured structural repair before
Audita receives decoded decisions. Audita then reconciles those decisions with
the correction indices requested in that batch: one usable entry keeps its
Audita receives decoded decisions. Each actual batch presents candidates
numbered from 1, independent of their internal proposal indices. Audita then
reconciles those local references: one usable entry keeps its
approval or editorial rejection; a missing or duplicate requested entry makes
only that candidate unavailable; unexpected indices are ignored. An empty list
makes all requested candidates unavailable. Results are ordered by request
identity and satisfy strict internal cardinality before the runner advances
makes all requested candidates unavailable. Decisions and unavailable indices
map back to internal proposal identities; results are ordered by request identity
and satisfy strict internal cardinality before the runner advances
approved candidates. An unavailable candidate never advances as approved.
Invalid confidence in a decoded test double also makes only its candidate
unavailable; production schema validation still rejects out-of-range confidence
@@ -79,6 +81,12 @@ chain without returning unchecked candidates as approved. Reconciliation makes
no semantic retry or extra model call; guided recovery remains
[deferred](../roadmap/future.md#domain-aware-response-recovery).
Debug request metadata records `proposal_indices` in local-reference order
(reference 1 is the first entry). Raw decoded responses and ignored indices use
local references; reconciled decisions and unavailable indices use internal
proposal indices. Batch token estimates use the same locally numbered payload
as prompt encoding.
## Decision and Rejection Reporting
Runner collects decisions, rejected candidates, and operation outcomes. Ledger
@@ -111,9 +119,11 @@ is covered by [report assembly](diagnostics-reporting.md).
## Supplemental Validation Context
Each candidate includes the immediately preceding and following source segments
available within its fixed chunk, plus glossary entries whose names, aliases, or
available within its fixed chunk, labeled `preceding` or `following` with speaker,
text, and categories, plus glossary entries whose names, aliases, or
recognized plurals appear in its original/resulting text or those neighbors.
Glossary matching reuses the protected vocabulary; entries retain glossary order.
Model-facing candidate and neighboring context omit internal segment IDs.
This supplies evidence such as a troupe definition for a proposed `Jesters`
correction or an adjacent speaker turn explaining deliberate repetition. A correction
already clear from its own segment does not require such evidence. No audio,