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

Deliver target references during pipeline preparation

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-20 18:57:44 +00:00
parent ac53f83ac8
commit 7806dba509
5 changed files with 167 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
docs/internal/modules.md
View File

@@ -19,11 +19,14 @@ validator chains and prompt asset collection.
Production input, chunk, output, and D&D spell-extract packages register strict
option decoders and run-local builders. Preparation decodes their options into
implementation-owned values and injects dependencies. The spell extractor is
typed over the canonical D&D model. D&D validators, merge, and normalize use
typed variants; JSON representation validators use serialized requests; and
unconditional validators expose separate chunk and typed variants. The D&D
production registrar registers only the canonical typed spell implementations.
implementation-owned values and injects dependencies plus the materialized
reference set for the selected target. Each builder receives an isolated clone
of that set; input and output builders receive no references. The spell
extractor is typed over the canonical D&D model. D&D validators, merge, and
normalize use typed variants; JSON representation validators use serialized
requests; and unconditional validators expose separate chunk and typed
variants. The D&D production registrar registers only the canonical typed spell
implementations.
Prepared extractors, extract validators, and codecs may be reused concurrently
by the run-wide extract pool. Production implementations are immutable after

17
docs/internal/pipeline.md
View File

@@ -53,10 +53,19 @@ against its resolved target declaration, reads and validates the file, and
builds both a `contracts.ReferenceSet` and provenance-only metadata on the
corresponding `ResolvedReferenceTarget`.
The runner clones the resulting set into the chunk, extract, merge, or normalize
request that owns the target. LLM-backed extensions may convert those items into
named prompt inputs. Reference content remains separate from source evidence and
source digests.
Preparation delivers the materialized set for each target through
`pipeline.BuildRequest`: chunkers and chunk validators receive the chunk target;
extractors and extract validators receive the lane extract target; mergers and
merge validators receive the lane merge target; and normalizers and normalize
validators receive the lane normalize target. Input and output builders receive
an empty set because those stages cannot declare references. Every builder gets
an isolated deep clone of its target set, so construction-time mutation cannot
change another builder, the resolved pipeline, or later runtime requests.
The runner continues to clone the resulting set into the chunk, extract, merge,
or normalize request that owns the target. LLM-backed extensions may convert
those items into named prompt inputs. Reference content remains separate from
source evidence and source digests.
Binding precedence, path resolution, accepted content, and media-type behavior
are configuration contracts; see [Configuration](../config.md#pipelines).