Claude claude
  • Joined on 2026-07-12
claude closed issue Brummel/Aura#314 2026-07-23 06:36:24 +02:00
Triage the findings of the 2026-07-22 external release-binary field test
claude commented on issue Brummel/Aura#314 2026-07-23 06:36:24 +02:00
Triage the findings of the 2026-07-22 external release-binary field test

Decision log — filed and decided autonomously (agent-driven run, 2026-07-23); no human review at filing time.

  • Churn finding routed to documentation, not bug. Options considered: (A) file…
claude commented on issue Brummel/Aura#267 2026-07-23 06:36:23 +02:00
Ship a generated agent bootstrap card

Field evidence for what the bootstrap card must cover — from the 2026-07-22 external field test (an LLM agent driving the release binary with no source or docs access; triage in #314):

1.…

claude opened issue Brummel/Aura#314 2026-07-23 06:36:23 +02:00
Triage the findings of the 2026-07-22 external release-binary field test
claude opened issue Brummel/Aura#313 2026-07-23 06:36:23 +02:00
Emit an explicit notice when every window of a walk-forward records zero trades
claude opened issue Brummel/Aura#312 2026-07-23 06:36:23 +02:00
Persist a price/signal tap pair so measure ic is reachable from the release binary
claude commented on issue Brummel/Aura#297 2026-07-22 00:37:24 +02:00
Convert the remaining process::exit sites in the assembly crate to RunnerError propagation

Fieldtest evidence (cycle #283, example refusal_probe)

The tap-subscribers fieldtest hit exactly this edge from the downstream side. A World-program consumer that subscribes an unknown fold…

claude opened issue Brummel/Aura#311 2026-07-22 00:37:24 +02:00
Re-running a different blueprint into a same-named trace dir orphans still-chartable tap files
claude opened issue Brummel/Aura#310 2026-07-22 00:37:24 +02:00
Decide the Named fold subscription's data-authorability boundary — data selector vs Rust-only
claude opened issue Brummel/Aura#309 2026-07-22 00:37:23 +02:00
Echo/list a plain aura run's recorded trace handle (and document its trace-dir name)
claude opened issue Brummel/Aura#308 2026-07-21 23:48:07 +02:00
Migrate the legacy Recorder surface onto the tap-subscriber delivery shape
claude commented on issue Brummel/Aura#283 2026-07-21 21:16:58 +02:00
Drain taps during the run — subscribers (stream-to-disk, fold, live consumer) replace buffer-then-drain

Spec auto-sign (grounding-check PASS, no human in the loop)

The re-produced tap-subscribers spec — the registry model recorded in the design-revision comment (issues/283#issuecomment-4218) —…

claude commented on issue Brummel/Aura#283 2026-07-21 21:05:39 +02:00
Drain taps during the run — subscribers (stream-to-disk, fold, live consumer) replace buffer-then-drain

Design revision (user decision, 2026-07-21) — one consumer mechanism, layered fold registry

During implementation review the user re-examined the signed design's three parallel subscription…

claude opened issue Brummel/Skills#34 2026-07-21 19:25:17 +02:00
Reconcile the task_text_path carrier contract with implement-loop's inline task-text handoff
claude commented on issue Brummel/Aura#283 2026-07-21 18:56:15 +02:00
Drain taps during the run — subscribers (stream-to-disk, fold, live consumer) replace buffer-then-drain

Spec sign-off (user decision)

The tap-subscribers spec passed the grounding-check (all load-bearing assumptions ratified by named green tests) and was approved by Brummel, 2026-07-21.

One…

claude opened issue Brummel/Aura#307 2026-07-21 18:49:29 +02:00
Binary/compact on-disk trace format — JSON does not scale to multi-million-point series
claude commented on issue Brummel/Aura#283 2026-07-21 18:28:22 +02:00
Drain taps during the run — subscribers (stream-to-disk, fold, live consumer) replace buffer-then-drain

Scope amendment (specify, grounding-check finding)

The fresh-context grounding-check surfaced a second declared-tap entry point this issue (and C27's Current state) never mentioned: `run_measur…

claude commented on issue Brummel/Aura#283 2026-07-21 18:13:24 +02:00
Drain taps during the run — subscribers (stream-to-disk, fold, live consumer) replace buffer-then-drain

Fold vocabulary v1 amendment (user decision)

FoldKind gains First — kind-preserving, binds at any kind, its emitted row carries the first warm value's timestamp (every other fold's row…

claude commented on issue Brummel/Aura#283 2026-07-21 18:02:43 +02:00
Drain taps during the run — subscribers (stream-to-disk, fold, live consumer) replace buffer-then-drain

Design reconciliation (specify)

Spec: tap-subscribers (in production, combined cycle with #77). The 2026-07-20 design comments settled the model (one tap concept, consumers as subscribers,…

claude commented on issue Brummel/Aura#77 2026-07-21 18:02:43 +02:00
Rename Recorder -> Probe (the edge tap); decide whether a Probe must heap-allocate a record per cycle

Design reconciliation (specify)

Spec: tap-subscribers (in production, combined cycle with #283). This issue's part 1 (rename Recorder -> Probe) is still listed open; this records its…