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

Collect PromptKit execution observations with logical attribution

Browse Source
This commit is contained in:
Eric Rakestraw
2026-09-24 02:23:57 +00:00
parent 4812032c9e
commit 4bfc5f3456
11 changed files with 457 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/internal/llm-runtime.md
View File

@@ -30,5 +30,9 @@ PromptKit's per-backend admission applies to both roles and every generation,
retry, and repair. The runner still processes module instances in order,
collects concurrent section work deterministically, and cancels remaining
section work on a runtime failure. `llm.DiagnosticsWriter` remains the protected
request/response artifact writer. Execution observations and report summaries
are completed by the following roadmap work.
request/response artifact writer. `llm.ObservationCollector` captures metadata
events under a short mutex and freezes them after runner work joins. Its logical
records include preparation failures; summary usage comes from terminal events
once per call and retains knownness and completeness for each field. Runner wall
and validator timings remain separate from provider attempts. The report and
artifact mapping is completed by the following roadmap work.