cost_nodes_for (beside stop_rule_for_regime) is the one CostSpec ->
bound-builder binding — every component fully bound, so the wrapped
param space stays cost-invariant. run_blueprint_member joins the cost
rows into summarize_r (member metrics genuinely net) and stamps the
cost components into the manifest params; CliMemberRunner threads the
doc's cost. The re-run sides re-derive the model from the manifest:
reproduce via cost_specs_from_params (the #233 stop pattern — a costed
family reproduces bit-identically) and persist_campaign_traces binds
the same model so the C1 drift alarm compares like with like.
Hand-computed pin: a constant cost model yields
net_expectancy_r == expectancy_r - cost_per_trade/|entry-stop| on a
synthetic member.
Verified: full workspace suite green, clippy -D warnings clean; in-loop
spec + quality gates passed per task.
refs #234
The defining loop of a genuine external project, proven end-to-end and
green on arrival: a fresh aura-new project authors an OPEN blueprint
over its own node (knob_lab::Scale, factor unbound); --list-axes shows
the axis, a real-data GER40 sweep over it yields two members whose
manifests carry the project-node binding, the family persists and
reproduces 2/2 bit-identically, and one campaign cell over the same
blueprint runs to exit 0 linking a sweep family. No implementation was
needed — the loop already worked; this pin is the previously-missing
evidence (the deepest exercised path before was a single param-less
aura run). The axis-discovery leg is un-gated so the test stays
meaningful on a data-less host.
closes#235
The acceptance proof: hl_channel — a causal Donchian channel (Delay(1)
excludes the current bar, C2) consuming high/low/close roles, built from
rostered vocabulary, shipped as the r_channel/r_channel_open example
pair (builder + regenerator + serialize pins, the r_* pattern). Proven
at three layers: a non-gated loaded-vs-carve equivalence over inline
sources (non-zero-bias hardened per review), the unconditional synthetic
multi-column refusal, and archive-gated CLI e2e — aura run on GER40
end-to-end plus a sweep whose members run and reproduce 2/2
bit-identically.
Ledger: new C26 entry (the binding vocabulary — closed column set +
price alias, name-driven default + campaign data.bindings override,
canonical order = the C4 tie-break, Blockly-litmus argument, the #71
extension point for recorded non-price sources) and the C20/C24
scaffolding-clause annotations: the single-price data weld is retired,
wrap_r's remaining R-scaffolding retirement stays #159.
Verified: all proof tests green, full workspace suite green, clippy -D
warnings clean; independent quality review approved.
closes#231
DataSection gains an additive bindings block (role -> column; serde
default + skip-if-empty, so binding-less documents keep their content
ids — pinned). Validation is two-tier along the existing line: the
intrinsic tier checks binding VALUES against the column vocabulary
(DocFault::UnknownBindingColumn, alias-annotated display register); the
resolver tier checks binding KEYS against the loaded strategies'
input_roles() (RefFault::BindingRoleUnknown — a key must name a role of
at least one campaign strategy). A cross-surface pin keeps the doc-tier
vocabulary and the CLI binding module from drifting.
CliMemberRunner threads the campaign overrides into resolve_binding on
BOTH halves (column opening and wrap), keeping the C1 drift alarm
comparing like-with-like; the verb sugar passes no bindings (name
defaults rule).
Proof: an archive-gated campaign e2e rebinds price -> open and yields
different realized metrics from the close-bound run; refusal prose
exact-pinned at both tiers.
Verified: full workspace suite green, clippy -D warnings clean;
independent quality review, all findings repaired.
refs #231
The six Close-only open sites route through the resolved binding's
column set via open_columns (probe_window, open_real_source,
run_sources/windowed_sources, the campaign member open, the trace
re-run open) — a strategy declaring high/low/close roles gets exactly
those columns, merged in the canonical C4 order. Synthetic data refuses
any binding beyond {close} with the honest --real remedy (the walk
generates a close series only); the sweep/mc family builders ride their
established Err contract, run/walkforward/reproduce refuse exit-1.
Proof at two layers: an engine e2e composes an OHLC blueprint from data
and runs it over four inline VecSources to hand-computed rows (the
merge-order pin), and an archive-gated CLI e2e sweeps a high/low
blueprint over GER40 opening the High and Low columns.
Verified: engine OHLC e2e green, full workspace suite green, clippy -D
warnings clean.
refs #231
--trace <fam> now translates through the verb sugar into a persist_taps
campaign-presentation block (was persist_taps: vec![] — the #168 no-op)
and persist_campaign_traces writes EVERY member of a selection-free
swept cell, one subdirectory per member under the cell dir, keyed by
the member's manifest params label in reproduce's exact format
(filesystem-sanitized, ordinal fallback); nominee cells keep their flat
layout. Members re-run at the cell's own stop regime and resolved pip,
streaming one member at a time, with the C1 drift alarm preserved per
member. The walkforward sibling lifts identically; run/mc --trace stay
refused by design (no campaign context / no family-name concept — their
help was already honest). Clap help lines and the chart NotFound hint
restored; the old #168 refusal pins re-pinned to the delivered
behaviour.
Post-review repairs: member_trace_key + cell_member_fanout extracted
pure and unit-pinned (6 tests), persisted_cells counts cells again,
cell-invariant space/geo hoisted out of the member loop, verb_sugar
tail comment corrected.
Verified: headline e2e green (GER40 archive), cli_run 124/0, full
workspace suite green, clippy -D warnings clean; independent spec
review compliant, quality review findings all repaired.
closes#224
refs #168
Pins the #224 delivery headline: the #168 refusal lifts and at least
one non-empty tap-series file lands under runs/traces/. Layout-agnostic
on purpose — the per-member key convention is the GREEN slice's call.
refs #224
Editing project src/ without cargo build silently runs the previous
dylib with plausible stale numbers (role-2 authoring-loop footgun).
Pins: source mtime newer than the dylib -> stderr warning naming both
timestamps, run proceeds unchanged (warn, not refuse — a stale run is
still deterministic and manifest-stamped).
refs #237
Five new rostered node types (count-pin 23 -> 28, both the in-crate
shape test and the cross-boundary CLI vocabulary e2e): Const is unary
with an f64 'value' param — the clock input drives it, its value is
ignored, since a zero-input node never evaluates in the total-push
engine — mirroring EqConst's constant-as-param pattern; Div is binary
IEEE-754 (x/0 -> signed inf, 0/0 -> NaN, unit-tested, no error
channel); Abs unary mirroring Sqrt; Max/Min binary pairwise, distinct
from the windowed RollingMax/RollingMin.
Acceptance proof: the committed executable spec composes an RSI-class
gain/loss-split-and-ratio signal purely from blueprint data through
std_vocabulary and runs it to hand-computed RS values — the r_meanrev
constant-folding workaround is no longer forced.
Verified: headline test green, aura-std 163/0, full workspace suite
green (independent mini-verify), clippy -D warnings clean.
closes#236
aura graph <op-script.json> exits 2 mislabeling the valid JSON array as
'blueprint document is not valid JSON'; register/--params already
shape-discriminate via composite_from_any. Pins render parity: op-script
and its built envelope render byte-identically at exit 0.
refs #226
wrap_r hardwired SimBroker::builder(SYNTHETIC_PIP_SIZE); the resolved
geometry-sidecar pip reached only the manifest broker label, so every
real-data run computed total_pips/max_drawdown at 0.0001 regardless of
instrument (GER40 pip=1: inflated 10^4) while the label claimed the
real pip.
wrap_r now takes pip_size. Real-pip call sites pass the resolved pip:
run_signal_r (resolve_run_data reordered before the wrap),
run_blueprint_member, and the campaign trace re-run in
persist_campaign_traces (instrument_geometry lookup mirroring the
run_member refusal — required so the C1 drift alarm compares re-run
and nominee at the same pip). Probe-only call sites (param-space and
axis probes; metrics discarded) keep SYNTHETIC_PIP_SIZE explicitly.
The two golden stitched_total_pips pins in cli_run.rs rescaled by
exactly the 10^4 bug factor while n_trades/expectancy_r stayed
byte-identical — confirming R metrics were never pip-contaminated.
Alternative rejected: dropping pip-denominated metrics from real-data
reports — the manifest already stamps the resolved pip, so running the
graph at it restores label truthfulness without shrinking the report.
Verified: full workspace suite green (0 failed incl. the real-data e2e
suite), clippy -D warnings clean.
closes#232
Two failing e2e pins (skip-on-no-data, GER40 archive present here):
- reproduce_real_sweep_family_re_derives_bit_identically: a --real sweep
family must reproduce N/N bit-identically; currently 0/N DIVERGED because
reproduce_family re-runs members over DataSource::Synthetic.
- reproduce_real_walkforward_family_does_not_panic: a --real WalkForward
family must yield a verdict or a clean refusal; currently panics at the
empty-OOS-window expect (main.rs:1123) for the same reason.
refs #229
The two open examples now expose their author-intended single knobs — the
closed builders always bound these pairs to one value by hand; the open forms
falsely offered them as independent axes:
- r_breakout_open: channel_hi.length + channel_lo.length -> channel_length
(the Donchian channel is structurally ONE parameter)
- r_meanrev_open: mean_window.length + var_window.length -> window; the band
factor stays an independent axis
Regenerated via the emitters (never hand-edited); the closed examples are
byte-unchanged. The carve builders gang in the open branch only.
Test migration: the two axis-namespace pins, five --real e2e invocations
(single gang axis, the 10,20 diagonal for the campaign pair — the mismatched
20,40/10,20 grid was exactly the configuration space the gang retires), and
the param_stability row counts (4 -> 3). The r-sma walkforward golden anchor
is untouched (it never swept a ganged pair).
Docs: authoring-guide gains the seventh op + the third param state
(open/bound/ganged) + the gang wrap note; README op list + Axis concept;
glossary gang entry; ledger C24 records the gang verb and the pre-ship
Tier-2 dormancy (no format-version bump while no out-of-repo reader exists).
Verified: full workspace suite 1104/0 (--real e2e included, local data
present), clippy -D warnings clean, cargo doc clean; live acceptance:
introspect --params prints channel_length:I64 alone / window:I64 +
band.factor:F64.
closes#61
Builder: NodeHandle::param -> ParamRef, GraphBuilder::gang, build() resolves
the gang table (collect-then-reject, BuildError::{UnknownParam,AmbiguousParam,
BadGang}) and terminates in Composite::with_gangs — the same predicate the
op-script and serde boundaries use. C24 lockstep extended: an op-script gang
replay serializes byte-identically to the GraphBuilder twin (FlatGraph edges +
sources + canonical JSON).
Render: model_to_json emits a per-scope gangs fragment (name, kind, [node,pos,
"param"] members) for ganged scopes only — the gang-free model stays
byte-identical (model_golden untouched). graph-viewer.js annotates a ganged
open param with its public knob name; guarded by a viewer_gang_param.{mjs,rs}
pair RED-first per the established viewer_bound_param convention (a welcome
extra beyond the plan's file list).
Ratified deviation: the model's kind string uses the serde form ("I64") — the
plan's implementation snippet (kind_str -> "i64") contradicted its own test;
resolved toward the test + the blueprint_serde form. Two quality nits held as
principled plan-holds (inline resolution block; the unreachable unwrap_or
placeholder check_gangs refuses first).
Verified: aura-engine lib 264/0 (model_golden, lockstep, builder, carrier all
green), viewer_gang_param 1/0, workspace clippy -D warnings clean. Slice
resumed across a transient API failure via workflow resume (cached prefix).
refs #61
Serde: CompositeData carries an additive-optional gangs section (omitted when
empty — every existing v1 document round-trips byte-identically, NO
format-version bump per the #61 decision; BLUEPRINT_FORMAT_VERSION doc now
records the pre-ship Tier-2 dormancy). project() emits gangs canonically
(members by (node,pos), gangs by first member) so declaration order never
reaches the content id; reconstruct() re-mints through Composite::with_gangs
and a corrupted section refuses as the new typed LoadError::Gang.
strip_debug_symbols blanks gang + member names, keeps (node,pos,kind) — the
identity id stays gang-name-blind and gang-structure-sensitive.
Construction: Op::Gang { as_name, into } with the feed-style two-phase eager
arm (member resolution against the post-bind schemas, kind uniformity,
single-gang membership; OpError::{GangKindMismatch,AlreadyGanged,GangArity});
finish() routes the assembled composite through with_gangs, and gang-name
collisions surface via the existing injectivity gate on the projected space.
CLI: OpDoc::Gang ({"op":"gang","as":…,"into":[…]}), kind_label/From/
format_op_error arms, and format_load_error phrases gang faults as prose
(gang_fault_prose) instead of leaking Debug — a ratified improvement over the
plan bytes.
Held quality nit (principled plan-hold): gang()'s inline collect-then-reject
param resolution is the module's established convention (bind/try_bind); a
shared cross-crate helper is out of this task's scope.
Verified: workspace build clean, aura-engine lib 258/0, aura-cli
graph_construct 48/0 (incl. the new gang-op e2e), clippy -D warnings clean.
refs #61
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 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 `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 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
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.
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
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
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
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 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 (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
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 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
`generalize_dissolves_through_the_campaign_path` asserts the verb now runs
through the one campaign path: exactly one generated process document, one
generated campaign document (carrying the --name handle and the stop as a
non-empty risk regime), and one campaign-run record are durably auto-registered,
plus the campaign-path family set (1 CrossInstrument grade family + 2
per-instrument Sweep families). The observable proof the inline path is gone.
refs #210
`dispatch_generalize` synthesizes the bare `sma_signal` blueprint, resolves the
window (explicit --from/--to, else the first symbol's full window), and calls
the new `run_generalize_sugar`; the inline `run_generalize` is deleted. The
sugar builds the selection-bearing campaign doc, runs it through
`run_campaign_returning`, reprints the byte-identical `{"generalize":…}` +
`{"family_id":…}` lines, and persists the CrossInstrument family.
The exact-grade anchor stays green through the path shift — proving the two stop
mechanisms (former grid axis, now the risk-regime seam -> StopRule::Vol) yield
identical R. The family pin relaxes to "exactly one CrossInstrument family"
since the campaign executor now also persists a per-instrument Sweep family per
cell (the durable audit trail; #210 Q4). Two new e2e pin the window fallback and
the family member attribution order.
Deviations from the plan (necessary, verified): cross_instrument_members returns
Vec<aura_engine::RunReport> (aura_registry::RunReport is not pub); a shared
validate_before_register helper is factored out of run_sweep_sugar (DRY); the
run_generalize doc-comment and the now-unused `generalization` import removed.
refs #210
The current `aura generalize` binds its protective stop as a grid axis
(`r_sma_sweep_family` with `stop_open=true`); the pending generalize
dissolution rebinds the same stop through the risk-regime seam
(`RiskRegime::Vol -> StopRule::Vol`). The existing generalize e2e
(`generalize_grades_a_candidate_across_two_instruments`) asserts shape
only — `worst_case` and the per-instrument R floats are never checked —
so a divergence between the two stop bindings would ship green.
This adds `generalize_real_e2e_pins_the_exact_current_grade`, capturing
the exact current R grade of the identical invocation (GER40 0.0105637…,
USDJPY 0.0057959…, worst_case 0.0057959…, sign_agreement 2). Green today
against the inline path; after the dissolution the same command must
reproduce these bytes — the acceptance gate that catches a stop-mechanism
divergence loudly instead of silently.
Resolves the generalize-dissolution grounding block (the unpinned
stop-mechanism R equivalence) by the risk-regime characterization-pin
pattern. refs #210
The runtime-binding slice — the regime's stop now actually reaches the graph and
the record:
- `StopArm { Open, Bound(StopRule) }` replaces `wrap_r`'s `stop_open: bool` so a
bound stop carries its params; all call sites threaded (the r-sma sweep path
stays Open, every bound site passes the resolved rule).
- `run_blueprint_member` takes a `stop: StopRule` and stamps `stop_length` /
`stop_k` into the member manifest (the ratified C18 extension — the stop is no
longer invisible on the campaign/blueprint path); its callers thread the
default, and `CliMemberRunner` maps `cell.regime` (None -> baked default,
Some(Vol) -> that vol stop).
- The characterization pin flips from asserting the stop's ABSENCE to requiring
the stamped default; a real two-regime e2e pins that each regime stamps its
own k.
Known deferred gap (concern, documented descope): `persist_campaign_traces`
re-runs the nominee to persist its traces and — since `CellRealization` carries
no regime — binds that re-run to the DEFAULT stop, so a non-default-regime
nominee's persisted trace would reflect the wrong stop. Only the persist path
(non-empty `persist_taps`) is affected; the core run/stamp/generalize path is
correct. Filed as a follow-up. Full workspace suite green.
refs #210
The first slice of the risk-regime structural axis (spec/plan abab1f1):
- aura-research: a serializable `RiskRegime` closed vocabulary (externally
tagged, sole variant `Vol { length, k }` — a content-addressable mirror of
the shipped two-variant StopRule, so a future Fixed regime is additive), and
an optional top-level `CampaignDoc.risk: Vec<RiskRegime>` that absent-
serializes (the `description` precedent) — content-id parity for every
risk-less document.
- validate_campaign refuses a non-positive regime (length < 1 or k <= 0, NaN
included) via a new `DocFault::BadRegime`; the CLI renders it as prose at the
research_docs seam (register/validate paths).
- The three CLI-seam E2E tests pin that a well-formed risk section passes
`campaign validate` and a bad one is refused with prose (exit 1, no Debug
leak) — the field is reachable at the seam a data author drives, not only in
library units.
Adding the field is compile-breaking at every `CampaignDoc { .. }` literal
(serde default does not cover Rust construction), so this slice also threads
`risk: vec![]` into the sites across aura-cli and aura-campaign — the
field-addition's compile-gate completion the plan should have scoped here. The
BadRegime prose reads `risk[i]: ...` (the implementer's terser wording over the
plan's illustrative string; the spec pinned no exact text). Full workspace
suite green.
refs #210
The dissolved real-data sweep member manifest carries only the swept signal
axes today — no stop param; the R-path stop is a wrap_r constant baked outside
the signal param_space. The existing member-line pin
(sweep_real_blueprint_member_lines_pin_the_dissolved_contract) locates each
binding by `find`, so it never pinned this absence. This characterization pin
does, as the grounding ratification for the risk-regime-axis design pass: the
resolved-regime manifest stamp will flip it to require the stop key — the
ratified additive contract extension, exactly like the instrument stamp.
refs #210
Three test-first fixes from the cycle-0110 fieldtest findings:
- Axis-name preflight on the dissolved sweep arm: every --axis name is
checked against the wrapped probe namespace (the --list-axes names)
BEFORE the #203 strip; an unknown or raw-form name is refused
house-style echoing exactly what the user typed, with a --list-axes
pointer — no more stripped-then-mangled fragments from the deep
referential refusal. Data-free, fires before the archive is touched.
- Validate-before-register in the sweep sugar: intrinsic doc checks +
executor preflight + the pure bind_axes coverage check (reused, not
re-inlined; now pub(crate)) all run in-memory before
register_generated — a refused invocation leaves no generated
document in the content-addressed store and no campaign_runs.jsonl
line (previously P2/P3 refusals littered runs/campaigns, one doc
malformed).
- blueprint_slot_prose: the sweep/walkforward/mc loaded-blueprint slots
share one dispatch-boundary presenter — an op-script array gets a
targeted 'run aura graph build first' hint, every load error goes
through blueprint_load_prose + the missing-project hint, and the raw
{e:?} Debug leak (#184's pattern, deliberately left on these three
slots back then) is gone. Two stale Debug-leak pins flipped, two new
refusal tests.
Suite 1060/0, clippy -D warnings clean.
refs #210
Brummel