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
`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
`translate_generalize` builds the selection-bearing campaign document
(`[std::sweep(argmax), std::generalize]`, a single risk regime carrying the
stop, the candidate as single-value raw axes) + `GeneratedGeneralize` +
`register_generated_g`, mirroring the sweep translator. A determinism unit test
pins identical-invocation -> identical content id and the regime/pipeline shape.
The new items are unused until the dispatch-rewire task (#210 T3) wires the
runner; a bridge `#![allow(dead_code)]` (removed in T3) mirrors the sweep
sibling's landing.
refs #210
`run_campaign_returning` runs the resolve->execute body and returns a
`CampaignRun` bundle (outcome + campaign/strategies/server); `present_campaign`
consumes it for the stdout tail; `run_campaign_by_id` becomes their composition.
Behaviour-preserving — the existing campaign + sweep-sugar e2e stay green
(research_docs 54/0 incl. the real-data e2e, sweep dissolution e2e green).
Exposes the outcome so the forthcoming generalize sugar can read it without the
presentation tail.
refs #210
Second verb dissolution: `aura generalize` becomes thin sugar over the one
campaign executor, byte-identical output, the stop carried by a single risk
regime. Spec grounding-check PASS (auto-signed) after the exact-grade anchor
(f3f32b8) closed the stop-mechanism R-parity block. Plan derives four
implementation forks (Q1 blueprint source, Q2 run-outcome bundle, Q3 window,
Q4 the campaign-path family set — user-visible), all recorded on #210.
refs #210
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
Architect drift review (c9d962f..HEAD). What holds: the nominee key is the
3-tuple (strategy, window, regime) and no argmax over regime_ordinal exists, so
the ledger's kept-separate / compared-not-selected semantics is what the code
does; the C18 manifest stamp is honest (the characterization pin flipped from
asserting absence to requiring the exact resolved 3/2.0, a strengthening, and a
real two-regime e2e catches per-cell mis-resolution); no dead code (cell.regime
and regime_ordinal are both read after the runtime-binding slice), absent/empty
risk keeps content-id parity, and CampaignGeneralization.regime_ordinal is
serde-default so pre-feature records still parse.
Resolution:
- FIX (inline, this commit): the spec promised a C10 AND a C20 note; only C10
landed. C20's enumerated structural-axis list (strategy/instrument/broker/
window) was left silently incomplete — the risk regime is added as the fourth
matrix axis, with a dated realization pointer to the C10 semantics.
- carry (documented descope): no std::risk descriptor in CAMPAIGN_SECTIONS —
risk is a top-level array, not a slot-bearing section; no invariant broken.
- carry (filed #212): the persist re-run + campaign_cell_key omit the regime
because CellRealization gained none; the architect verified this is a LOUD C1
drift-alarm refusal for a non-default regime + persist_taps, not silent wrong
data (#212 corrected accordingly).
- trivial: validate_campaign's regime-check comment corrected (it catches NaN,
not all non-finite; +inf is unreachable via JSON).
Regression gate: full workspace suite green, clippy clean (no dedicated
regression script; the suite + lint are the gate). Spec and plan removed
(git rm) at cycle close per the project convention. No baseline moved.
refs #210
The last slice of the risk-regime structural axis. The sugar parity
(`translate_sweep` emitting `risk: vec![]`, absent-serializing) and the
real-data two-regime e2e landed in the earlier slices (the loop's self-correction
and its e2e phase), so this closes the remaining pieces:
- design-ledger note: the risk regime realizes the StopRule structural axis at
the campaign-document level — kept-separate keying, compared-not-selected (the
R-unit argument), the C18 stamp, absent-parity, and the deferred trace gap
(#212).
- clippy: `validate_campaign`'s regime check reads `k <= 0.0 || k.is_nan()`
instead of `!(k > 0.0)` (neg_cmp_op_on_partial_ord), behaviour-identical.
Full workspace suite green; clippy clean.
refs #210
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 regime becomes the fourth structural coordinate of the campaign matrix, a
kept-separate axis (a peer of window, not aggregated-over like instrument):
- aura-campaign: CellSpec gains `regime` + `regime_ordinal`; the executor
resolves the regime list (absent/empty risk -> one default cell, ordinal 0),
runs a cell per (strategy, instrument, window, regime), and keys the nominee
map by the 3-tuple including the regime ordinal — so generalize aggregates
across instruments WITHIN a regime, never across regimes. Family names gain a
`-r{regime_ordinal}` discriminator so two regimes' families cannot collide.
- aura-registry: `CampaignGeneralization` gains `regime_ordinal` (with
`#[serde(default)]`, so pre-feature stored records still parse — pinned by a
new backward-compat test).
The existing single-regime execute tests shift their family ids by `-r0`; a new
test pins that two regimes yield distinct `-r0`/`-r1` families. `CellSpec.regime`
is write-only in this slice — its sole reader is the deferred member runner
(the next slice) — a held quality nit, seam-prep as the plan prescribes. 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
Spec auto-signed on a grounding-check PASS: the risk regime becomes a
structural campaign axis (a peer of instruments/windows, kept-separate in
the executor, each member's resolved stop stamped into its manifest;
regimes are compared, never argmax-selected across — a cross-regime E[R]
argmax would mix R units, C10). The 5-task plan threads it through
aura-research (RiskRegime + CampaignDoc.risk), aura-campaign + aura-registry
(matrix expansion + regime_ordinal), and aura-cli (StopArm + wrap_r + the
manifest stamp). Two bounded, documented descopes: the descriptive
CAMPAIGN_SECTIONS introspection entry and multi-regime trace-dir isolation.
refs #210
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
Authoring guide §1: the inline SMA-crossover op-script no longer binds
fast/slow lengths — it is byte-identical to the corpus file it claims
to match (content id 597d719b… verified against the binary), and the
previously unwritten rule is stated: an op-script bind pins a param
OUT of the sweepable space (closed — no campaign axis or --axis can
reopen it). New passage + example distinguishing the raw param-space
namespace (--params, campaign-document axes) from the wrapped
--list-axes/--axis surface; glossary sweep entry carries the same
one-sentence distinction.
refs #210
Consumer scenario against the public surface only: selection-free
process doc round-trip, the dissolved real-data sweep (doc dedupe +
realization accumulation + C1 bit-identity), refusal edges, rank-later
over the persisted family. 0 bugs; the cycle's own axes all came back
working. 4 friction + 2 spec-gap findings on the verb entry ergonomics
and pre-existing guide drift — transcribed in
docs/specs/fieldtest-sweep-dissolution.md for triage.
refs #210
Architect review (scope e7c7bde..b7aaa0b) found three items; resolutions:
- fix: docs/authoring-guide.md + glossary aligned with the shipped
vocabulary (std::sweep selection group optional/all-or-nothing,
selection-free = terminal-only, worked example verified against the
live binary).
- fix: the #203 wrapped/raw axis-name convention is now single-sourced
in campaign_run.rs (wrapped_to_raw_axis + raw_matches_wrapped, a
cross-documented inverse pair; dispatch_sweep and both bind sites
call through it; inverse-property unit test). Ratify note: this
unifies two previously different algorithms onto the documented
first-segment semantics — the old loose ends_with suffix-match also
accepted sub-segment shorthands (e.g. axis "length" against
"sma_signal.fast.length") that no stored document or test used;
such shorthands now refuse loudly (unbound/unknown axis) instead of
matching, the refuse-don't-guess reading of #203.
- carry: run_blueprint_sweep/blueprint_sweep_family remain generically
real-capable though the dispatch no longer routes real data to them;
the residual capability is shared DataSource machinery, its removal
falls out with the built-in/synthetic branch retirement (#159), and
the synthetic-only status is documented at the fn.
What holds: C24 canonical form (flatten group leaves every stored
content id unchanged, golden pin untouched), C18 lineage (topology_hash
IS content_id_of, single store write resolves the strategy ref;
selection-free arm still persists the full family), C25 closed-
vocabulary discipline (all-or-nothing group, Blockly-clean), C3 (ms/ns
conversion through the ingest seam's own named fn).
Ledger: #109 open-thread status lifted to cycles 0107-0110 reality
(executor shipped, amendment package landed, verb dissolution running
as milestone #210 with sweep dissolved).
Regression gates: cargo test --workspace 1056/0; clippy -D warnings
clean; cargo doc clean. Cycle spec+plan removed at close per
convention.
refs #210
aura sweep <bp.json> --real ... --axis ... now runs as thin sugar over
its generated campaign document through the one campaign executor: the
dispatch registers the canonical blueprint (topology_hash IS
content_id_of over the same canonical bytes, so the strategy ref
resolves against the existing single store write), strips the CLI's
wrapped axis names to the raw campaign namespace (#203 bind
convention), converts the probed archive window back through the
ingest seam's own epoch_ns_to_unix_ms (made pub; C3 — the seam owns
the ms/ns convention, never an inline division), and hands off to
verb_sugar::run_sweep_sugar. The inline real-data arm is gone; the
synthetic arm and --list-axes are untouched.
campaign_run gains RunPresentation {Full, MemberLinesOnly}:
run_campaign keeps Full (record line unchanged, project gate
unchanged); the sugar path runs MemberLinesOnly — the generated doc's
emit already limits stdout to family_table member lines, the mode
suppresses only the final record line. The record append is identical
in both modes; no project gate on the by-id path (the dissolved verb
works project-less, exactly as before).
The characterization pin survives the re-cut with exactly the one
sanctioned assertion flip (instrument-absence -> instrument==GER40)
and now also pins the generated artifacts: one process + one campaign
document auto-registered (dedup on a second identical invocation),
raw axis keys in the stored document, the stored window a ms sub-range
of the request, C1 at the member-report level with the registry's
run-suffix increment isolated.
Suite 1055/0, clippy clean, gated real-data paths executed locally.
refs #210
The pure half of the sweep re-cut: translate_sweep maps a real-data
blueprint-sweep invocation (axes, name, symbol, window, canonical
blueprint bytes) to a selection-free single-stage process document plus
a campaign document carrying exactly the invocation's intent (seed 0 —
no stage consumes it — so identical invocations dedupe onto identical
content ids); register_generated puts both into the content-addressed
stores. Unit tests pin determinism, name flow, mixed-kind-axis refusal,
and that generated documents pass intrinsic validation + preflight.
Dead-code-allowed until the dispatch rewire wires the module (next
task removes the bridge attribute). Plan bytes reconciled with three
necessary deviations the spec gate surfaced: derive(Debug) for
unwrap_err, ScalarKind lives in aura_core, and 'gen' is reserved in
edition 2024.
refs #210
The std::sweep selection triple (metric/select/deflate) becomes ONE
optional group, Option<SweepSelection>, serde-flattened so the wire
form keeps the flat slots: every existing document parses to Some and
its canonical bytes — and content id — are unchanged (golden pin
byte-untouched). A half-populated group is refused by the schema-strict
parser (all-or-nothing); a bare {"block":"std::sweep"} is the
selection-free sweep.
Campaign side: preflight permits a selection-free sweep only as the
pipeline's terminal stage (new ExecFault::SelectionFreeSweepNotTerminal,
prose in aura-cli's exhaustive exec_fault_prose); the executor's
selection-free arm appends the family exactly as before but records no
StageSelection and produces no nominee (recording one would fabricate
intent — #210 fork decision 1).
Introspection follows: the sweep block's schema table marks the group
optional; CLI introspection pins updated. New tests: group-or-nothing
refusals, selection-free round-trip + distinct content id, terminal-only
preflight accept/refuse, selection-free execute realization.
refs #210
Cycle 1 of the verb-dissolution milestone (refs #210): the real-data
blueprint sweep re-cut as sugar over a generated, auto-registered
campaign document; optional selection group in the sweep stage
vocabulary; terminal-only preflight rule. Spec auto-signed on a
grounding-check PASS (decision log on #210); ephemeral per convention,
removed at cycle close.
Two green pins the sweep-dissolution cycle rests on (refs #210):
- sweep_real_blueprint_member_lines_pin_the_inline_contract: the inline
real-data blueprint sweep prints one member line per grid point in
odometer axis order, carries the swept bindings in manifest.params,
persists exactly one Sweep family — and never stamps an instrument
key (RunManifest::instrument stays None on this path).
- campaign_run_real_e2e_sweep_gate_walkforward (extended): every
family_table member line emitted by the real campaign member-runner
path is stamped with the instrument under test.
Together they pin the one behavioural delta between the two paths (the
additive instrument stamp) that the dissolution's parity contract is
phrased against.
Close two milestone-fieldtest doc-gaps (F6/F8) with one pass now that the
surfaces are stable. A newcomer could only learn the three headless JSON
artifact kinds from the fieldtest corpus: the op-script grammar was
undocumented (#208) and there was no worked process/campaign example nor a
pointer to the discoverable metric vocabulary (#197).
Add docs/authoring-guide.md — a worked, verified example per artifact kind
(op-script -> graph build; process document -> process validate/register;
campaign document -> campaign validate/register/run), every command run
against the binary and its output transcribed. Documents all six ops
(source/input/add/feed/connect/expose) with their JSON shapes, and teaches
the metric roster split (rankable / gate / | generalize) pointing at
'aura process introspect --metrics' as the source of truth rather than
hand-copying the rosters. A short paragraph in project-layout.md links it.
Docs only; no code or CLI change (the surfaces already suffice). Grammar
grounded on construction.rs; examples faithful to the milestone corpus.
closes#197closes#208
aura run leaked the raw LoadError Debug form (UnknownNodeType("..."))
while graph build already phrased the same fault house-style (#162
convention: engine error types are Display-free, the CLI presents them).
Route the run path through the shared blueprint_load_prose presenter (now
pub(crate), env-agnostic) so both surfaces phrase a LoadError identically
and neither leaks the Debug token (#184). Add unresolved_namespace_hint:
when the unresolved id looks project-namespaced (::) and no project was
loaded (env.provenance() is None), append a hint pointing at the missing
Aura.toml — the newcomer running the host from the wrong directory now
gets an orienting diagnosis instead of a bare type error (#185). The hint
is applied on both the run and graph-build paths. RED-first: the two
existing run-path pins were flipped to assert the prose + absence of the
Debug token before implementing; suite green (1043/0).
closes#184closes#185
DEFLATION_N_RESAMPLES (1000) and DEFLATION_BLOCK_LEN (5) were duplicated
as independent copies in aura-cli and aura-campaign — a silent-drift risk
(an edit in one crate but not the other refuses nothing, it just produces
a wrong deflation result). Promote a single definition into aura-registry,
which owns optimize_deflated (the sole consumer of these counts); aura-cli
imports it and aura-campaign re-exports it to keep its public path stable.
DEFLATION_SEED stays cli-local (no campaign twin). Values unchanged;
behaviour-preserving, suite green unchanged (1043/0).
closes#199
The research-artifacts milestone fieldtest closed GREEN and the milestone
is formally closed; per the ephemeral-artifact convention its spec is
git-rm'd at cycle close. The verdict survives durably in the tracked
corpus (fieldtests/milestone-research-artifacts/FINDINGS.md), the closed
milestone, and the ledger.
Second half of the style pin. assets/aura.css now carries (a) the full
:root token palette (Catppuccin-Mocha-derived; --bg deliberately darker
than Mocha base; new --border3 #585b70 completes the border ladder at an
identical computed value), (b) the shell rules migrated color-literal to
var() with identical computed values (font stacks stay literal — the
--mono token's longer fallback chain would change the computed value),
and (c) an opt-in, class-scoped component library distilled from the
milestone demo page (.aura-doc register, .wrap, .badge, .stats, .cards,
.term, .callout, table.res, .pipe) — unused by the runtime pages, which
render pixel-identically. CHART_CSS migrates to the same tokens (it
lands in the same document after the shell <style>, so :root resolves).
CLAUDE.md gains the binding '## HTML surfaces' rule: every HTML surface
embeds this asset; extend, never fork.
Gates: suite 1043/0, clippy -D warnings clean, doc build 0 warnings;
regenerated chart page resolves all 17 used var() names against its
:root. Independent CSS audit passed (two cosmetic notes: --bg3/--orange
currently unused; the pre-existing html,body height:100% also reaches
future .aura-doc pages).
closes#209
Pure byte-preserving extraction: the CSS block inside SHELL_HEAD moves
verbatim into crates/aura-cli/assets/aura.css and is spliced back via
concat!(.., include_str!(..), ..). Proven against a pre-change baseline:
chart HTML (aura chart 42edebd2-0/597d719b-GER40-w0) and graph HTML
(bare aura graph) regenerate sha256-identical (bcc2cc0f.., a0e6a97f..),
each deterministic across two generations. Suite 1043/0.
First half of the style pin: the asset becomes the single source the
runtime pages embed; tokens + component library follow separately.
refs #209
MILESTONE VERDICT: GREEN — the whole span (0106-0109) holds end to
end as one continuous consumer scenario: authored from a bare {} via
introspection alone, every ref resolved from the public surface, three
validation tiers, run by content id over two real instruments through
the full v2 pipeline, realization recorded (selection/survivors/
bootstrap/generalizations/trace_name), traces on disk and charted,
read back via campaign runs, byte-identical re-runs (C1), refusals
precise. 0 bugs, 0 frictions, 0 spec gaps; 2 doc-gaps.
F7 fixed in this commit (the docs claimed an archive-root path without
naming the key; a guessed [paths] archive silently no-ops): project-
layout and the glossary Aura.toml entry now name [paths] data, and the
aura new template advertises the commented-out key. F8 (op-script
grammar not CLI-discoverable) filed as #208, sibling of the #197 docs
half — one docwriter pass once desired.
The milestone-close gate evidence is this corpus; the formal milestone
close and the push remain user-reserved.
refs #189
The --unwired help line names the whole-envelope starting move (start
from a bare {}), closing the 0106-F1 discoverability gap the narrowed
issue kept open; the wrong-kind refusal names the exact key a blind
author must fix ('the "kind" key must be "process"') instead of
describing the mismatch abstractly. The third original item (block-ids
vs field names in --vocabulary) is sufficiently served by the
envelope probe per the issue's narrowing comment.
RED-first (tdd-author handoff): both pins observed failing on the old
help text / prose.
Gates: workspace 1043/0, clippy -D warnings clean.
closes#193
Architect verdict: drift_found — the code holds (C1 honored not
assumed: the nominee re-run's metrics-equality hard refusal; C22/C14
clean: existing TraceStore + unchanged viewer, serde-default widening
round-trips, name composition single-sourced in derive_trace_name).
Resolved here:
- C18: the 0107 paragraph's 'persist_taps is deferred' points forward;
new cycle-0109 realization paragraph records the closed tap
vocabulary + UnknownTap tier, the nominee-only non-reduce re-run
with the C1 metrics guard, the campaign trace family layout, the
trace_name claim contract, the loud-skip lines, and the noted
chart-over-family-root debt.
- Glossary: tap entry names the closed vocabulary + escalation rule;
campaign document's presentation clause references it; campaign run
gains the trace_name pointer.
- Debt fixed inline (architect med): tap_channel gains the
emit_vocabulary-twin debug_assert cross-pin so a fifth vocabulary
tap fails loudly instead of silently skipping.
The consumed 0108 fieldtest spec is removed with the cycle's spec+plan
(all its dispositions shipped: F6 #205, F8 #207, F11 #206, F7/F9/F10
doc-tightens).
Regression: cargo test --workspace 1041/0; clippy -D warnings clean;
cargo doc 0 warnings.
refs #201
The deferral line dies; persist_taps is honored: after execute()
returns with a claimed trace_name, the CLI re-runs each cell's nominee
once in non-reduce mode (all four channels drained; windowed to the
nominee manifest's own ns bounds; bound via the shipped
point_from_params inverse against the wrapped probe space), asserts
METRICS equality against the recorded nominee (the C1 drift alarm —
hard refusal on divergence), and writes the requested-and-producible
taps through the existing TraceStore as
traces/{campaign8}-{run}/{strategy8}-{instrument}-w{n}/{tap}.json
(ensure_name_free once; window ordinal doc-derived by position match).
Loud lines: per-cell no-nominee skip, per-run net_r_equity
unproducible skip (no cost leg in the campaign runner), one summary.
The Task-1(b) seam test tightened to pin the deferral line's absence.
Gated e2e extended: persist_taps [equity, r_equity] over GER40 —
trace_name in the record, both tap files on disk, aura chart reads
the cell back — ran its FULL path on this host (local archive
present), not the skip branch.
Gates: workspace 1041/0, clippy -D warnings clean.
closes#201
Task 1: the tap namespace is a closed vocabulary — tap_vocabulary()
(the wrap convention's four sink names; escalation = new entry or an
authored blueprint sink, never an open node-path namespace) with
DocFault::UnknownTap in validate_campaign (index-addressed, prose
enumerating the vocabulary via the single source), SlotKind::TapKinds
on the persist_taps slot, open-slot hint naming the taps. The 0107
deferral seam test split into its two 0109 pins (unknown tap refuses
at validate; a valid tap passes validate and hits the member-data
seam) — the deferral eprintln itself survives until task 3.
Task 2: CampaignRunRecord.trace_name lands serde-default sparse; the
claim contract holds across the seam — execute stamps the sentinel iff
persist_taps is non-empty, append_campaign_run composes
Some("{campaign8}-{run}") onto the stored line (safe prefix take at
the registry seam), execute mirrors the same derivation onto the
returned copy; None stays None; the hand-seeded byte-identity dump pin
survives (absent -> skipped).
Gates: workspace 1037/0, clippy -D warnings clean.
refs #201
4 tasks, strictly sequential: tap vocabulary + UnknownTap intrinsic
validation (deferral eprintln survives until task 3; the 0107 deferral
test splits into its two 0109 pins), trace_name widening + the
claim-sentinel name-composition contract across registry and executor,
persist_campaign_traces (nominee non-reduce re-run, metrics-equality
C1 guard, TraceStore member-dir writes, loud skips, deferral line
dies), gated e2e extension (trace files + chart read-back).
Drafted per-task against the live tree (3 authors); cross-task seams
verified in the notes: campaign_run.rs untouched by tasks 1-2 (task
3's fences stay valid), the task-1(b) test found by fixture not name,
tap->channel mapping verified against persist_traces_r, nominee params
bound from the report manifest via the shipped point_from_params
inverse, reduce/non-reduce metrics equality grounded in the shared
SeriesFold/GatedRecorder ledger construction.
refs #201
Cycle 0109, anchored on #201. Encodes the five swarm-triaged decisions
(#201 comment 2026-07-04; F1-F4 unanimous, F5 4/5 with dissent
recorded): closed tap vocabulary of the wrap convention's four sink
names (escalation = new vocabulary entry or authored blueprint sink,
never an open node-path namespace); nominee-only non-reduce re-run per
cell (bounded, C1/reproduce precedent, equality-asserted); the
existing TraceStore family-shaped under {campaign8}-{run}; wiring
consumer-side after execute() returns (MemberRunner stays one-method,
aura-campaign stays trace-agnostic bar a one-line name stamp);
CampaignRunRecord.trace_name as the one sparse pointer (the 0108-F10
navigability lesson). Seam refinement recorded: the run counter is
assigned in append_campaign_run, so the store write composes the name
from a claim sentinel — contract pinned, exact seam is the planner's.
Boss-signed via grounding-check PASS (11/11). Planner note carried
from the check: the re-run equality assert pins METRICS equality (the
C1 core) — manifest fields are fresh-context and not reconstructed
cross-mode.
refs #201
The recorded bootstrap/generalization evidence is no longer write-only:
'aura campaign runs' lists every stored record (campaign id, run
counter, cell count, first cell's stage signature); 'aura campaign
runs <id> [run]' dumps the BARE stored line(s) — the store form,
byte-identical, never the {"campaign_run": ...} run-emit wrapper (the
F10 parsing trap). A lookup, not an action: empty/unmatched notes and
exits 0 (the runs-family convention); outside a project the campaign
family's project refusal.
RED-first (tdd-author handoff): hermetic seed of one hand-written
store line into the fixture project, list + byte-identical dump pinned,
observed failing on clap's unknown-subcommand exit 2.
Gates: workspace 1027/0, clippy -D warnings clean.
closes#206
--metrics now tags the four generalizable names (expectancy_r,
net_expectancy_r, sqn, sqn_normalized) via check_r_metric as the
predicate — the registry's own R-expectancy rule, no fourth roster
site (#190). The GeneralizeNonRMetric refusal names the real rule
with the roster pointer instead of mislabeling R-denominated-but-
unranked metrics (max_r_drawdown is a drawdown in R, not a 'pip
metric').
RED-first (tdd-author handoff): the extended --metrics pins and the
flipped prose pins (unit + seam) observed failing on the old output.
Gates: workspace 1026/0, clippy -D warnings clean.
closes#207
valid == runnable for every pure document/campaign property: inside a
project, once intrinsic + referential pass, validate fetches the
referenced process from the store and runs the data-free
aura_campaign::preflight (promoted to pub) — an executable shape gains
'campaign document valid (executable): pipeline shape and static
guards pass'; a shape/param/metric/instrument fault refuses under
'campaign is not executable:' with the exec_fault_prose detail, exit 1,
before any member runs. Outside a project the skip line is unchanged
(the third tier needs the store like the second).
Collateral the RED author predicted: the referential e2e's OK fixture
(PROCESS_DOC: deflate+plateau sweep, overfit_probability gate) was
intrinsically-valid-but-never-executable — that test now registers an
executable twin (argmax/no-deflate, per-member gate metric); the base
PROCESS_DOC fixture stays untouched for all other consumers.
RED-first (tdd-author handoff): the third-tier pin observed failing on
the two-line validate output.
Gates: workspace 1026/0, clippy -D warnings clean.
closes#205
The std::monte_carlo block doc now names the position-dependent
semantics (pooled OOS after wf / per-survivor otherwise) and the > 0
execution guard the generic u32 slot hint could not carry; the
std::generalize block doc names campaign scope, the >= 2-instrument
need, and the R-expectancy metric family. Glossary: new 'stage
bootstrap' entry defines the realization payload incl. prob_le_zero;
the campaign-run entry gains the generalizations schema and the
stdout-wrapper-vs-bare-store-line note. Introspection text and
glossary only — no document content id moves.
Gates: workspace green, clippy clean.
refs #200
Verdict: honest, recorded, reproducible inference on top of the 0107
loop — pooled_oos provably pools the wf OOS windows (n_trades 948+895
= 1843), per_survivor flags a razor-thin gate-passer at
prob_le_zero 0.525 (the inference layer earning its keep), the
two-instrument std::generalize records worst_case/sign_agreement over
last-wf-window nominees, byte-identical across three runs modulo the
run counter, and all eight boundary probes refuse loudly at the right
tier. 0 bugs.
Triage: F1-F5 carry-on; F6 (campaign validate blesses
executor-unrunnable shapes — the third tier invisible) and F11 (no
CLI read-back for recorded realizations) filed as issues; F7/F9/F10
doc-tightens follow this commit inline; F8 (generalize R-metric set
undiscoverable + misleading refusal prose for R-denominated-but-
unranked metrics) filed with the --metrics tag half. The fieldtest
spec rides in docs/specs/ as next-cycle planner input per convention.
refs #200
Architect verdict: drift_found — the expected pre-audit doc lag; the
code holds (C1: doc-seeded bootstrap + BTreeMap-ordered generalize;
C14/C23 sparse widening pinned by the pre-0108-line parse test;
terminal-annotator dataflow confirmed — nothing flows out, no new
emit kind, no content-id movement). All items resolved here:
- C18: 0107's 'refuse loudly at preflight' points forward; new
cycle-0108 realization paragraph records the v2 shape, the
dual-input stage bootstrap, campaign-scope generalize, the tier
boundary (test-pinned on both sides), the record widenings, and
the stringly wf-detection debt.
- Glossary: campaign document -> v2 shape; bootstrap and Monte-Carlo
entries disambiguate the three senses (construction vs statistical
r_bootstrap vs seed axis — the std::monte_carlo stage IS the
trade-sequence bootstrap, named for r_bootstrap's arguments);
generalize gains the campaign-scope realization.
Regression: cargo test --workspace 1025/0; clippy -D warnings clean;
cargo doc 0 warnings. Spec + plan removed at close per convention.
closes#200
The retired v1-boundary test is replaced by v2 pins: mc-before-wf
refuses with the executor shape prose (while process validate accepts
the same doc — the tier boundary observable across two commands, added
by the task-2 e2e phase and kept), single-instrument generalize
refuses data-free on the built fixture project, and the two
addressing-mode tests' stale rationale comments now name the
member-data seam they actually hit. PROCESS_BLOCKS doc strings drop
'in v1' (introspection text only — no content id moves). The gated
real-data e2e extends its process with the monte_carlo suffix and
asserts the pooled_oos bootstrap in the final campaign_run line — ran
its full assert path on this host.
Task-5 duplicates the plan had double-drafted (task 2's e2e phase
pre-landed three of its tests) were correctly NOT re-added.
Gates: workspace 1025/0 (fully green again), clippy -D warnings clean.
refs #200
The mc arm bootstraps the stage's incoming R-evidence with one
semantics, input-shaped by position (#200 decision 1): after a
walk_forward it pools the wf family's per-window OOS trade_rs in roll
order into ONE r_bootstrap (PooledOos); after sweep/gates it
bootstraps each surviving member's fresh in-memory series
(PerSurvivor, ordinals into the population family; a zero-trade
member records the engine's defined all-zero degenerate). Seeded from
the campaign doc's seed (C1). The wf family is read by reference from
the cell's families vec — no clone. run_cell's Generalize arm is an
explicit no-op naming the campaign scope.
The generalize phase runs after the cell loop (#200 decision 2):
nominees (last wf window's OOS report, else the sweep winner; None on
gate truncation) grouped by (strategy, window) across instruments via
a BTreeMap (deterministic order); >= 2 winners feed the shipped
generalization(), fewer record the shortfall (generalization: None,
missing named) — divergent per-instrument winners are exposed via
their params, never averaged away.
Gates: campaign 40/0 (4 execute_mc + 3 execute_generalize new),
workspace build clean; the known-RED cli integration test flips in
task 5.
refs #200
Task 1: RBootstrap and Generalization gain serde derives;
lineage.rs gains StageBootstrap (per_survivor | pooled_oos) and
CampaignGeneralization; StageRealization.bootstrap and
CampaignRunRecord.generalizations land serde-default sparse (a
pre-0108 campaign_runs.jsonl line still parses — pinned), threaded
None/empty through every literal site. No behaviour change.
Task 2: ExecFault::UnsupportedStage is gone; the preflight now admits
the v2 shape sweep [gate]* [wf]? [mc]? [generalize]? via a monotone
rank walk (precise per-pair PipelineShape prose) and statically
refuses: single-instrument generalize (GeneralizeNeedsInstruments),
non-R generalize metrics via check_r_metric (GeneralizeNonRMetric —
no fourth roster site), zero mc params (ZeroBootstrapParam). CLI
prose swapped accordingly. The loop's E2E phase added a tier-boundary
pin: process validate accepts [sweep, mc, walk_forward] while campaign
run refuses it data-free.
KNOWN RED (documented in the plan, flips in task 5):
crates/aura-cli/tests/research_docs.rs::campaign_run_v1_boundary_refuses_mc_process
still pins the retired 'not executable in v1' prose. Interim gates:
registry 57/0, campaign 33/0, cli --bin 111/0, workspace build clean.
refs #200
Brummel