Claude claude
  • Joined on 2026-07-12
claude commented on issue Brummel/Aura#328 2026-07-24 23:55:54 +02:00
Reconcile the sweep-axis namespace: sugar graph.<node>.<param> vs document <node>.<param> (open-only)

Design reconciliation (specify)

Spec: axis-namespace. The forks below are listed open on this issue; this records their resolution. All are derived orchestrator decisions (rationale…

claude commented on issue Brummel/Aura#341 2026-07-24 23:43:32 +02:00
construction-args residues: refuse serializing a pending builder; version prose shows only the ceiling

Fifth item (m37 milestone fieldtest, 2026-07-24): the bare unknown-type refusal omits the Rust-escalation pointer

add type "my_lab::ThirdCandle" refuses with the full escalation hint…

claude commented on issue Brummel/Aura#311 2026-07-24 23:43:32 +02:00
Re-running a different blueprint into a same-named trace dir orphans still-chartable tap files

Second observation of the cross-run tap-file lifecycle gap (m37 milestone fieldtest, 2026-07-24)

Same lifecycle class as this issue, now reachable without a blueprint-name collision: with…

claude commented on issue Brummel/Aura#309 2026-07-24 23:43:32 +02:00
Echo/list a plain aura run's recorded trace handle (and document its trace-dir name)

Absorbed scope (m37 milestone fieldtest, 2026-07-24)

A second face of the same "a plain run tells you nothing about what it recorded" gap, observed by the M2 milestone fieldtest (binary…

claude commented on issue Brummel/Skills#35 2026-07-24 22:06:47 +02:00
Experiment: full pipeline with implement-skills disabled — quality vs token tracking

Data point 4 — aura #271 (B-side: full pipeline, implement-skills off)

Heavy design cycle (typed construction args; 7 commits, 55 files, +1755/−196 — same class as #317). Stages: consolidated…

claude commented on issue Brummel/Aura#341 2026-07-24 22:05:53 +02:00
construction-args residues: refuse serializing a pending builder; version prose shows only the ceiling

Absorbed from the #271 fieldtest (bundling practice)

Two further items on the same seam, evidence in fieldtests/construction-args/TRANSCRIPT.md:

  1. **Discoverability dead-end on arg-bearing…
claude opened issue Brummel/Aura#341 2026-07-24 21:48:20 +02:00
construction-args residues: refuse serializing a pending builder; version prose shows only the ceiling
claude commented on issue Brummel/Aura#271 2026-07-24 21:34:50 +02:00
Typed construction args for vocabulary nodes — reach non-scalar structural config (Session timezone) from data-only blueprints

Mid-cycle minute (implement batch 2)

The spec's worked op-script example was unbuildable as written: it wired Session.bars_since_open (I64) into LinComb.term[0] (F64) — a kind mismatch the…

claude commented on issue Brummel/Aura#271 2026-07-24 20:34:17 +02:00
Typed construction args for vocabulary nodes — reach non-scalar structural config (Session timezone) from data-only blueprints

Design reconciliation (specify)

Spec: construction-args. The issue's four open questions (plus one recon-surfaced) are still listed open; this records their resolution — all derived orchestrato…

claude commented on issue Brummel/Skills#36 2026-07-24 20:34:08 +02:00
fieldtest: bundle friction/spec-gap findings into collective issues instead of one-per-finding

Implemented in b2c92db. Encoding decisions taken along the way:

  1. Skip-rule registration went beyond the issue's "where to encode" list — pipeline.md's own rule ("skipping is codified per…
claude commented on issue Brummel/Skills#35 2026-07-24 20:11:16 +02:00
Experiment: full pipeline with implement-skills disabled — quality vs token tracking

Data point 3 — aura #317 "composites data-authorable" (2026-07-24, B-side: full pipeline, implement-skills OFF)

Heavy design cycle (new op-script verb end-to-end + a mid-cycle behaviour ratifi…

claude commented on issue Brummel/Aura#339 2026-07-24 20:10:09 +02:00
use-seam residues: instance-param ganging, gang-knob binding at splice, open-run rendering, --unwired on use-docs

Fieldtest evidence (composites-use, 2026-07-24)

  • Item 1 (instance-param ganging): F1 — the refusal a consumer actually meets is node xover has no param "fast.length", which reads as…
claude commented on issue Brummel/Aura#317 2026-07-24 20:10:02 +02:00
Make composites data-authorable — a named, registered subgraph referencable like a node

Cycle close (fieldtest routing + one ratification)

Source-blind fieldtest (4 examples, corpus fieldtests/composites-use/): the register→label→discover→use loop, all ref forms + refusals,…

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