The #190 cycle-close audit found two now-stale claims that predate this
cycle's guard test: the ledger's known-debt note listed the metric-roster
triplication as tracked by #190 (the issue that just added the guard, closing
on push), and metric_vocabulary()'s doc comment told a hand-editor to keep the
list in sync by hand without mentioning that a red test now catches a desync.
Reconcile both to the honest state: the triplication remains (still a
hand-list) but drift from the shipped aura-analysis types is now caught by the
cross-crate guard `aura-campaign/tests/metric_vocabulary_e2e.rs`; the
single-source removal that would delete the hand-list is tracked under #147
(where the metric vocabulary's home is decided).
refs #190, #147
The #168 refusal left sibling --trace surfaces still lying and the design ledger
still describing CLI --trace as a live persist path (surfaced by the cycle-close
architect drift review). Reconcile them to record reality:
- the chart NotFound hint no longer points at `aura run --trace` (itself refused);
it names the live trace-writer (a campaign document's persist_taps presentation).
- RunCmd/McCmd --trace help stop promising persistence (both flags already refuse).
- README drops --trace from the live naming flags.
- the ledger records the CLI --trace retirement: per-member --trace was never
wired to the blueprint sweep (`let _ = persist`) and was silently dropped at
#159/#220 — it never migrated as the old HISTORY note claimed; the single live
TraceStore::write is the campaign persist_taps; restoration is deferred to #224.
Workspace suite green (62 groups / 0 failed), clippy -D warnings clean.
closes#168
refs #216
Architect drift review over 68317ec..6e22c98 (two items, both fixed here;
code and ledger verified drift-clean):
- The authoring guide's 'Register and run' transcript still showed the
pre-regime world (2 cells, regime-less family ids) directly under the
worked example this cycle made two-regime / 4-cell. The transcript now
shows the -r1 family-id suffix, per-cell regime fields (ordinal 0
serialize-skipped, the established byte-stability pattern), the four
cells, per-regime generalization entries, and a prose paragraph tying
the 4 cells to the validate count (regimes compared, never pooled).
- The fresh glossary entry declared 'Avoid: stop regime' while this very
cycle ships 'stop regimes' in its hint strings and guide prose — an
Avoid line the codebase itself violates records intent, not reality.
'stop regime' is dropped from Avoid ('risk section' stays: it wrongly
suggests a section rather than an axis list).
What holds (architect): content-id parity untouched (probe is read-only,
canonical bytes unchanged); the validate cell product mirrors the exec
cross-product exactly; all six spec acceptance criteria shipped.
Regression: cargo test --workspace 62 result groups / 0 failures; clippy
-D warnings clean; cargo doc 0 warnings (all at 6e22c98; this commit is
docs-only).
closes#216
The remaining introspection e2e pins: the bare-{} envelope probe (the
issue's exact reproduction) lists the optional risk slot; a bound
(non-empty) risk list closes it (no open slots); an EXPLICIT empty
'risk': [] still counts as open (pins the non-emptiness branch, which an
is_none()-based probe would get wrong); the --block std::risk assert is
sharpened to pin the optional rendering and the block doc line (the old
bare contains("risk") matched std::risk trivially).
Docs: the authoring guide's bare-{} transcript gains the risk line, the
§3 worked example gains a two-regime risk section (heading updated), a
prose paragraph explains the structural risk axis (stop defines R;
absent = the same default vol regime the verbs bind), and both validate
transcripts show the new matrix counts. The glossary gains the
'risk regime' entry (canonical term; avoid: stop regime, risk section).
Verified: cargo test --workspace 62 result groups / 0 failures; clippy
-D warnings clean; cargo doc 0 warnings; the guide's transcript strings
grep-match the shipped hint/summary bytes (1/2/1).
Cycle-close audit for the stop-default cycle (af8564d RED + 2102305
GREEN). Architect review: what holds — the argv extractors and the
campaign member runner default to the same single-sourced regime
constants; the multi-value refusal and the C10/C20 regime semantics
survive; manifests stamp the resolved stop (C18). Three drift items,
all resolved fix-path here:
- generalize's default path was shipped untested; added the
generalize_args_from_defaults_missing_knobs_to_the_regime unit test
mirroring mc's sibling.
- The None=>default / Some=>parse+single-value stop block recurred 4x
across the walkforward/mc extractors; extracted into the generic
stop_knob_or helper (refusal strings byte-identical; generalize's
typed unwrap_or extractor deliberately not unified — no parsing
there).
- Ledger stop-defaulting note now records the two default
representations: sweep binds no regime (late-resolved by the member
runner), the three verbs bind the default eagerly into the document
— same R behaviour, deliberately different content ids.
Regression gate green, no baseline moved: full workspace suite 0
failures across all test-result groups; clippy -D warnings clean;
cargo doc 0 warnings. No spec/plan working files existed (tdd entry
path — the committed executable spec is the contract).
refs #217
Cycle-close audit for the verb-axis-generalization cycle (a2294c7,
e7efe1f, b849bb7). Architect drift review: what holds — all four verbs
route through the one validate_and_register_axes seam into the campaign
executor; RGrid gone workspace-wide; zero too_many_arguments allows in
verb_sugar.rs; no r_sma_open embed at the verb dispatch sites (the
aura-graph default embed survives by design). Five drift items found,
all resolved fix-path in this commit:
- README (blueprint-verbs section + mc row), glossary (walk-forward
entry), and ledger (verb-dissolution passage) reconciled to the
shipped generic grammar; the ledger HISTORY note now separates the
two supersessions correctly (#159 retired the built-in --strategy
demo surface; #220 de-welded the verbs) instead of mis-attributing
the weld removal to #159.
- Four stale characterization doc-comments in cli_run.rs reworded:
the retired welded grammar is now named as the pinned grades'
provenance, not the current spelling; one dangling reference to a
deleted test repointed to the live anchor.
- The quadruplicated dispatch blocks extracted into two shared helpers
beside validate_and_register_axes: exit_axis_register_error (the
AxisRegisterError exit-map, byte-identical stderr + exit codes) and
campaign_window_ms (from_choice -> full_window -> unix-ms clip);
generalize's explicit unclipped (Some, Some) passthrough arm is
untouched — only its fallback arm, which already ran the identical
mechanics, calls the helper.
Regression gate green, no baseline moved (nothing to ratify):
cargo test --workspace exit 0, 62 test-result groups, 0 failures;
clippy --workspace --all-targets -D warnings clean; cargo doc
--workspace --no-deps 0 warnings. Spent cycle spec + plan working
files discarded per lifecycle.
refs #220
Drops docs/whitepaper/ (Bevy ECS visualizer concept). The evaluation
against the design ledger found it re-litigates the settled
web-from-disk visual-face fork (#101/#192/#209) on incorrect premises;
the salvageable ideas (on-demand trace slices, sweep-surface heatmaps,
param-binding-path highlighting) belong in the tracker, not a side doc.
Adds a conceptual whitepaper outlining how to use the Bevy game engine and its ECS architecture to build a highly performant, WASM-ready 3D/2D visualization layer (Playground) for Aura's massive backtest datasets.
Cycle-close audit tidy for the #159 demo-retirement arc: behaviour-free
reword of prose/comments/docs left pointing at symbols the arc deleted.
Adversarially verified by the audit workflow; cargo build --workspace
--all-targets green.
- README: drop the removed `--harness` token; restrict the legacy built-in
form claim to walkforward/mc/generalize (run/sweep no longer resolve one).
- glossary: the built-in `--strategy` sweep surface is retired (#159), not a
live inline path.
- INDEX.md ledger: append [HISTORY] supersession markers (house style) to the
dated realization notes advertising the retired `--harness` / built-in
`--strategy` CLI forms (cost-flag #153, cycles 0065/0066/0067, name-res,
#210 status); historical text preserved.
- aura-engine test-fixture docs: drop dead cross-crate refs to the deleted
aura-cli fns sample_harness / build_sample and the deleted `macd` composite.
- cli_run.rs: reword the #159-cut-2 pin doc to the current clap generic-usage
reality (no strategy_from / Strategy::RBreakout); r_sma_sweep_family ->
blueprint_sweep_family.
- verb_sugar.rs: fix the pre-existing `E[R]` unresolved-doc-link warning.
Remaining tidy — the main.rs comment cluster plus its rustdoc link at :1546
(the second cargo-doc warning) — held for a follow-up issue. The dead
cost-graph branch is tracked in #221. refs #159
The spec/plan lifecycle is a fixed plugin convention (skills/docs/conventions.md, sections File layout + Lifecycle). Restating it here is a drift vector: it had already gone stale (said git-tracked while the plugin moved to git-ignored on Jul 2). Remove the restated paragraph and enforce the git-ignored model with a project-local docs/.gitignore.
The verb-dissolution STATUS paragraph read "cycle 0110 dissolved the first verb
… Remaining: generalize, walkforward, and mc's R-bootstrap path" — stale at HEAD,
where all four verbs are dissolved. The per-cycle audits were each scoped to
their own commit range, so the cumulative status line lagged; the milestone
close fieldtest (#210, 2026-07-07) surfaced the drift.
Refresh the paragraph to the completed state, and record the per-verb
dissolved-form asymmetry as intended scope (ratify): for sweep the dissolved
form is the blueprint file (`<bp.json> --real`) while `aura sweep --strategy
r-sma --real` stays the inline built-in path — the built-in `--strategy` demo
surface is #159's hard-wired-harness retirement target, not the dissolution's;
for generalize/walkforward/mc the dissolved form is `--strategy r-sma --real`.
Glossary: note in the sweep and walk-forward entries that the CLI verbs are now
thin sugar over the campaign path.
Milestone closed 2026-07-07 on a green end-to-end fieldtest (0 bugs). Forward
findings filed: #216 (risk-axis discoverability), #217 (verb knob asymmetry),
#218 (no-project store litter).
refs #210
The FOURTH and LAST verb dissolution is closed. Architect drift review
over 18060cb..7f5f576: all design contracts hold, debt only.
What holds (architect-confirmed by reading the diff):
- Pure sugar: only crates/aura-cli/ changed; aura-campaign/aura-engine/
aura-research are byte-for-byte diff-free — invariant 10 (no
verb-special engine logic) and invariant 12 (the World runs it through
the one campaign path) both hold.
- The seed decision is C10/C18-sound: campaign.seed = the mc --seed is a
content-addressed manifest field (reproducible-from-manifest), and the
wf winners are argmax hence seed-independent — the pooled OOS series is
unchanged, only the bootstrap draw moves. Pinned by the dedicated e2e.
- Fork A / Fork C faithful: single RiskRegime::Vol, multi-value stop
refused (aligns with the C20 regimes-are-compared realization);
--name/--trace rejection mirrors the inline r-path; defaults match
McArgs::RealR exactly; zero deletions (run_mc_r_bootstrap / run_mc
retained for the fenced synthetic/non-real paths, until #159).
Regression gate (verified by the orchestrator, not the agent report):
full workspace suite green (0 failed), clippy --all-targets -D warnings
clean, and the byte-identity anchor mc_r_bootstrap_real_e2e ran the real
GER40 archive (6.83s, no skip) and passed byte-for-byte — the
equivalence gate is green.
Deferred debt, tracked, carry-on:
- #214 (arg-bundle consolidation): the fourth stacking of
too_many_arguments/type_complexity across the Generated*/translate_*/
*_args_from families. Deliberately deferred until all four verbs
dissolved; now unblocked — the recommended next iteration.
Ephemera removed at close (per the spec/plan lifecycle): the mc spec +
plan, plus a stray cycle-0110 fieldtest spec
(docs/specs/fieldtest-sweep-dissolution.md, added 36fbf49) that outlived
its cycle and was missed by the intervening closes.
refs #210
The FOURTH and LAST verb dissolution. `aura mc --strategy r-sma --real`
dissolves into thin sugar over the one campaign executor — a generated
[std::sweep(argmax), std::walk_forward, std::monte_carlo] campaign
document whose terminal monte_carlo stage reproduces the current
`mc_r_bootstrap` grade byte-for-byte (the committed anchor 3fc491a gates
it). Pure sugar, no executor change; mirrors the walkforward dissolution.
The one new load-bearing decision is the seed mapping: the campaign
carries the mc `--seed` (the wf winners are argmax hence
deflation-seed-independent, proven by the shipped walkforward anchor).
Fork C retention as walkforward: the built-in arm splits, run_mc_r_bootstrap
/ run_mc stay inline for the fenced synthetic/non-real paths (until #159).
Spec grounding-check PASS, auto-signed on #210 (2026-07-06).
refs #210
Cycle 3 of the verb-dissolution milestone (96dc783..a047af6). Architect drift
review over the range returned clean.
What holds:
- Pure sugar confirmed: `git diff 3a03617..a047af6 -- crates/aura-campaign
crates/aura-engine crates/aura-research` is EMPTY. All walkforward-specific
logic is confined to aura-cli. Invariant 10 (no verb-special engine logic) and
invariant 12 (one campaign path, via run_campaign_returning) preserved.
- No new campaign vocabulary: reuses StageBlock::WalkForward / WfMode::Rolling /
RiskRegime::Vol — the #160 3-copy vocab guard needs no update. C18:
content-addressed process + campaign + run recorded, e2e-verified.
- C10/C20: the stop binds as a single RiskRegime::Vol (structural, not a swept
param axis), consistent with the prior risk-regime cycle; Fork A refuses a
multi-value stop rather than silently re-semanticizing it.
- The two documented inline deviations are sound: full_window == wf_full_span on
the Real arm (both delegate to probe_window); raw_matches_wrapped correctly
matches wrapped fast/slow and the unwrapped stop.
Deferred debt (all [low], tracked, carry-on):
- Fork A narrows the surface: the inline path swept the stop as an IS-refit grid
axis (RGrid.stop_* are Vec); the dissolved path refuses a multi-value stop. The
byte-anchor covers the single-stop grade — "byte-for-byte" is scoped, not total.
Design-ratified on #210 (Fork A / the risk-regime model: the stop defines R and
is compared, never argmax-swept).
- The reducer's .expect()/unreachable! on report shape mirrors the inline
reducer's posture; anchor-guarded for today.
- The #214 arg-bundle is now at its third instance (rule-of-three trip point);
deferral to after the mc dissolution is deliberate (noted on #214).
Full workspace suite green; clippy --all-targets -D warnings clean; the
equivalence anchor walkforward_real_e2e_pins_the_exact_current_grade green through
the dissolution. Spec + plan removed (git rm) per the cycle lifecycle.
refs #210
Third verb dissolution: route `aura walkforward --strategy r-sma --real`
through the one campaign path as thin sugar, reproducing the summary line
byte-for-byte. Key finding (verified): this is PURE SUGAR — no executor
change — because the campaign walk_forward stage's per-window OOS reports
carry everything the summary needs (stitched_total_pips == the per-window
total_pips summed in roll order; pooled oos_r from the reports' in-memory
trade_rs). The built-in arm SPLITS: only r-sma-real dissolves; the synthetic
and non-r-sma-real branches keep the inline run_walkforward (Reading A). The
--select plateau path is carved out to #215; the equivalence anchor 96dc783
is the acceptance gate.
refs #210
Second verb dissolution (#210) closed drift-clean. Architect: no ledger drift.
What holds (architect, verified against the diff + a live test run):
- Byte-parity proven, not assumed — the exact-grade anchor runs green through
the dissolved path; {"family_id":"generalize-0"} survives (the per-cell Sweep
families take a distinct campaign-prefixed name).
- C18 stamping preserved — the member runner maps cell.regime -> StopRule::Vol
and stamps manifest.instrument; the anchor confirms regime-seam R == former
grid-axis R.
- run_campaign_returning/present_campaign split is behaviour-preserving — the
run record is written inside execute, so the sugar path (bypassing the
presenter) still records it.
- Q4 is not drift — the +2 per-instrument Sweep families are the executor's
uniform, reproducible audit artifacts (sweep-dissolution precedent,
C18-consistent); stdout unchanged; the relaxed family pin is faithful.
Regression: cargo test --workspace green (every crate 0 failed);
clippy --workspace -D warnings clean.
Drift resolution:
- [medium] no-window generalize grades over symbols[0].full_window (one shared
window) vs the inline path's per-instrument windows. RATIFIED: a single shared
window is the campaign model's natural expression, the explicit-window path
(both e2e + the exact-grade anchor) is byte-identical, and symbols[0] is a
pragmatic pick; no value pin because a full-archive grade is fragile against
archive growth. Deferred design reconsideration filed as #213.
- [low] two #[allow(too_many_arguments)] in verb_sugar.rs — carry-on; the
arg-bundling refactor is best done once the remaining verbs dissolve (#214).
Spec + plan removed at cycle close (git-tracked in this project).
refs #210
Second verb dissolution: `aura generalize` becomes thin sugar over the one
campaign executor, byte-identical output, the stop carried by a single risk
regime. Spec grounding-check PASS (auto-signed) after the exact-grade anchor
(f3f32b8) closed the stop-mechanism R-parity block. Plan derives four
implementation forks (Q1 blueprint source, Q2 run-outcome bundle, Q3 window,
Q4 the campaign-path family set — user-visible), all recorded on #210.
refs #210
Architect drift review (c9d962f..HEAD). What holds: the nominee key is the
3-tuple (strategy, window, regime) and no argmax over regime_ordinal exists, so
the ledger's kept-separate / compared-not-selected semantics is what the code
does; the C18 manifest stamp is honest (the characterization pin flipped from
asserting absence to requiring the exact resolved 3/2.0, a strengthening, and a
real two-regime e2e catches per-cell mis-resolution); no dead code (cell.regime
and regime_ordinal are both read after the runtime-binding slice), absent/empty
risk keeps content-id parity, and CampaignGeneralization.regime_ordinal is
serde-default so pre-feature records still parse.
Resolution:
- FIX (inline, this commit): the spec promised a C10 AND a C20 note; only C10
landed. C20's enumerated structural-axis list (strategy/instrument/broker/
window) was left silently incomplete — the risk regime is added as the fourth
matrix axis, with a dated realization pointer to the C10 semantics.
- carry (documented descope): no std::risk descriptor in CAMPAIGN_SECTIONS —
risk is a top-level array, not a slot-bearing section; no invariant broken.
- carry (filed #212): the persist re-run + campaign_cell_key omit the regime
because CellRealization gained none; the architect verified this is a LOUD C1
drift-alarm refusal for a non-default regime + persist_taps, not silent wrong
data (#212 corrected accordingly).
- trivial: validate_campaign's regime-check comment corrected (it catches NaN,
not all non-finite; +inf is unreachable via JSON).
Regression gate: full workspace suite green, clippy clean (no dedicated
regression script; the suite + lint are the gate). Spec and plan removed
(git rm) at cycle close per the project convention. No baseline moved.
refs #210
The last slice of the risk-regime structural axis. The sugar parity
(`translate_sweep` emitting `risk: vec![]`, absent-serializing) and the
real-data two-regime e2e landed in the earlier slices (the loop's self-correction
and its e2e phase), so this closes the remaining pieces:
- design-ledger note: the risk regime realizes the StopRule structural axis at
the campaign-document level — kept-separate keying, compared-not-selected (the
R-unit argument), the C18 stamp, absent-parity, and the deferred trace gap
(#212).
- clippy: `validate_campaign`'s regime check reads `k <= 0.0 || k.is_nan()`
instead of `!(k > 0.0)` (neg_cmp_op_on_partial_ord), behaviour-identical.
Full workspace suite green; clippy clean.
refs #210
Spec auto-signed on a grounding-check PASS: the risk regime becomes a
structural campaign axis (a peer of instruments/windows, kept-separate in
the executor, each member's resolved stop stamped into its manifest;
regimes are compared, never argmax-selected across — a cross-regime E[R]
argmax would mix R units, C10). The 5-task plan threads it through
aura-research (RiskRegime + CampaignDoc.risk), aura-campaign + aura-registry
(matrix expansion + regime_ordinal), and aura-cli (StopArm + wrap_r + the
manifest stamp). Two bounded, documented descopes: the descriptive
CAMPAIGN_SECTIONS introspection entry and multi-regime trace-dir isolation.
refs #210
Authoring guide §1: the inline SMA-crossover op-script no longer binds
fast/slow lengths — it is byte-identical to the corpus file it claims
to match (content id 597d719b… verified against the binary), and the
previously unwritten rule is stated: an op-script bind pins a param
OUT of the sweepable space (closed — no campaign axis or --axis can
reopen it). New passage + example distinguishing the raw param-space
namespace (--params, campaign-document axes) from the wrapped
--list-axes/--axis surface; glossary sweep entry carries the same
one-sentence distinction.
refs #210
Consumer scenario against the public surface only: selection-free
process doc round-trip, the dissolved real-data sweep (doc dedupe +
realization accumulation + C1 bit-identity), refusal edges, rank-later
over the persisted family. 0 bugs; the cycle's own axes all came back
working. 4 friction + 2 spec-gap findings on the verb entry ergonomics
and pre-existing guide drift — transcribed in
docs/specs/fieldtest-sweep-dissolution.md for triage.
refs #210
Architect review (scope e7c7bde..b7aaa0b) found three items; resolutions:
- fix: docs/authoring-guide.md + glossary aligned with the shipped
vocabulary (std::sweep selection group optional/all-or-nothing,
selection-free = terminal-only, worked example verified against the
live binary).
- fix: the #203 wrapped/raw axis-name convention is now single-sourced
in campaign_run.rs (wrapped_to_raw_axis + raw_matches_wrapped, a
cross-documented inverse pair; dispatch_sweep and both bind sites
call through it; inverse-property unit test). Ratify note: this
unifies two previously different algorithms onto the documented
first-segment semantics — the old loose ends_with suffix-match also
accepted sub-segment shorthands (e.g. axis "length" against
"sma_signal.fast.length") that no stored document or test used;
such shorthands now refuse loudly (unbound/unknown axis) instead of
matching, the refuse-don't-guess reading of #203.
- carry: run_blueprint_sweep/blueprint_sweep_family remain generically
real-capable though the dispatch no longer routes real data to them;
the residual capability is shared DataSource machinery, its removal
falls out with the built-in/synthetic branch retirement (#159), and
the synthetic-only status is documented at the fn.
What holds: C24 canonical form (flatten group leaves every stored
content id unchanged, golden pin untouched), C18 lineage (topology_hash
IS content_id_of, single store write resolves the strategy ref;
selection-free arm still persists the full family), C25 closed-
vocabulary discipline (all-or-nothing group, Blockly-clean), C3 (ms/ns
conversion through the ingest seam's own named fn).
Ledger: #109 open-thread status lifted to cycles 0107-0110 reality
(executor shipped, amendment package landed, verb dissolution running
as milestone #210 with sweep dissolved).
Regression gates: cargo test --workspace 1056/0; clippy -D warnings
clean; cargo doc clean. Cycle spec+plan removed at close per
convention.
refs #210
The pure half of the sweep re-cut: translate_sweep maps a real-data
blueprint-sweep invocation (axes, name, symbol, window, canonical
blueprint bytes) to a selection-free single-stage process document plus
a campaign document carrying exactly the invocation's intent (seed 0 —
no stage consumes it — so identical invocations dedupe onto identical
content ids); register_generated puts both into the content-addressed
stores. Unit tests pin determinism, name flow, mixed-kind-axis refusal,
and that generated documents pass intrinsic validation + preflight.
Dead-code-allowed until the dispatch rewire wires the module (next
task removes the bridge attribute). Plan bytes reconciled with three
necessary deviations the spec gate surfaced: derive(Debug) for
unwrap_err, ScalarKind lives in aura_core, and 'gen' is reserved in
edition 2024.
refs #210
Cycle 1 of the verb-dissolution milestone (refs #210): the real-data
blueprint sweep re-cut as sugar over a generated, auto-registered
campaign document; optional selection group in the sweep stage
vocabulary; terminal-only preflight rule. Spec auto-signed on a
grounding-check PASS (decision log on #210); ephemeral per convention,
removed at cycle close.
Close two milestone-fieldtest doc-gaps (F6/F8) with one pass now that the
surfaces are stable. A newcomer could only learn the three headless JSON
artifact kinds from the fieldtest corpus: the op-script grammar was
undocumented (#208) and there was no worked process/campaign example nor a
pointer to the discoverable metric vocabulary (#197).
Add docs/authoring-guide.md — a worked, verified example per artifact kind
(op-script -> graph build; process document -> process validate/register;
campaign document -> campaign validate/register/run), every command run
against the binary and its output transcribed. Documents all six ops
(source/input/add/feed/connect/expose) with their JSON shapes, and teaches
the metric roster split (rankable / gate / | generalize) pointing at
'aura process introspect --metrics' as the source of truth rather than
hand-copying the rosters. A short paragraph in project-layout.md links it.
Docs only; no code or CLI change (the surfaces already suffice). Grammar
grounded on construction.rs; examples faithful to the milestone corpus.
closes#197closes#208
The research-artifacts milestone fieldtest closed GREEN and the milestone
is formally closed; per the ephemeral-artifact convention its spec is
git-rm'd at cycle close. The verdict survives durably in the tracked
corpus (fieldtests/milestone-research-artifacts/FINDINGS.md), the closed
milestone, and the ledger.
MILESTONE VERDICT: GREEN — the whole span (0106-0109) holds end to
end as one continuous consumer scenario: authored from a bare {} via
introspection alone, every ref resolved from the public surface, three
validation tiers, run by content id over two real instruments through
the full v2 pipeline, realization recorded (selection/survivors/
bootstrap/generalizations/trace_name), traces on disk and charted,
read back via campaign runs, byte-identical re-runs (C1), refusals
precise. 0 bugs, 0 frictions, 0 spec gaps; 2 doc-gaps.
F7 fixed in this commit (the docs claimed an archive-root path without
naming the key; a guessed [paths] archive silently no-ops): project-
layout and the glossary Aura.toml entry now name [paths] data, and the
aura new template advertises the commented-out key. F8 (op-script
grammar not CLI-discoverable) filed as #208, sibling of the #197 docs
half — one docwriter pass once desired.
The milestone-close gate evidence is this corpus; the formal milestone
close and the push remain user-reserved.
refs #189
Architect verdict: drift_found — the code holds (C1 honored not
assumed: the nominee re-run's metrics-equality hard refusal; C22/C14
clean: existing TraceStore + unchanged viewer, serde-default widening
round-trips, name composition single-sourced in derive_trace_name).
Resolved here:
- C18: the 0107 paragraph's 'persist_taps is deferred' points forward;
new cycle-0109 realization paragraph records the closed tap
vocabulary + UnknownTap tier, the nominee-only non-reduce re-run
with the C1 metrics guard, the campaign trace family layout, the
trace_name claim contract, the loud-skip lines, and the noted
chart-over-family-root debt.
- Glossary: tap entry names the closed vocabulary + escalation rule;
campaign document's presentation clause references it; campaign run
gains the trace_name pointer.
- Debt fixed inline (architect med): tap_channel gains the
emit_vocabulary-twin debug_assert cross-pin so a fifth vocabulary
tap fails loudly instead of silently skipping.
The consumed 0108 fieldtest spec is removed with the cycle's spec+plan
(all its dispositions shipped: F6 #205, F8 #207, F11 #206, F7/F9/F10
doc-tightens).
Regression: cargo test --workspace 1041/0; clippy -D warnings clean;
cargo doc 0 warnings.
refs #201
4 tasks, strictly sequential: tap vocabulary + UnknownTap intrinsic
validation (deferral eprintln survives until task 3; the 0107 deferral
test splits into its two 0109 pins), trace_name widening + the
claim-sentinel name-composition contract across registry and executor,
persist_campaign_traces (nominee non-reduce re-run, metrics-equality
C1 guard, TraceStore member-dir writes, loud skips, deferral line
dies), gated e2e extension (trace files + chart read-back).
Drafted per-task against the live tree (3 authors); cross-task seams
verified in the notes: campaign_run.rs untouched by tasks 1-2 (task
3's fences stay valid), the task-1(b) test found by fixture not name,
tap->channel mapping verified against persist_traces_r, nominee params
bound from the report manifest via the shipped point_from_params
inverse, reduce/non-reduce metrics equality grounded in the shared
SeriesFold/GatedRecorder ledger construction.
refs #201
Cycle 0109, anchored on #201. Encodes the five swarm-triaged decisions
(#201 comment 2026-07-04; F1-F4 unanimous, F5 4/5 with dissent
recorded): closed tap vocabulary of the wrap convention's four sink
names (escalation = new vocabulary entry or authored blueprint sink,
never an open node-path namespace); nominee-only non-reduce re-run per
cell (bounded, C1/reproduce precedent, equality-asserted); the
existing TraceStore family-shaped under {campaign8}-{run}; wiring
consumer-side after execute() returns (MemberRunner stays one-method,
aura-campaign stays trace-agnostic bar a one-line name stamp);
CampaignRunRecord.trace_name as the one sparse pointer (the 0108-F10
navigability lesson). Seam refinement recorded: the run counter is
assigned in append_campaign_run, so the store write composes the name
from a claim sentinel — contract pinned, exact seam is the planner's.
Boss-signed via grounding-check PASS (11/11). Planner note carried
from the check: the re-run equality assert pins METRICS equality (the
C1 core) — manifest fields are fresh-context and not reconstructed
cross-mode.
refs #201
The std::monte_carlo block doc now names the position-dependent
semantics (pooled OOS after wf / per-survivor otherwise) and the > 0
execution guard the generic u32 slot hint could not carry; the
std::generalize block doc names campaign scope, the >= 2-instrument
need, and the R-expectancy metric family. Glossary: new 'stage
bootstrap' entry defines the realization payload incl. prob_le_zero;
the campaign-run entry gains the generalizations schema and the
stdout-wrapper-vs-bare-store-line note. Introspection text and
glossary only — no document content id moves.
Gates: workspace green, clippy clean.
refs #200
Verdict: honest, recorded, reproducible inference on top of the 0107
loop — pooled_oos provably pools the wf OOS windows (n_trades 948+895
= 1843), per_survivor flags a razor-thin gate-passer at
prob_le_zero 0.525 (the inference layer earning its keep), the
two-instrument std::generalize records worst_case/sign_agreement over
last-wf-window nominees, byte-identical across three runs modulo the
run counter, and all eight boundary probes refuse loudly at the right
tier. 0 bugs.
Triage: F1-F5 carry-on; F6 (campaign validate blesses
executor-unrunnable shapes — the third tier invisible) and F11 (no
CLI read-back for recorded realizations) filed as issues; F7/F9/F10
doc-tightens follow this commit inline; F8 (generalize R-metric set
undiscoverable + misleading refusal prose for R-denominated-but-
unranked metrics) filed with the --metrics tag half. The fieldtest
spec rides in docs/specs/ as next-cycle planner input per convention.
refs #200
Architect verdict: drift_found — the expected pre-audit doc lag; the
code holds (C1: doc-seeded bootstrap + BTreeMap-ordered generalize;
C14/C23 sparse widening pinned by the pre-0108-line parse test;
terminal-annotator dataflow confirmed — nothing flows out, no new
emit kind, no content-id movement). All items resolved here:
- C18: 0107's 'refuse loudly at preflight' points forward; new
cycle-0108 realization paragraph records the v2 shape, the
dual-input stage bootstrap, campaign-scope generalize, the tier
boundary (test-pinned on both sides), the record widenings, and
the stringly wf-detection debt.
- Glossary: campaign document -> v2 shape; bootstrap and Monte-Carlo
entries disambiguate the three senses (construction vs statistical
r_bootstrap vs seed axis — the std::monte_carlo stage IS the
trade-sequence bootstrap, named for r_bootstrap's arguments);
generalize gains the campaign-scope realization.
Regression: cargo test --workspace 1025/0; clippy -D warnings clean;
cargo doc 0 warnings. Spec + plan removed at close per convention.
closes#200
5 tasks, strictly sequential: record widenings + serde derives
(workspace-green), preflight v2 + fault-set swap (leaves ONE known-RED
aura-cli integration test, documented loudly, flipped by task 5;
interim gates exclude the aura-cli integration targets), the mc stage
arm (dual-input bootstrap), the campaign-scope generalize phase
(nominee threading), CLI seam flips + doc tidy + gated e2e extension
restoring full workspace green.
Drafted per-task against the live tree (4 authors), assembled with two
reconciliations: the task-2 typo-trap fence replaced by its
authoritative form (plans carry only literally-applicable bytes), and
task 4's old-quote aligned to task 1's record-literal bytes (comment
lines included). Cross-task byte seams verified: task 3 quotes the
pre-task-2 unreachable-arm (task 2 does not touch exec.rs); task 5
pins the prose task 2 defines (substrings verified compatible).
refs #200
Cycle 0108, anchored on #200. Encodes the five swarm-triaged decisions
(#200 comment 2026-07-03, all convergent on cited ground, no bounce):
std::monte_carlo bootstraps the stage's incoming R-evidence (per-survivor
after sweep/gates, pooled per-window OOS series after walk_forward) via
the shipped r_bootstrap; std::generalize runs at campaign scope over
per-cell nominees per (strategy, window); both stay terminal annotators
(unanimous); realization widens existing records (StageRealization.bootstrap,
CampaignRunRecord.generalizations, serde-default); v2 executable shape
sweep [gate]* [wf]? [mc]? [generalize]? with static preflight guards.
No document-schema bytes move — every existing content id survives.
Boss-signed via grounding-check PASS (11/11). The first dispatch
BLOCKed on one unpinned current-behaviour assumption ([sweep, mc,
walk_forward] passes the intrinsic tier); the gap was closed by the
green characterization test
validate_process_permits_walk_forward_after_an_annotator (pins the
intrinsic/executor tier boundary), and the fresh re-dispatch ratified
all eleven assumptions.
refs #200
Architect verdict: drift_found — the code holds its contracts (C1
determinism incl. lowest-index fault attribution and doc-seeded
deflation; C16 seam: aura-campaign excludes ingest/std/composites,
MemberRunner isolates the condemned CLI scaffolding; the walk_forward
lockstep set moved together), the docs lagged the tree. All six drift
items resolved in this commit:
- C18: 'no executor exists' retired (0106 text now points forward);
new cycle-0107 realization records the executor, the aura-campaign
home, ListSpace, the campaign_runs.jsonl sibling store, zero-survivor
exit-0 semantics, emit/persist_taps split, the #196 on-ramp, and the
machinery-true std::walk_forward correction.
- C16: aura-campaign added to the non-node crate enumeration
(cycle-0107 realization; explicitly not C21's World).
- Glossary: campaign document entry corrected (run verb, execution
prose); new 'campaign run' entry; blueprint entry gains the on-ramp
verbs.
Carry-on debt (self-noted in code, tracked): metric-roster
triplication #190, deflation-constant duplication #199; cross-cell
fault orphans + nested-parallelism oversubscription noted in the
tasks-6-7 commit body. Follow-ups filed on the milestone: #200
(mc/generalize stage execution), #201 (persist_taps wiring).
Regression: cargo test --workspace 987/0; clippy -D warnings clean;
cargo doc 0 warnings. Spec + plan removed at close per convention
(durable rationale lives in the ledger; the canonical record is the
git history).
closes#198
Cycle 0107, anchored on #198 (campaign executor; #196 blueprint on-ramp
rides along). Encodes the twelve decisions recorded on #198: eleven from
the fork triage (2026-07-03) plus the user-decided executor home (a new
library crate, 2026-07-03). Scope: aura-campaign library crate
(MemberRunner seam, execute, gate evaluation, preflight, realization
assembly), std::walk_forward vocabulary correction to machinery-true
fields, engine ListSpace, registry CampaignRunRecord + campaign_runs
store, CLI campaign-run verb + driver, #196 on-ramp verbs.
Boss-signed via grounding-check PASS (17/17 load-bearing assumptions
ratified against currently-green tests). One construction note carried
to the plan: a private Registry::blueprint_path already exists and is
promoted to public rather than duplicated.
refs #198, refs #196
C25 (new): the nine authoring roles cut by artifact + surface + iteration
cost, the recognizability test, the 6a/6b split on invariant 12's tier
boundary with the id machinery as interface, the text-first/headless-first
invariant (visual surfaces = stateless projections, viewers over editors),
and the Blockly litmus test as every vocabulary's acceptance criterion.
C20: the 'plain Rust loops, not a config schema' clause and the mini-DSL
forbid are scoped — they forbid an open logic-bearing language, not the
closed-vocabulary campaign document that now carries experiment intent
under the P1 construct tier; generators may stay Rust, what they yield is
data.
C22: stateless-projection refinement generalized to all artifact classes;
the shipped face recorded as the web-from-disk front. Glossary playground
entry aligned (the egui-native wording was stale against the 2026-06
revision).
CLAUDE.md invariant 10: clarified that closed-vocabulary data artifacts
(op-scripts, blueprints, process/campaign documents) are not the forbidden
DSL — RustAst failed as an open logic-bearing language; new logic
escalates to a Rust block, never a freetext hole.
All content ratified on #188 (body + addenda + resolution comments); this
commit is production of the durable record, no new design.
closes#192
Architect drift review (holds: C14 headless authoring, C16/C17 no-DSL with
aura-research a true leaf, content-id move behaviour-preserving per the
untouched id goldens). Resolution per item:
- fix (docs): C18 gains the cycle-0106 realization note (processes/ +
campaigns/ stores, document canonical form, the content-id primitive's
library home, the referential tier, no-executor status); the #109
analysis-meta-level open thread records the artifact half shipped v1 and
what stays open (executor question, verb dissolution 'once it carries',
the remaining #188 amendment package). Glossary: new campaign document +
process document entries; content id generalized to all three artifact
classes; experiment marked superseded by the campaign document (#188
re-cut of the builder-API thread).
- fix (code): the --unwired guide advertised an identity_id process ref
that validate_campaign refuses — the process.ref open-slot hint now says
content-id-only (strategy refs keep both); lib + seam pins updated.
- filed forward: #190 (metric-vocabulary single-sourcing, the 0105 roster
drift class), #191 (identity-ref store scan is O(store), performance
only).
- carry-on: regression gates green by hand — cargo test --workspace 916/0,
clippy -D warnings clean, cargo doc --no-deps 0 warnings; no baseline to
ratify (project has no metric baseline scripts).
Cycle 0106 spec and plan retired per convention (git rm); durable record
is the ledger notes above plus #188/#189.
refs #189
New research_docs.rs module: role-addressed process verbs with house-style
fault prose (Display-free enums phrased at the seam), the introspect
exactly-one-of usage guard (exit 2), and content-addressed registration.
Seven binary seam tests pin intrinsic-ok/refusal prose, vocabulary/block/
unwired/content-id introspection, exit codes, and the stored file's
location under the runs root.
Quality-gate finding folded in (and back into the plan): register no
longer re-derives the store path from runs_root — aura-registry now
exposes process_path/campaign_path, the same single mapping its put/get
pair routes through, so the printed path cannot drift from the store
layout.
Verification: research_docs seam tests 7/0, registry 49/0, clippy clean.
refs #189
The aura-research leaf crate: ProcessDoc/CampaignDoc with strict parsing
(hand-rolled StageBlock deserializer — deny_unknown_fields does not compose
with internally-tagged enums; Axis declares its ScalarKind once with bare
values, per the #189 user veto), canonical form + content_id_of (the
SHA-256 primitive moved from aura-cli, which now delegates — the id pin set
incl. the independent sweep-store recompute stayed green untouched),
intrinsic validation for both document types (P1 constraints structural),
and the introspection contract (schema tables single-source parse
strictness AND vocabulary/describe/open-slots — the Blockly litmus made
checkable). aura-registry: content-addressed processes/ + campaigns/
stores on the blueprint-store pattern (Ok(None) treat-as-empty) and the
referential tier (validate_campaign_refs: process/strategy refs incl.
identity-scan, axis-name + declared-kind checks against param_space).
Plan deviations, verified by hand and folded back into the plan file:
- Task 9's fixture could not use aura-composites as planned: every shipped
composite with an open param routes through LinComb, which the zero-arg
std_vocabulary roster deliberately excludes, so none round-trips through
blueprint_from_json with the by-type-name resolver. The test hand-builds
a minimal Bias composite instead (generic over param_space, as planned);
the unused pro-forma aura-composites dev-dep from the repair pass is
dropped. This is why the loop reported task 9 BLOCKED
(review-loop-exhausted on the literal code block); the tree itself is
complete and green.
- A plan-verbatim test assertion false-matched ("deflate" as substring of
"deflated-positive"); tightened to the JSON key.
- OpenSlot doc comment backticked (rustdoc read strategies[0] as a link;
doc gate back to 0 warnings).
Verification: cargo test --workspace 898/0; clippy -D warnings clean;
cargo doc --no-deps 0 warnings. Tasks 10-12 (CLI verb families, final
gates) follow.
refs #189
User veto (2026-07-03) of the per-cell tagged Scalar draft: the kind is a
property of the parameter, not of each value. An axis is now
{"kind": "I64", "values": [8, 12, 16]} — mixed-kind axes are
unrepresentable, canonical form normalizes value spelling, and the
referential kind check is one comparison per axis. Op-script binds keep
their tagged form (single-value slots). Decision log: #189.
refs #189
The campaign example wrote bare JSON numbers in the axes while the spec's
own typed-cell clause (op-script bind parity) requires the tagged Scalar
wire form. Example now matches the clause; no assumption changed.
refs #189
Two doc-tightenings from the green milestone fieldtest (F3, F6 in
fieldtests/milestone-project-environment/FINDINGS.md): the glossary
manifest entry now names the topology hash and the project provenance
block {namespace, dylib_sha256, commit} a project-hosted run carries;
project-layout.md's Aura.toml annotation now matches what the scaffold
actually emits today ([paths] runs only — the data archive root joins
once real data enters).
refs #180
Resolves the #181 design pass (option c: ledger declaration, no lockstep
mechanism). The aura-new templates (scaffold.rs) are the canonical
authoring shape and evolve with the engine; the cycle-0102 demo-project
fixture is an intentionally frozen known-good twin for the load-boundary
tests. Deliberately NOT lockstep-guarded: no consumer requires the copies
to match (skeptic-verified — nothing treats the fixture as what aura new
emits), each is e2e-guarded on its fitness for purpose (build/load/
charter/deterministic run; blueprint wiring is pinned in neither, stated
honestly after an adversarial skeptic pass refuted the stronger claim),
and an equality guard would convert deliberate template improvements into
forced churn of the frozen fixture — the same cross-purpose coupling that
rules out regenerating the fixture from the scaffolder.
closes#181, refs #180
Architect drift review (range 7b429f9..57f401f): drift_found (low/medium
only), resolved inline as close-fixes:
- crates/aura-std/src/vocabulary.rs — the roster-site doc now names BOTH
count pins a node addition trips (the in-crate shape test and aura-cli's
cross-boundary --vocabulary count e2e); the singular phrasing understated
the cross-crate lockstep the extra e2e introduced.
- docs/design/INDEX.md — the C24 enforcement-shift passage gains the 0105
delivery note: resolver-vs-list drift closed by construction via the
roster macro; the un-rostered-node residual stays fail-safe.
Noted, no action: spec/plan predicted 884 (no new test) but delivery added
one e2e (885) — consciously superseded, disclosed in the iter commit body;
the artifacts are ephemeral and removed below.
What holds (architect): byte-preserving refactor confirmed against the
diff (22 keys/order exact, signatures and module doc untouched, every
consumer unchanged); invariant 9 / C24 preserved (compile-time expansion,
no registry); the new e2e count pin is genuinely roster-tied.
Regression gates (all green): cargo build clean; cargo test --workspace
885 passed / 0 failed (884 baseline + 1 new e2e); clippy --all-targets
-D warnings clean; cargo doc --no-deps 0 warnings.
Ephemeral cycle artifacts removed per project convention (git rm):
docs/specs/0105-std-vocabulary-roster-macro.md,
docs/plans/0105-std-vocabulary-roster-macro.md.
refs #180
Brummel