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

Enhance debug output to include response content files and update related metadata handling

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-08 08:52:19 -05:00
parent 68ec69f2e4
commit 610bdb4fea
6 changed files with 178 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/internal/pipeline.md
View File

@@ -90,8 +90,10 @@ current run ID. The runner writes framework-boundary inputs, outputs,
structured LLM calls, validator calls, timing, and retry attempt metadata
through that interface. Each retry or validator attempt records any LLM calls
made within that attempt in an `llm_calls` array and writes paired
`prompt-000N.json` and `response-000N.json` files under the attempt directory.
Debug output is not used for resume and can contain sensitive source,
`prompt-000N.json` and `response-000N.json` metadata files under the attempt
directory. LLM response bodies are written as sibling `response-content-000N.*`
files, using pretty-printed JSON when the content is valid JSON and raw text
otherwise. Debug output is not used for resume and can contain sensitive source,
reference, prompt, and model-output material. Concrete modules still do not
receive workspace paths.

18
docs/operations.md
View File

@@ -139,14 +139,16 @@ Debug artifacts include framework-boundary inputs and outputs for source,
chunk, extract, merge, normalize, and output work, structured LLM request and
response data from Notarius contracts, validator requests and results, timing,
and retry attempt metadata. LLM calls made inside a retry or validator attempt
write paired `prompt-000N.json` and `response-000N.json` files under that
attempt directory and are linked from the attempt `llm_calls` array. Prompt and
response content in those artifacts is written as raw text for inspection.
Debug artifacts may contain source material, reference material, prompt inputs,
model outputs, and other sensitive data. API keys are not written, and obvious
credential-shaped values and sensitive map keys are redacted in framework
envelopes, but debug directories should still be protected as sensitive local
state.
write `prompt-000N.json`, `response-000N.json`, and
`response-content-000N.*` files under that attempt directory and are linked from
the attempt `llm_calls` array. Prompt content is written inline in the prompt
artifact. Response metadata is written to `response-000N.json`, while the
response body is written separately as pretty-printed JSON when possible or as
raw text otherwise. Debug artifacts may contain source material, reference
material, prompt inputs, model outputs, and other sensitive data. API keys are
not written, and obvious credential-shaped values and sensitive map keys are
redacted in framework envelopes, but debug directories should still be protected
as sensitive local state.
## Retention