2.5 KiB
2.5 KiB
Step 6: the digest step
Built 2026-10-13.
What was built
sourcesonExecutionEngine.start, and on/generateand A2A message metadata: files by name. The Workflow'sdigestreads the ones it knows and returns aDigested: the spec's fields, the sources it used, and a note per field of where it was read from. A Workflow with nodigestreads none.scope.merged: the digested spec with what the caller supplied laid over it, field by field. What the caller wrote wins.- A new provenance,
digested. It stands as a supplied value does: the scope analyst cannot overwrite it, and only the customer's own answer changes it. The completed spec'sprovenanceandreadiness, and the information register, count digested values apart.readinesshas thedigestedkey only when something was digested, so a spec that was not is recorded as before. - Sources are kept as supplied, under the Customer case's
intent/NNN.sources/, each with its hash inhistory.json, in the Execution's state and inexecution.json. - A source code did not read is a document for the Specialist that completes the spec, in its context as
source_documents, up to 60,000 characters each. - Refused before anything runs or is written: a source whose name is not a safe relative path, sources that are not text by name, and a source of a kind the Workflow knows and cannot read.
Differed from the plan
- The plan had the inventory travel as a separate data file to the Specialists that use it. It still travels in the spec's data file, to every Specialist. That needs the engine to let a Workflow say which of a spec's fields are shown to whom, and is not built.
- A Workflow still cannot name the spec's two files; they are
scope.yamlandscope.json.
Tests
tests/toy/test_digest.py: eight tests on the toy Workflow with a small catalogue and a digest of a made-up format. 529 pass in all.
Verified
pytest -q: 529 passed. ruff check ., ruff format --check ., mypy .: clean.
A guard added after, 2026-10-14
In an Execution with nobody to answer, a Specialist that ends three runs running without submitting its Deliverable now stops the Execution with a warning (MAX_UNFINISHED_RUNS in nodes/execution_nodes.py). Each such run is answered automatically and run again; with no guard it went on until the Orchestrator's turn limit. An operating model evaluation case looped this way for about two and a half hours. A submission resets the count. Two tests on the toy Workflow; 531 pass.