One public knob fanning into >=2 sibling params: Gang/GangMember types
(the Role name/targets split + BoundParam pos/name dual), Composite.gangs
behind the single fallible Composite::with_gangs gate, check_gangs as the
shared $A predicate (all three future minting boundaries route here), and
CompileError::BadGang(GangFault) as the typed refusal.
PrimitiveBuilder::original_pos (aura-core) extracts bind's pos-reconstruction
loop verbatim so gang members and BoundParam share one coordinate space.
Deviation ratified vs the plan: GangFault::KindMismatch carries structural
{node, name} coordinates instead of a stringly member label, consistent with
the sibling arms (plan amended). A redundant test-local fixture wrapper was
dropped after a fresh quality re-review of the blocked task diff.
Verified: cargo test -p aura-engine --lib 249/0, -p aura-core 53/0, clippy
-D warnings clean on both crates.
refs #61
The #28 cycle-close audit found aura graph <file> silently rendered the embedded
sample at exit 0 when the positional named an unreadable blueprint (typo,
nonexistent path, wrong extension): is_blueprint_file returns None both for "no
positional" and for a bad arg, and dispatch_graph's None arm conflated them —
re-introducing the exact #28 "I asked for my graph, got the sample" surprise in
the error path, and diverging from every sibling verb (a bad blueprint arg is a
usage fault, exit 2, per C14). Split the None arm: no positional -> the sample
(unchanged); a positional that is not a readable .json -> a usage error naming
the arg, exit 2, mirroring dispatch_run.
Also close the paired doc drift the audit flagged: the README blueprint-verb
table and the authoring guide now document the aura graph <file> render surface,
absent while graph was the last sample-bound verb.
refs #28
The #28 cycle-close audit found the just-shipped `aura graph <file>` silently
renders the embedded sample at exit 0 when the positional names an unreadable
blueprint (typo, nonexistent path, wrong extension): is_blueprint_file returns
None both for "no positional" (the legit sample default) and for a bad arg, and
dispatch_graph's None arm conflates them — re-introducing the exact #28 "I asked
for my graph, got the sample" surprise in the error path. This pins the fix: a
named-but-unreadable arg exits 2 like its siblings, while bare `aura graph` still
renders the sample.
refs #28
aura graph was the last verb still sample-bound: its no-subcommand arm always
rendered the embedded r_sma_open.json, so a downstream researcher who authored
their own blueprint could introspect it as data but not RENDER it to see
mis-wiring before a run — the Construction-layer milestone payoff only half
realized. Give GraphCmd a first-positional blueprint (args_conflicts_with_subcommands
so it coexists with build/introspect/register), and branch the no-subcommand arm
on is_blueprint_file, mirroring dispatch_run: read the file, reload it via
blueprint_from_json against the project/std vocabulary, and render_html it; the
no-argument form still renders the embedded sample.
The library-packaging half (a downstream-linkable render crate) is dropped — the
ratified consumer surface is CLI-over-blueprint-data (decision on #28). The
nested-composite render is not a concern: the old graph.rs ascii render that
carried the unimplemented! was retired, render_html serializes via model_to_json
with no panic, and #26 is already closed.
closes#28
aura graph is the last verb still sample-bound: its no-subcommand arm always
renders the embedded r_sma_open.json, ignoring any blueprint path, while
run/sweep/mc/walkforward/generalize consume a consumer blueprint file via
is_blueprint_file. This pins the target: aura graph <blueprint.json> renders
that file's own graph (its inlined model reflects the file's nodes, e.g.
r-breakout's channel_hi), not the embedded sample.
refs #28
The campaign walk_forward stage picked its per-window in-sample winner by
optimize_deflated (argmax) unconditionally, dropping the stage's `select`
field, and both the preflight and the `walkforward` verb's `--real` campaign
sub-branch refused plateau:* with a forward-pointer here (the #210 decision-4
deferral; the synthetic non-`--real` sub-branch has accepted plateau since
#173). Honour plateau selection when no gate precedes the wf stage.
- Preflight: the plateau-in-wf refusal is narrowed to gate-preceded stages.
With no preceding gate the survivors are the full sweep grid, so the
parameter lattice (grid.axis_lens) is exact and optimize_plateau is sound; a
gate filters survivors below the grid, breaking the lattice, so plateau after
any gate stays refused. The refusal is static — document validity must be
data-independent (a gate's filtering depends on the data) — and keeps the
existing "a gated survivor subset has no parameter lattice" message, which now
describes exactly the only case it fires.
- Executor: run_walk_forward_stage threads the per-cell grid.axis_lens and picks
each window's in-sample winner via select_sweep_winner — the same dispatch the
sweep stage uses. (Argmax, deflate=true) is byte-identical to the old
optimize_deflated call, so the argmax grade and content-id pins are unchanged;
the plateau arms read axis_lens and ignore deflate.
- CLI: the walkforward verb threads --select through translate_walkforward /
run_walkforward_sugar (a walkforward-local param, not the shared four-verb
SugarInvocation), mapping the parsed Selection to the research SelectRule via
select_rule_of; the refusal and its select_is_plateau helper are deleted.
Scope is walkforward-only — the mc verb's wf-stage select is untouched.
The plateau:worst grade anchor (stitched_total_pips = -9683776.67) is distinct
from the argmax anchor (-10398606.67), proving the plateau path genuinely
changes winner selection rather than falling back to argmax. A gate-free plateau
process validates clean while a gate-preceded one is refused (a new
campaign-validate e2e). Argmax defaults stay byte-identical.
closes#215
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
metric_vocabulary() hand-lists 17 scalar metric names; a field added or
renamed on RMetrics/RunMetrics/FamilySelection (aura-analysis) silently
desynced the gate/stage checks — a new scalar stayed un-gateable until every
roster was hand-updated (the 3-copy drift class #160 closed for node type ids).
Pin the vocabulary against the types' real serde output instead of a second
hand-copy: enumerate the scalar (JSON-Number) fields of real instances of the
three metric-bearing types and assert set-equality with metric_vocabulary().
A new un-gated scalar (present in the type, absent from the vocabulary) or a
stale vocabulary entry (present in the vocabulary, gone from every type) now
goes red. RMetrics comes from the real producer summarize_r; RunMetrics and
FamilySelection from exhaustive struct literals, so a new field also breaks
the test's compilation until it is consciously classified. Selection
provenance numbers (n_trials, raw_winner_metric) and the Optional annotation
identifiers are excluded with rationale — the types mix scalar metrics with
scalar provenance and carry no type-level marker between them, so that one
distinction stays explicit.
Green on arrival (the rosters agree today); the roster-macro maximal shape
that would remove the hand-list entirely waits on #147 (where the metric
vocabulary's home is decided). Guard test only, no production change.
closes#190
The `aura new` scaffold shipped one node, a param-less Identity, so a
downstream author had no public example of a build closure consuming a
bound param — the highest-value gap the project-environment fieldtest found
(F2): a newcomer could copy a param-less node but had to read engine source
to write their first *tunable* one, which the consumer contract forbids.
Swap that single starter node for a Scale node (mirroring the std gain
operator): its schema declares a `factor` ParamSpec and its build closure
reads the bound value (`|p| Box::new(Scale::new(p[0].f64()))`), and the
starter blueprint binds `factor` so `aura run` exercises the bound-param
path with zero hand-editing.
factor is bound to 1.0 — a neutral identity default the newcomer then tunes,
not the only C7-safe value (only |factor|>1 would push the terminal `bias`
output past the bounded [-1,+1] contract; the knob is genuinely read and
multiplied each cycle). The param-reading closure is the copyable template
content #183 delivers; a hypothetical `|_|` regression is caught by the
scaffold unit test's source guard, and tests/project_new.rs re-validates the
swap by building and running the scaffold end to end.
Template-side only (#181): the frozen 0102 demo-project fixture is untouched.
closes#183
The `aura new` scaffold ships one node, a param-less Identity, so there is
no public example of a build closure consuming a bound param — the F2 gap
the project-environment fieldtest rated its highest-value authoring miss.
This pins the target: the rendered starter lib.rs declares a ParamSpec and
reads p[0] in its build closure, and the starter blueprint binds `factor`
on the project's own node, so `aura run` exercises the bound-param path
with zero hand-editing.
refs #183
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
The clap help promised "persists each member's/OOS window's taps" and the chart
NotFound hint recommended `aura sweep --trace`, but every blueprint-mode arm
discarded the flag (run_blueprint_sweep's `let _ = persist`, the --real sugar's
persist_taps: vec![]) — the surface advertised trace-recording the code dropped.
Refuse --trace up front on both verbs (exit 2, "--trace is not yet available on
<verb>; see #224"), mirroring the existing aura run / aura mc refusals; drop the
false promise from the two help lines and the chart NotFound hint. Delivering
per-member trace-writing is deferred to #224.
Collateral: four synthetic-sweep tests that used --trace as a family-name handle
move to --name (same handle, still accepted); the walkforward name/trace test now
pins the up-front #224 refusal.
Workspace suite green (62 groups / 0 failed), clippy -D warnings clean.
refs #168
The clap help promises "persists each member's taps" and the chart hint
recommends `aura sweep --trace`, but every blueprint-mode arm discards the flag
(run_blueprint_sweep's `let _ = persist`, the --real sugar's persist_taps: vec![])
— the surface advertises trace-recording the code drops. Pin the decided honest
behaviour: sweep/walkforward refuse --trace up front (exit 2, naming the flag and
pointing forward to the deferred trace feature #224), mirroring the aura run / mc
refusals.
refs #168
A dissolved verb (sweep/generalize/walkforward/mc --real) run outside a project
silently created a content-addressed runs/ store in the cwd and ran to
completion — Env::runs_root falls back to a relative ./runs with no project, and
the four dispatchers skipped the provenance gate that `campaign run` applies
first (campaign_run.rs:322-333). It is now refused up front: one gate in the
shared validate_and_register_axes chokepoint, after axis validation and before
the first store touch (put_blueprint), via a new AxisRegisterError::NoProject
mapped to exit 1 carrying "<verb> needs a project …".
Placement is load-bearing: axis validation (an UnknownAxis usage error, exit 2)
stays ahead of the project gate, so a malformed --axis still exits 2 regardless
of project — a malformed command is malformed in any environment and already
writes no store. Four per-verb pins assert the refusal (exit 1, "needs a
project", no store); the six exit-2 usage-refusal tests stay green.
Workspace suite green (62 groups / 0 failed), clippy -D warnings clean.
closes#218
The four dissolved verbs (sweep/generalize/walkforward/mc --real) are about to
gain a project gate that refuses outside a project (#218). 25 cli_run.rs tests
today run a well-formed verb to completion in a bare cwd and pin its grade /
store effect — i.e. they pin the pre-gate behaviour. Relocate them into the
built project fixture (fresh_project() over the demo-project cdylib, serialized,
store reset per test) so they still exercise the verb path once the gate lands.
Grades are byte-identical in-project (the fixture Aura.toml overrides no
instrument or data path — DEFAULT_DATA_PATH is absolute), verified against the
exact pins; local run 113 passed / 0 failed / 0 skipped with archive data.
Two new tests pin that the in-project run stamps manifest.project provenance
(the sweep chokepoint and generalize's run_blueprint_member path), a path no
cli_run.rs test previously exercised. The built_project/project_lock helpers are
duplicated into this binary to keep the change inside cli_run.rs; a shared
tests/common extraction is a separate hygiene item.
refs #218
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).
The structural risk-regime axis worked end to end but was invisible on the
public surface (refs #216): the --unwired probe swept only required slots
(risk is #[serde(default)]), no vocabulary block described RiskRegime, and
the validate summary counted axes/windows but no regimes or cells.
- open_slots_campaign gains its one optional-slot probe: a risk-less (or
empty/non-array) document lists
'open slot: risk (optional, list of stop regimes { vol: { length, k } };
absent = one default regime)'; a bound list closes the slot. Never a
required flip — content-id parity of risk-less documents is load-bearing.
- CAMPAIGN_SECTIONS gains std::risk (SlotKind::Regimes, required: false) so
--vocabulary lists it and --block std::risk describes the regime shape.
- The intrinsic validate summary now reports the realized matrix, mirroring
the exec cross-product exactly (strategies x instruments x windows x
regimes; empty risk = one default cell, marked '(default)'). Points stay
a grid property, deliberately not a cell factor.
Sanctioned migrations (recorded on #216): the two unit pins encoding the old
invisibility — open_slots_report_partial_documents_by_path now pins exactly
one open slot on the complete risk-less fixture (doubling as the probe's
unit pin; fixture bytes unchanged), and the presentation-hint test migrates
from full-vector equality to locating its entry (its purpose is the hint
text, not the vector length).
Verified: cargo test -p aura-research (29/0), -p aura-cli --test
research_docs (60/0), clippy -D warnings clean.
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
GREEN side of the #217 executable-spec: --stop-length/--stop-k are now
optional on the three dissolved verbs; each missing flag independently
defaults to the single-sourced regime constants (length 3, k 2.0) at
the argv-boundary extractors — the same regime the campaign member
runner resolves for an unbound regime. The generated campaign document
still binds the regime explicitly, so the default spelling is
content-identical to an explicit --stop-length 3 --stop-k 2.0 (pinned
by registry dedup in the headline test). The multi-value stop refusal
survives byte-identically; sweep is untouched.
Sanctioned contract migrations (decision on the issue, 2026-07-09):
walkforward_dissolved_refuses_missing_knobs now pins the surviving
multi-value refusal; mc_args_from_refuses_missing_knobs pins the
default path. Usage strings name the defaults.
Held quality nit (deferred to cycle close, minimal-slice constraint):
the None=>default / Some=>parse stop block recurs 4x across the
walkforward/mc extractors.
closes#217
walkforward_stopless_defaults_the_regime_byte_identically_to_explicit_3_2
pins the decided contract (#217 decision comment, 2026-07-09): a
walkforward invocation without --stop-length/--stop-k succeeds, each
omitted knob defaulting to the single-sourced regime (length 3, k 2.0),
and produces a campaign document content-identical to the explicit
--stop-length 3 --stop-k 2.0 spelling (registry dedup: exactly one doc).
Currently RED: the verb refuses with the requires-knobs usage error.
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
Task 5 of the verb-axis-generalization plan — the cycle's point, pinned:
- walkforward_campaign_runs_an_arbitrary_blueprint and
mc_campaign_runs_an_arbitrary_blueprint drive r_breakout_open.json
(wrapped channel_hi/channel_lo axes) over the real archive;
generalize_campaign_runs_an_arbitrary_blueprint grades
r_meanrev_open.json across two instruments. All three invocations
were structurally impossible before this cycle (exit 2).
- New refusals: campaign mode without --axis (wf/mc), mc --real +
--seeds mix, raw-form axis name before data access, unknown axis as
a named Knob fault — each mirroring sweep's shipped contract.
- Final acceptance gates ran green in the loop: full workspace suite,
clippy -D warnings, cargo doc warning-free, zero too_many_arguments
allows in verb_sugar.rs, no RGrid in the workspace, no r_sma_open
embed at the three verb dispatch sites (the aura graph default embed
survives by design).
closes#220closes#214
Tasks 3-4 of the verb-axis-generalization plan:
- walkforward: the welded r-sma campaign branch moves out of the None
arm into the blueprint mode, split on --real (campaign sugar) vs the
unchanged synthetic family path; WalkforwardCmd drops
--strategy/--fast/--slow; the full-window clip block, wf_ms_sizes and
WINNER_SELECTION_METRIC move unchanged; the --select plateau #215
refusal survives. walkforward_summary_json_from_reports is de-welded:
the axis-name list is passed in from the invocation instead of the
const AXES r-sma quadruple.
- mc: McCmd drops the welded flags and gains --axis; the blueprint arm
splits on --real (campaign pipeline: requires --axis, refuses
--seeds) vs the unchanged synthetic seed family (--seeds); block-len/
resamples/seed defaults and the --name/--trace refusal stay
byte-identical.
- translate_walkforward/run_walkforward_sugar and translate_mc/
run_mc_sugar adopt SugarInvocation (+ WfWindows/McKnobs); ZERO
#[allow(clippy::too_many_arguments)] remain in verb_sugar.rs (#214
complete).
- Tests: wf/mc e2e groups migrate argv-only (grade anchors keep all
pinned floats verbatim); collateral usage/retired-token tests assert
clap's structural rejection of the deleted flags; the synthetic
family control groups pass unmodified.
Necessary deviation from the plan's literal step text: re-added
#[allow(clippy::type_complexity)] on walkforward_args_from (clippy -D
warnings flags the 6-tuple; mirrors its siblings). Held quality nits
(validate/strip block now quadruplicated across the four dispatch fns;
inline exit-mapping recurrence) are deliberate plan-holds — dedup
follows as the rule-of-three cleanup at cycle end.
Verification: full workspace suite green in the loop's independent
verify; build + clippy -D warnings clean.
refs #220, refs #214
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.
Tasks 1-2 of the verb-axis-generalization plan (spec auto-signed on a
grounding-check PASS, decision log on #220):
- verb_sugar gains the shared SugarInvocation<'_> carrier (#214) with
VolStop and the factored doc_axes_from/risk_from/probe_params_from
helpers; translate_sweep/run_sweep_sugar adopt it (no behaviour
change — sweep argv and family output byte-identical), and
translate_generalize/run_generalize_sugar follow, dropping their
too_many_arguments allows (4 remain for wf/mc).
- generalize is de-welded: GeneralizeCmd takes a blueprint positional
plus repeatable --axis <wrapped-name>=<value> (one value per axis);
--strategy/--fast/--slow are deleted; dispatch_generalize runs the
sweep sequence (read, wrapped-namespace validation, canonicalize +
topology_hash registration, wrapped_to_raw_axis strip) with a new
usage closure. RGrid is deleted workspace-wide.
- cli_run generalize tests migrate argv-only; the exact-grade anchor
keeps all pinned floats verbatim; generalize_refuses_a_non_r_sma_
strategy is deleted (its premise — a strategy gate — dissolves by
design); the multi-value refusal now fires per --axis.
Verification: full workspace suite green in the loop's independent
verify; build + clippy clean. Held quality finding (kept as a
plan-hold): dispatch_generalize duplicates dispatch_sweep's
validation/strip block verbatim — dedup follows once wf/mc land the
same block (rule-of-three, end of this cycle).
refs #220, refs #214
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.
Behaviour-preserving removal of the unreachable single-run cost seam: no
caller ever passed Some(cost). Drops the cost parameter from wrap_r (the
compiler enumerated 8 sites, all passing None), the dead branch, the
vol_proxy arm, CostConfig, SLIP_VOL_LENGTH, and the 4 inert cost imports;
RollingMax/RollingMin/Sub move to #[cfg(test)] (last production caller
gone). The cost_graph composite stays alive in aura-composites; the
campaign/sweep reduce path (C10) is untouched. Decision + rationale on the
issue. Suite green unchanged (62 groups), clippy clean.
closes#221
The persist-side C1 drift alarm re-ran every nominee under the hardcoded
default vol-stop because CellRealization dropped the regime at the record
boundary — a non-default risk regime + persist taps false-failed C1 and
refused to persist a correct trace; two regimes over the same cell would
also have collided in one trace dir.
Fix at the record boundary: CellRealization carries regime + regime_ordinal
(serde-default + skip-serializing keeps pre-existing stored records
byte-stable), populated where the cell is realized; the regime->StopRule
binding is single-sourced in stop_rule_for_regime, shared by the member
runner and the persist re-run so the two sites cannot drift apart again;
campaign_cell_key appends -r{regime_ordinal} for non-default regimes
(default keys unchanged, no stored dir renamed).
closes#219, closes#212
Two RED tests pinning the lossy record boundary: CellRealization carries
no regime, so persist_campaign_traces' drift-alarm re-run hardcodes the
default vol-stop and false-fails C1 for any campaign with a non-default
risk regime + persist taps (facet A), and campaign_cell_key has no regime
discriminator so two regimes' traces would collide in one dir (facet B,
masked by A's refusal today).
refs #219, refs #212
Behaviour-free comment/rustdoc sweep of the last file the #159
demo-retirement audit flagged: repoint run_sweep/run_mc/mc_family/
walkforward_family/r_sma_sweep_over/run_oos_r/sample_blueprint_with_sinks
references to their live blueprint_* analogs or mark them retired.
De-links the r_sma_sweep_family intra-doc link at blueprint_sweep_family —
cargo doc --workspace --no-deps is now warning-clean. Verified: suite
1029/0, clippy clean, diff comment-only.
closes#222, refs #159
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 two legacy pip-scored demos — the SMA-cross (`sma`/`Strategy::SmaCross`) and
momentum (`momentum`/`Strategy::Momentum`) — and the whole built-in *synthetic*
run/sweep/walkforward/mc + `macd` surface they anchored are dropped, not
migrated: both terminated in a `SimBroker(pip_size)` construction-arg node
absent from the zero-arg std vocabulary and reported the legacy pip yardstick
C10 retired with the realistic broker. With the R-family already migrated to
data (cuts 1-3) the `Strategy` enum held only these two, so the retirement
collapses the entire built-in-strategy machinery: `Strategy`, `HarnessKind`,
`strategy_from`, `run_sweep`/`sweep_family`/`momentum_*`,
`run_sample*`/`sample_*`/`sma_cross`, the built-in
`walkforward_family`/`sweep_over`/`run_oos` and `run_mc`/`mc_family`, the `macd`
composite cluster, and `run_dispatch`/`run_args_from`/`RunCmd.--harness`.
The generic surfaces survive untouched: `aura run <bp.json>`,
`aura sweep <bp.json> --axis`, `aura walkforward|mc --strategy r-sma --real`,
`aura campaign`, `aura generalize`. Grammar consequence (derived forks logged on
#159): `run`/`sweep` now require an explicit blueprint (no synthetic default);
`sma`/`momentum` join the retired r-breakout/r-meanrev tokens in the generic
`Usage:` error, pinned by a new negative
(`sweep_and_walkforward_reject_retired_pip_tokens_as_unrecognized`); bare
`aura graph` renders the shipped `examples/r_sma_open.json` (loaded via
`blueprint_from_json`), and the render self-containment test with it; the
`sample-model.json` viewer corpus + its two `.mjs` tests stay frozen as static
test data.
`member_key`/`MAX_KEY`/`fnv1a64` were removed too. The plan wrongly listed
`member_key` as a survivor; after the built-in sweep/mc retire it has no
production caller (campaign_run derives its own content key), so it and its unit
tests are genuinely dead. The spec-compliance gate surfaced this plan-deviation;
it was ratified after verifying the tree stays green.
Verified: `cargo build --workspace`, `cargo test --workspace` (0 failed), and
`cargo clippy --workspace --all-targets -- -D warnings` all clean.
refs #159
Cut 3 of the hard-wired demo retirement. Unlike r-sma/r-breakout, r-meanrev could
not round-trip as data: its band computes band_k*sigma (a constant times a stream)
and the closed 22-node std_vocabulary had no way to express it (EqConst is i64->bool,
Bias is clamp(signal/scale,±1), Mul is binary, LinComb is excluded as a
construction-arg node; no Div/Const/constant-emitter). Standard operators are missing
by chance, not by design, so this adds the one r-meanrev needs.
Scale node (aura-std): out = input * factor — one f64 input, one f64 `factor` param,
stateless, warm-up-filtered (the EqConst/Bias shape). A zero-input `Const` emitter was
rejected: the per-cycle eval loop gates every node through an input-firing test
(harness.rs `fires()`), so a node with no input never fires without an engine-core
change; `Scale` fits the existing model and, by IEEE-754 commutativity, reproduces the
retiring LinComb's band byte-for-byte. Rostered (`"Scale" => Scale`); the two
vocabulary count-pins bump 22 -> 23.
r-meanrev migration: r_meanrev_signal(window, band_k) is carved out of the fused
r_meanrev_graph as a #[cfg(test)] price->bias Composite whose band is `Scale` in place
of `LinComb(1)`; production loads the shipped JSON (examples/r_meanrev{,_open}.json),
never a builder. Before the fused builder was deleted, an equivalence test proved the
carved Scale-band signal reproduces its grade byte-for-byte on the synthetic stream
(window=3, band_k=2). Durable survivors: the byte-identity of the examples to the
carve, the loaded-grades-identically-to-carve proof, the closed/open introspect
anchors (mean_window.length, var_window.length, band.factor — band_k is now a
first-class sweepable param), and — re-pointed onto the carve rather than dropped —
the fades-short-above/long-below behavioural test, which becomes the durable
carve-correctness gate the deleted equivalence test used to be.
Deletions + the dead-code cascade the retirement opened: r_meanrev_graph,
r_meanrev_sweep_family, Strategy::RMeanRev (+ all arms). r-meanrev was the last reader
of run_sweep's grid, so the whole vestigial built-in-sweep grid apparatus retires with
it: run_sweep's `grid` param, the sweep call-site grid build, and SweepCmd's
--fast/--slow/--stop-length/--stop-k/--window/--band-k (sma/momentum sweeps build their
own blueprints and ignored these; the fast/slow/stop-* had been vestigial since r-sma's
cut 1b). RGrid the struct SURVIVES — the dissolved `generalize` verb resolves its
candidate from its fast/slow/stop_length/stop_k via generalize_args_from — so only its
window/band_k fields go; its stale doc-comment (r-sma-sweep / persist_traces_r / CLI
flags, all now gone) is rewritten to its true generalize-only role. Also retired as
transitively dead: persist_traces_r and the metrics_object test helper (their only
callers were the deleted families/tests); Add/Gt/Latch/Mul/Sqrt imports are now
#[cfg(test)] (their last production caller was r_meanrev_graph).
Test surface: the two built-in --strategy r-meanrev sweep tests drop; a new negative
pins that --strategy r-meanrev on both sweep and walkforward now falls into the generic
usage error; the grid-flag stray-positional negative is re-pointed to a surviving flag.
Verification (own, not the workflow's report): full `cargo test --workspace` green
(0 failed across 62 result lines); `cargo clippy --workspace --all-targets -- -D
warnings` clean, no dead-code residue; the r-sma + r-breakout anchors and the
dissolved-verb real goldens (generalize still reads RGrid) stay green. Bundled as one
commit (the Scale node's count-pin and the r-meanrev anchors share graph_construct.rs,
so a clean two-commit split was not path-separable); the implement-loop ran all three
plan tasks in one pass and the tree was verified by hand.
refs #159
Cut 2 of the hard-wired demo retirement, applying the r-sma template one level
down. The r-breakout signal leg was fused into r_breakout_graph (which also built
the whole pip/R harness inline), so this cut first carves the signal leg out as a
pure price->bias Composite, ships it as a proven blueprint example, then deletes
the fused builder and the built-in --strategy r-breakout surface. The r-breakout
topology now exists only as data (crates/aura-cli/examples/r_breakout{,_open}.json).
Carved: r_breakout_signal(channel) -> Composite, a verbatim lift of the fused
builder's signal leg (Delay/RollingMax/RollingMin/Gt/Latch/Sub) exposing the raw
exposure as "bias"; the generic wrap_r/run_signal_r path (unchanged) supplies the
pip/R harness. It is #[cfg(test)] — its only role is regenerating the examples and
pinning them to a faithful serialisation; production loads the shipped JSON, never
this builder (so no dead-code residue, no production topology constructor — #159's
invariant).
Proof: before the fused builder was deleted, an equivalence test proved the carved
signal, wrapped and run, reproduces the retiring r_breakout_graph grade byte-for-byte
on the synthetic stream at channel=3 with the shared default R-stop (metric
computation is identical on both paths). That gate is deleted with the builder it
references; the durable anchors that survive are the byte-identity of the shipped
examples to the carve, the loaded-example-grades-identically-to-the-carve proof, and
the closed-ness / open-axis introspect anchors (channel_hi.length, channel_lo.length
per-node — ganging is the separate #61).
Deleted: r_breakout_graph, r_breakout_sweep_family (aura sweep --strategy r-breakout),
Strategy::RBreakout + all four match arms, the r-breakout token from the --strategy
usage strings and docs, and the now-dead --channel flag + RGrid.channel field (its
sole reader was r_breakout_sweep_family). The data successors: aura run
examples/r_breakout.json, and aura sweep examples/r_breakout_open.json --axis
channel_hi.length --axis channel_lo.length.
Test surface: the three built-in-surface sweep tests drop; the walkforward
valid-but-unsupported-token test is re-pointed to momentum (the property is generic
and stays live until Cut 4); and a new negative pins that --strategy r-breakout on
both sweep and walkforward now falls into the generic usage error, not a
special-cased message — catching a half-finished retirement that left the token
parseable.
Verification (own, not the workflow's report): full `cargo test --workspace` green
(0 failed across every binary); `cargo clippy --workspace --all-targets -- -D warnings`
clean, no dead-code residue; the r-sma introspect + grade anchors and the
dissolved-verb real goldens stay green. The implement-loop ran both plan tasks in one
pass (task_range was not honoured); the tree was verified by hand — grep-confirmed the
retired surface is gone and the carve is #[cfg(test)]-scoped.
refs #159
Cut 1b of the hard-wired demo retirement — the removal half. With the proven
example shipped in cut 1, delete the r-sma builder and its whole transitive
closure so no production function constructs the r-sma topology any more; it
exists only as data (crates/aura-cli/examples/r_sma{,_open}.json).
Deleted: sma_signal (the builder), r_sma_graph, run_r_sma (aura run --harness
r-sma), r_sma_sweep_family (aura sweep --strategy r-sma), the synthetic inline
r-sma walkforward/mc machinery (r_sma_space/r_sma_sweep_over/run_oos_r/
run_mc_r_bootstrap/mc_r_bootstrap_report + the walkforward_family RSma arm), both
fixture emitters, the round-trip + cut-1 byte-fidelity tests, the R_SMA_FAST/
SLOW/BIAS_SCALE consts, and the Strategy::RSma / HarnessKind::RSma / McArgs::RealR
variants. The three dissolved-verb synth sites (generalize/walkforward/mc
--strategy r-sma --real) now embed the shipped open example via include_str!
instead of building it — byte-safe, guarded by the unchanged dissolved-verb
real-archive goldens. The two now-redundant fixtures move to the examples
(deleted, ~40 readers repointed). The --cost-* flags on `aura run` retire with
the harness (their sole consumer was run_r_sma; cost-model coverage survives
engine/std/composites-level).
The retired demo surfaces (--harness r-sma, sweep/walkforward/mc --strategy r-sma
inline) have working data successors: aura run examples/r_sma.json, aura sweep
examples/r_sma_open.json --axis …, and the --strategy r-sma --real campaign path.
Deviation from the plan, noted: StopArm collapsed to StopRule in wrap_r's
signature (its only other variant, Open, died with r_sma_graph) — cleaner than
the planned vestigial single-variant enum; behaviour-preserving, touching
campaign_run.rs and the r-breakout/r-meanrev call sites.
Follow-up (not this cut): wrap_r's cost-node-building branch is now unreachable
(nothing passes Some(CostConfig) after run_r_sma's deletion) yet clippy-clean —
a latent cleanup for when the inline cost surface fully retires.
The stage1-r param-suffix remapping (r_sma_friendly_name + the FAST/SLOW/
STOP_LENGTH/STOP_K_SUFFIX consts) went dead and was removed, closing #167 by
deletion.
Verification (own, not the workflow's report): full `cargo test --workspace`
green; `cargo clippy --workspace --all-targets -- -D warnings` clean, no
dead-code residue; the cut-1 grade anchor (shipped_r_sma_example_reproduces_the_
builtin_grade) and the dissolved-verb real goldens (generalize/walkforward/mc
_dissolves_through_the_campaign_path) stay byte-identical. A first workflow
attempt was discarded after a subagent's `git checkout -- main.rs` recovery
silently reverted earlier tasks' edits (filed on the plugin tracker as
Brummel/Skills#23); this landing is the hardened re-run, verified by hand.
closes#167
refs #159
Cut 1 of the hard-wired demo retirement — the copy+prove phase. The r-sma demo
strategy now ships as runnable blueprint data under crates/aura-cli/examples/
(r_sma.json closed 2/4, r_sma_open.json open), emitted from the current builder
so it is byte-for-byte the builder's serialization.
Two load-bearing proofs, captured while the builder is still alive:
- byte-fidelity: the shipped examples equal blueprint_to_json(&sma_signal(..)) —
the "the copy is identical to the original" evidence the retirement method
requires before any original is removed;
- grade anchor: `aura run examples/r_sma.json` reproduces the built-in
`--harness r-sma` metrics byte-for-byte (expectancy_r/sqn/total_pips/n_trades).
Plus two property tests on the shipped copies (beyond the plan, kept as on-topic
proof strengthening): the closed example introspects to zero unbound params
(genuinely closed), and the open example lists exactly its two SMA-length axes
from the public gallery location.
Purely additive: the builder (sma_signal) and every inline r-sma surface are
retained. The recon showed deleting the builder has a large transitive closure
(the synthetic inline surface, the Strategy::RSma enum, ~40 integration tests);
that removal is cut 1b, a separate cycle, made safe by the byte-fidelity proof
frozen here.
Full workspace suite green; clippy -D warnings clean.
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
Milestone-close fieldtest for "Verb dissolution" (#210), authored from the
public interface only. Three end-to-end scenarios over the real GER40/USDJPY
2025 archive:
1. all four dissolved verbs on the r-sma real path (sweep via blueprint;
generalize/walkforward/mc via --strategy) — correct + deterministic;
2. reach-through — `aura generalize` auto-registers a campaign+process
document and `aura campaign run <id>` reproduces worst_case byte-for-byte;
3. a hand-authored 2-instrument × 2-window × 2-regime matrix (8 cells → 4
generalizations) no verb can express — regimes compared, never argmax'd.
Result: 0 bugs; the core promise holds empirically (behaviour preservation,
campaign-substrate reach-through, and the risk-regime axis all confirmed).
Residual findings are discoverability/ergonomics follow-ups, filed as #216
(risk-axis discoverability), #217 (verb knob asymmetry), #218 (no-project
store litter). The friction-and-bug spec stays a git-ignored working file.
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`
now runs as thin sugar over the one campaign executor: a generated,
content-addressed [std::sweep(argmax), std::walk_forward, std::monte_carlo]
campaign document whose terminal monte_carlo stage produces the same
StageBootstrap::PooledOos(RBootstrap). The sugar reads it from
run.outcome.record.cells[].stages[].bootstrap and reprints the existing
mc_r_bootstrap_json — one line, byte-identical to the inline path.
Pure sugar, NO executor change (aura-campaign/aura-engine/aura-research
diff-free). Mirrors the shipped walkforward dissolution:
- verb_sugar.rs: GeneratedMc, translate_mc, register_generated_mc,
run_mc_sugar (record-read + one grade line, no member lines).
- main.rs: mc_args_from + the dispatch_mc built-in-arm split gated on
`--strategy r-sma && --real`.
The one new load-bearing decision is the seed mapping: translate_mc sets
campaign.seed = the mc --seed. The wf winners are argmax hence
deflation-seed-independent (proven by the shipped walkforward anchor), so
the pooled OOS series is unchanged while the terminal r_bootstrap at that
seed reproduces the inline bootstrap. A new e2e
(mc_dissolved_seed_changes_the_bootstrap_draw_not_the_pooled_series)
pins exactly this: two --seed values yield identical n_trades but a moved
E[R] mean.
Fork C retention (as walkforward): the arm splits, run_mc_r_bootstrap /
run_mc stay inline for the fenced synthetic/non-real paths (until #159).
The three synthetic-r-sma tests use no --real, so they never enter the
sugar branch and run the inline path unchanged. --name/--trace are
rejected on the sugar path, matching the inline mc r-path.
Verification: the committed byte-identity anchor
mc_r_bootstrap_real_e2e_pins_the_exact_current_grade runs the real GER40
archive and passes byte-for-byte through the new path; full workspace
suite green; clippy --all-targets -D warnings clean.
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
The fourth and last verb dissolution (mc's R-bootstrap path) reroutes the inline
`walkforward_family -> pooled_oos_trade_rs -> r_bootstrap` through the campaign
`[std::sweep(argmax), std::walk_forward, std::monte_carlo]` process, whose terminal
monte_carlo stage does the identical `StageBootstrap::PooledOos(r_bootstrap(...))`
seeded from the campaign seed. Before that rewire, this pins the EXACT current
bootstrap grade of a fixed 2025 GER40 invocation (block_len=5, resamples=1000,
seed=42, multi-point fast 3,5 x slow 12,20 grid) so the dissolution must reproduce
it byte-for-byte (the acceptance gate).
The load-bearing subtlety the dissolution rests on: the campaign path uses ONE
campaign seed for both the wf-stage deflation and the mc-stage bootstrap, whereas
the inline path uses a fixed DEFLATION_SEED for the wf winners and the mc `--seed`
for the bootstrap. This reconciles because the wf winners are argmax (deflation
only annotates provenance), so they are seed-independent — the walkforward anchor
already proved it (the campaign path at seed 0 reproduced the inline
DEFLATION_SEED winners byte-for-byte). So `campaign.seed = mc --seed` leaves the
pooled OOS series unchanged and makes the bootstrap match. n_trades=20681 matches
the walkforward multi-grid anchor, confirming mc pools the same OOS-R series.
Deterministic; gated on the local GER40 archive, skips cleanly on a data refusal.
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
The dispatch split lands: `dispatch_walkforward`'s built-in arm now routes
`--strategy r-sma --real` through the one campaign path (`run_walkforward_sugar`
-> generated campaign doc -> executor -> summary reprint), reproducing the
`{"walkforward":{…}}` line byte-for-byte. Everything else — synthetic (any
strategy) and non-r-sma real — stays on the inline `run_walkforward`, fenced
until #159 (Reading A). The committed anchor
`walkforward_real_e2e_pins_the_exact_current_grade` passes: the dissolved path
reproduces windows=9, stitched_total_pips, oos_r, and the param_stability means
exactly. `--select plateau:*` is refused (exit 2 -> #215, Fork B); a multi-value
stop is refused (Fork A).
Two plan guesses were wrong and the anchor + real-data e2e caught both; the fixes
are documented inline:
- Window resolution: the plan mirrored generalize's `(--from,--to) -> (f,t)`
shortcut, but the inline `wf_full_span` ALWAYS clips `--from`/`--to` to the
archive's actual first/last bar (`probe_window`), even when both flags are
explicit — a holiday/weekend edge shifts every IS/OOS window's calendar
placement (stitched_total_pips diverged by ~5.16M, param_stability means intact,
confirming only window boundaries moved). The dissolved path now calls
`source.full_window(env)` unconditionally, matching the inline behaviour;
verified byte-for-byte against the still-fenced inline path.
- Reducer axis match: the campaign path records the blueprint axes wrapped
(`sma_signal.fast.length`) while the stop rides unwrapped via the risk regime, so
the reducer's exact-name match panicked on real data. Fixed with the existing
`campaign_run::raw_matches_wrapped` (#203) wrap-convention helper.
Tests: the dissolution-proof e2e `walkforward_dissolves_through_the_campaign_path`
(one process + one campaign + one campaign-run auto-registered, windows=9) plus
front-end refusal coverage (multi-value stop, `--select plateau`, missing knobs,
empty `--real`, unknown `--select`, `--name`/`--trace` exclusivity). Full workspace
suite green; `clippy --all-targets -D warnings` clean.
refs #210
The additive machinery for the walkforward dissolution, unwired this slice
(dispatch_walkforward untouched — `aura walkforward` behaviour byte-for-byte
unchanged). Two pieces, both mirroring the generalize seam:
- `translate_walkforward` + `register_generated_wf` + `GeneratedWalkforward`
(verb_sugar.rs): argv -> a `[std::sweep(argmax), std::walk_forward]` process +
a campaign carrying the multi-value fast/slow IS-refit grid over one instrument
under a single Vol risk regime (the stop). The preceding sweep enumerates the
survivor grid; the wf stage refits it per window.
- `walkforward_summary_json_from_reports` (main.rs): the pure-sugar reducer that
reconstructs the verb's summary line from the campaign's recorded per-window OOS
reports — `stitched_total_pips` = the per-window total_pips summed in roll order,
`param_stability` over the four r-sma axes via the same `MetricStats::from_values`,
pooled `oos_r` via `r_metrics_from_rs`. Byte-identical to the inline
`walkforward_summary_json` (the committed anchor gates it once Task 3 wires it).
Both carry `#[allow(dead_code)]` until Task 3's dispatch split calls them.
The third `Generated*`/`register_generated_*` trio duplicates the sweep/generalize
shape by design (per-verb mirror); the bundle consolidation is deferred to #214.
Unit test note: `r_metrics_from_rs` clears `trade_rs` (it is the terminal pooled
reducer), so the reducer's characterization fixture rebuilds each window's
`RMetrics` with `trade_rs` restored, modelling what a real OOS window's report
carries (from `summarize_r`).
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
The third verb dissolution (walkforward) reroutes the inline per-window
IS-refit (`walkforward_family` -> `select_winner` -> OOS run -> stitch/pool)
through the campaign `std::walk_forward` stage. Two summary fields have no
campaign equivalent today: `stitched_total_pips` (the runner discards the raw
OOS pip curve, `oos_equity: vec![]`) and pooled `oos_r` (only a following
`std::monte_carlo` stage produces it). Before the executor work that closes
those gaps, this pins the EXACT current grade of a fixed 2025 GER40 invocation
so the dissolution must reproduce it byte-for-byte (the acceptance gate).
The grid is deliberately multi-point (fast 3,5 x slow 12,20): it makes the
per-window winner selection non-degenerate (`param_stability` varies across the
9 windows), so a winner-pick divergence between the inline and campaign refit
cannot ship green — the same gap the generalize anchor closed for its sibling
shape-only test. Deterministic (C1); gated on the local GER40 archive, skips
cleanly on a data refusal.
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
Brummel