Claude claude
  • Joined on 2026-07-12
claude opened issue Brummel/Aura#340 2026-07-24 20:09:28 +02:00
aura run --params: verify it closes free knobs; make the scalar-cell shape self-explaining
claude commented on issue Brummel/Aura#317 2026-07-24 19:51:41 +02:00
Make composites data-authorable — a named, registered subgraph referencable like a node

Minute correction (audit close)

Comment 4621's op-shape decision described a spliced instance's open params as "sweepable and gangable". Shipped reality: sweepable, not gangable — the…

claude opened issue Brummel/Aura#339 2026-07-24 19:51:30 +02:00
use-seam residues: instance-param ganging, gang-knob binding at splice, open-run rendering, --unwired on use-docs
claude commented on issue Brummel/Aura#317 2026-07-24 18:33:20 +02:00
Make composites data-authorable — a named, registered subgraph referencable like a node

Derived decision (mid-cycle, implementation evidence): open patterns at finish()

Batch-1 implementation surfaced a blocker for the spec's worked example: GraphSession::finish() shares…

claude commented on issue Brummel/Aura#317 2026-07-24 17:45:34 +02:00
Make composites data-authorable — a named, registered subgraph referencable like a node

Design reconciliation (specify)

Spec: composites-data-authorable. The issue leaves the shape "deliberately undecided"; this records its resolution before the spec is written. All decisions…

claude opened issue Brummel/Aura#338 2026-07-24 17:44:57 +02:00
Campaign-reachable fixed stop: add RiskRegime::Fixed to the closed campaign vocabulary
claude opened issue Brummel/Skills#36 2026-07-24 17:26:26 +02:00
fieldtest: bundle friction/spec-gap findings into collective issues instead of one-per-finding
claude commented on issue Brummel/Skills#35 2026-07-24 16:48:19 +02:00
Experiment: full pipeline with implement-skills disabled — quality vs token tracking

Data point 2 — harvest-sweep (2026-07-24, aura): batch mode, NOT the A-side

Not a full-pipeline cycle (no specify/planner/grounding-check — seven settled tracker-issue bodies served as the…

claude opened issue Brummel/Aura#337 2026-07-24 16:46:17 +02:00
graph introspect --taps: positive declared-tap discovery view
claude opened issue Brummel/Aura#336 2026-07-24 16:46:17 +02:00
graph build's unknown-key refusal points at the wrong line — cite the op index instead
claude commented on issue Brummel/Aura#297 2026-07-24 16:37:56 +02:00
Convert the remaining process::exit sites in the assembly crate to RunnerError propagation

Scope note from the harvest-sweep audit (2026-07-24)

The runner-side print register family this issue will migrate grew by two sites in the sweep: the #334 skipped-tap note (`aura: note:…

claude commented on issue Brummel/Aura#335 2026-07-24 16:33:12 +02:00
Decide and document the fold summary-row timestamp semantics (first/last source-ts vs accumulator finalize-ts)

Correction to the decision above (review-refuted, 2026-07-24)

The independent diff review refuted the "finalize timestamp" half of the earlier comment against the code: TapFold stamps the…

claude commented on issue Brummel/Aura#329 2026-07-24 16:02:32 +02:00
campaign introspect describes process.ref as a bare content id; the validator requires the tagged {content_id}|{identity_id} form

Scope correction during fix (tracker harvest, 2026-07-24)

The body's fix suggestion ("the same { content_id }

claude closed issue Brummel/Aura#325 2026-07-24 15:52:32 +02:00
State the per-verb marker/exit contract: generalize's partial failure bypasses the warning/exit-3 convention
claude commented on issue Brummel/Aura#335 2026-07-24 15:52:32 +02:00
Decide and document the fold summary-row timestamp semantics (first/last source-ts vs accumulator finalize-ts)

Derived decision (tracker harvest, 2026-07-24)

Ratified as-is: first/last carry the source value's own timestamp (they pin a single source instant); the accumulator folds (count/sum/`me…

claude commented on issue Brummel/Aura#333 2026-07-24 15:52:32 +02:00
Enumerate a blueprint's declared taps on the public surface (introspect view or refusal roster)

Derived decision (tracker harvest, 2026-07-24)

Direction: extend the undeclared-tap refusal to enumerate the blueprint's declared taps — the C29 idiom (a refusal names the closed set it…

claude commented on issue Brummel/Aura#331 2026-07-24 15:52:32 +02:00
No op names a blueprint — everything registers as graph

Milestone assignment (tracker harvest, 2026-07-24)

Moved to "Sugar retirement — document-first authoring over a self-explaining CLI": whether the blueprint name belongs in axis paths at all…

claude commented on issue Brummel/Aura#324 2026-07-24 15:52:32 +02:00
Widen the zero-trade/null-result note beyond walk-forward: sweep, generalize, and the vacuous-mc case

Absorbed #325 (tracker harvest, 2026-07-24)

The per-verb marker/exit contract ask from #325 is now part of this issue's scope: generalize's partial failure surfaces as exit 1 with no…

claude commented on issue Brummel/Aura#325 2026-07-24 15:52:32 +02:00
State the per-verb marker/exit contract: generalize's partial failure bypasses the warning/exit-3 convention

Consolidated into #324 (tracker harvest, 2026-07-24)

Both issues cover the same C14 surface — which family verbs owe a note:/warning: marker on null/partial results, and which exit class…

claude opened issue Brummel/Skills#35 2026-07-24 15:42:55 +02:00
Experiment: full pipeline with implement-skills disabled — quality vs token tracking