Architect verdict: drift_found — the code holds (C1 honored not
assumed: the nominee re-run's metrics-equality hard refusal; C22/C14
clean: existing TraceStore + unchanged viewer, serde-default widening
round-trips, name composition single-sourced in derive_trace_name).
Resolved here:
- C18: the 0107 paragraph's 'persist_taps is deferred' points forward;
new cycle-0109 realization paragraph records the closed tap
vocabulary + UnknownTap tier, the nominee-only non-reduce re-run
with the C1 metrics guard, the campaign trace family layout, the
trace_name claim contract, the loud-skip lines, and the noted
chart-over-family-root debt.
- Glossary: tap entry names the closed vocabulary + escalation rule;
campaign document's presentation clause references it; campaign run
gains the trace_name pointer.
- Debt fixed inline (architect med): tap_channel gains the
emit_vocabulary-twin debug_assert cross-pin so a fifth vocabulary
tap fails loudly instead of silently skipping.
The consumed 0108 fieldtest spec is removed with the cycle's spec+plan
(all its dispositions shipped: F6 #205, F8 #207, F11 #206, F7/F9/F10
doc-tightens).
Regression: cargo test --workspace 1041/0; clippy -D warnings clean;
cargo doc 0 warnings.
refs #201
4 tasks, strictly sequential: tap vocabulary + UnknownTap intrinsic
validation (deferral eprintln survives until task 3; the 0107 deferral
test splits into its two 0109 pins), trace_name widening + the
claim-sentinel name-composition contract across registry and executor,
persist_campaign_traces (nominee non-reduce re-run, metrics-equality
C1 guard, TraceStore member-dir writes, loud skips, deferral line
dies), gated e2e extension (trace files + chart read-back).
Drafted per-task against the live tree (3 authors); cross-task seams
verified in the notes: campaign_run.rs untouched by tasks 1-2 (task
3's fences stay valid), the task-1(b) test found by fixture not name,
tap->channel mapping verified against persist_traces_r, nominee params
bound from the report manifest via the shipped point_from_params
inverse, reduce/non-reduce metrics equality grounded in the shared
SeriesFold/GatedRecorder ledger construction.
refs #201
Cycle 0109, anchored on #201. Encodes the five swarm-triaged decisions
(#201 comment 2026-07-04; F1-F4 unanimous, F5 4/5 with dissent
recorded): closed tap vocabulary of the wrap convention's four sink
names (escalation = new vocabulary entry or authored blueprint sink,
never an open node-path namespace); nominee-only non-reduce re-run per
cell (bounded, C1/reproduce precedent, equality-asserted); the
existing TraceStore family-shaped under {campaign8}-{run}; wiring
consumer-side after execute() returns (MemberRunner stays one-method,
aura-campaign stays trace-agnostic bar a one-line name stamp);
CampaignRunRecord.trace_name as the one sparse pointer (the 0108-F10
navigability lesson). Seam refinement recorded: the run counter is
assigned in append_campaign_run, so the store write composes the name
from a claim sentinel — contract pinned, exact seam is the planner's.
Boss-signed via grounding-check PASS (11/11). Planner note carried
from the check: the re-run equality assert pins METRICS equality (the
C1 core) — manifest fields are fresh-context and not reconstructed
cross-mode.
refs #201
The std::monte_carlo block doc now names the position-dependent
semantics (pooled OOS after wf / per-survivor otherwise) and the > 0
execution guard the generic u32 slot hint could not carry; the
std::generalize block doc names campaign scope, the >= 2-instrument
need, and the R-expectancy metric family. Glossary: new 'stage
bootstrap' entry defines the realization payload incl. prob_le_zero;
the campaign-run entry gains the generalizations schema and the
stdout-wrapper-vs-bare-store-line note. Introspection text and
glossary only — no document content id moves.
Gates: workspace green, clippy clean.
refs #200
Verdict: honest, recorded, reproducible inference on top of the 0107
loop — pooled_oos provably pools the wf OOS windows (n_trades 948+895
= 1843), per_survivor flags a razor-thin gate-passer at
prob_le_zero 0.525 (the inference layer earning its keep), the
two-instrument std::generalize records worst_case/sign_agreement over
last-wf-window nominees, byte-identical across three runs modulo the
run counter, and all eight boundary probes refuse loudly at the right
tier. 0 bugs.
Triage: F1-F5 carry-on; F6 (campaign validate blesses
executor-unrunnable shapes — the third tier invisible) and F11 (no
CLI read-back for recorded realizations) filed as issues; F7/F9/F10
doc-tightens follow this commit inline; F8 (generalize R-metric set
undiscoverable + misleading refusal prose for R-denominated-but-
unranked metrics) filed with the --metrics tag half. The fieldtest
spec rides in docs/specs/ as next-cycle planner input per convention.
refs #200
Architect verdict: drift_found — the expected pre-audit doc lag; the
code holds (C1: doc-seeded bootstrap + BTreeMap-ordered generalize;
C14/C23 sparse widening pinned by the pre-0108-line parse test;
terminal-annotator dataflow confirmed — nothing flows out, no new
emit kind, no content-id movement). All items resolved here:
- C18: 0107's 'refuse loudly at preflight' points forward; new
cycle-0108 realization paragraph records the v2 shape, the
dual-input stage bootstrap, campaign-scope generalize, the tier
boundary (test-pinned on both sides), the record widenings, and
the stringly wf-detection debt.
- Glossary: campaign document -> v2 shape; bootstrap and Monte-Carlo
entries disambiguate the three senses (construction vs statistical
r_bootstrap vs seed axis — the std::monte_carlo stage IS the
trade-sequence bootstrap, named for r_bootstrap's arguments);
generalize gains the campaign-scope realization.
Regression: cargo test --workspace 1025/0; clippy -D warnings clean;
cargo doc 0 warnings. Spec + plan removed at close per convention.
closes#200
5 tasks, strictly sequential: record widenings + serde derives
(workspace-green), preflight v2 + fault-set swap (leaves ONE known-RED
aura-cli integration test, documented loudly, flipped by task 5;
interim gates exclude the aura-cli integration targets), the mc stage
arm (dual-input bootstrap), the campaign-scope generalize phase
(nominee threading), CLI seam flips + doc tidy + gated e2e extension
restoring full workspace green.
Drafted per-task against the live tree (4 authors), assembled with two
reconciliations: the task-2 typo-trap fence replaced by its
authoritative form (plans carry only literally-applicable bytes), and
task 4's old-quote aligned to task 1's record-literal bytes (comment
lines included). Cross-task byte seams verified: task 3 quotes the
pre-task-2 unreachable-arm (task 2 does not touch exec.rs); task 5
pins the prose task 2 defines (substrings verified compatible).
refs #200
Cycle 0108, anchored on #200. Encodes the five swarm-triaged decisions
(#200 comment 2026-07-03, all convergent on cited ground, no bounce):
std::monte_carlo bootstraps the stage's incoming R-evidence (per-survivor
after sweep/gates, pooled per-window OOS series after walk_forward) via
the shipped r_bootstrap; std::generalize runs at campaign scope over
per-cell nominees per (strategy, window); both stay terminal annotators
(unanimous); realization widens existing records (StageRealization.bootstrap,
CampaignRunRecord.generalizations, serde-default); v2 executable shape
sweep [gate]* [wf]? [mc]? [generalize]? with static preflight guards.
No document-schema bytes move — every existing content id survives.
Boss-signed via grounding-check PASS (11/11). The first dispatch
BLOCKed on one unpinned current-behaviour assumption ([sweep, mc,
walk_forward] passes the intrinsic tier); the gap was closed by the
green characterization test
validate_process_permits_walk_forward_after_an_annotator (pins the
intrinsic/executor tier boundary), and the fresh re-dispatch ratified
all eleven assumptions.
refs #200
Architect verdict: drift_found — the code holds its contracts (C1
determinism incl. lowest-index fault attribution and doc-seeded
deflation; C16 seam: aura-campaign excludes ingest/std/composites,
MemberRunner isolates the condemned CLI scaffolding; the walk_forward
lockstep set moved together), the docs lagged the tree. All six drift
items resolved in this commit:
- C18: 'no executor exists' retired (0106 text now points forward);
new cycle-0107 realization records the executor, the aura-campaign
home, ListSpace, the campaign_runs.jsonl sibling store, zero-survivor
exit-0 semantics, emit/persist_taps split, the #196 on-ramp, and the
machinery-true std::walk_forward correction.
- C16: aura-campaign added to the non-node crate enumeration
(cycle-0107 realization; explicitly not C21's World).
- Glossary: campaign document entry corrected (run verb, execution
prose); new 'campaign run' entry; blueprint entry gains the on-ramp
verbs.
Carry-on debt (self-noted in code, tracked): metric-roster
triplication #190, deflation-constant duplication #199; cross-cell
fault orphans + nested-parallelism oversubscription noted in the
tasks-6-7 commit body. Follow-ups filed on the milestone: #200
(mc/generalize stage execution), #201 (persist_taps wiring).
Regression: cargo test --workspace 987/0; clippy -D warnings clean;
cargo doc 0 warnings. Spec + plan removed at close per convention
(durable rationale lives in the ledger; the canonical record is the
git history).
closes#198
Cycle 0107, anchored on #198 (campaign executor; #196 blueprint on-ramp
rides along). Encodes the twelve decisions recorded on #198: eleven from
the fork triage (2026-07-03) plus the user-decided executor home (a new
library crate, 2026-07-03). Scope: aura-campaign library crate
(MemberRunner seam, execute, gate evaluation, preflight, realization
assembly), std::walk_forward vocabulary correction to machinery-true
fields, engine ListSpace, registry CampaignRunRecord + campaign_runs
store, CLI campaign-run verb + driver, #196 on-ramp verbs.
Boss-signed via grounding-check PASS (17/17 load-bearing assumptions
ratified against currently-green tests). One construction note carried
to the plan: a private Registry::blueprint_path already exists and is
promoted to public rather than duplicated.
refs #198, refs #196
C25 (new): the nine authoring roles cut by artifact + surface + iteration
cost, the recognizability test, the 6a/6b split on invariant 12's tier
boundary with the id machinery as interface, the text-first/headless-first
invariant (visual surfaces = stateless projections, viewers over editors),
and the Blockly litmus test as every vocabulary's acceptance criterion.
C20: the 'plain Rust loops, not a config schema' clause and the mini-DSL
forbid are scoped — they forbid an open logic-bearing language, not the
closed-vocabulary campaign document that now carries experiment intent
under the P1 construct tier; generators may stay Rust, what they yield is
data.
C22: stateless-projection refinement generalized to all artifact classes;
the shipped face recorded as the web-from-disk front. Glossary playground
entry aligned (the egui-native wording was stale against the 2026-06
revision).
CLAUDE.md invariant 10: clarified that closed-vocabulary data artifacts
(op-scripts, blueprints, process/campaign documents) are not the forbidden
DSL — RustAst failed as an open logic-bearing language; new logic
escalates to a Rust block, never a freetext hole.
All content ratified on #188 (body + addenda + resolution comments); this
commit is production of the durable record, no new design.
closes#192
Architect drift review (holds: C14 headless authoring, C16/C17 no-DSL with
aura-research a true leaf, content-id move behaviour-preserving per the
untouched id goldens). Resolution per item:
- fix (docs): C18 gains the cycle-0106 realization note (processes/ +
campaigns/ stores, document canonical form, the content-id primitive's
library home, the referential tier, no-executor status); the #109
analysis-meta-level open thread records the artifact half shipped v1 and
what stays open (executor question, verb dissolution 'once it carries',
the remaining #188 amendment package). Glossary: new campaign document +
process document entries; content id generalized to all three artifact
classes; experiment marked superseded by the campaign document (#188
re-cut of the builder-API thread).
- fix (code): the --unwired guide advertised an identity_id process ref
that validate_campaign refuses — the process.ref open-slot hint now says
content-id-only (strategy refs keep both); lib + seam pins updated.
- filed forward: #190 (metric-vocabulary single-sourcing, the 0105 roster
drift class), #191 (identity-ref store scan is O(store), performance
only).
- carry-on: regression gates green by hand — cargo test --workspace 916/0,
clippy -D warnings clean, cargo doc --no-deps 0 warnings; no baseline to
ratify (project has no metric baseline scripts).
Cycle 0106 spec and plan retired per convention (git rm); durable record
is the ledger notes above plus #188/#189.
refs #189
New research_docs.rs module: role-addressed process verbs with house-style
fault prose (Display-free enums phrased at the seam), the introspect
exactly-one-of usage guard (exit 2), and content-addressed registration.
Seven binary seam tests pin intrinsic-ok/refusal prose, vocabulary/block/
unwired/content-id introspection, exit codes, and the stored file's
location under the runs root.
Quality-gate finding folded in (and back into the plan): register no
longer re-derives the store path from runs_root — aura-registry now
exposes process_path/campaign_path, the same single mapping its put/get
pair routes through, so the printed path cannot drift from the store
layout.
Verification: research_docs seam tests 7/0, registry 49/0, clippy clean.
refs #189
The aura-research leaf crate: ProcessDoc/CampaignDoc with strict parsing
(hand-rolled StageBlock deserializer — deny_unknown_fields does not compose
with internally-tagged enums; Axis declares its ScalarKind once with bare
values, per the #189 user veto), canonical form + content_id_of (the
SHA-256 primitive moved from aura-cli, which now delegates — the id pin set
incl. the independent sweep-store recompute stayed green untouched),
intrinsic validation for both document types (P1 constraints structural),
and the introspection contract (schema tables single-source parse
strictness AND vocabulary/describe/open-slots — the Blockly litmus made
checkable). aura-registry: content-addressed processes/ + campaigns/
stores on the blueprint-store pattern (Ok(None) treat-as-empty) and the
referential tier (validate_campaign_refs: process/strategy refs incl.
identity-scan, axis-name + declared-kind checks against param_space).
Plan deviations, verified by hand and folded back into the plan file:
- Task 9's fixture could not use aura-composites as planned: every shipped
composite with an open param routes through LinComb, which the zero-arg
std_vocabulary roster deliberately excludes, so none round-trips through
blueprint_from_json with the by-type-name resolver. The test hand-builds
a minimal Bias composite instead (generic over param_space, as planned);
the unused pro-forma aura-composites dev-dep from the repair pass is
dropped. This is why the loop reported task 9 BLOCKED
(review-loop-exhausted on the literal code block); the tree itself is
complete and green.
- A plan-verbatim test assertion false-matched ("deflate" as substring of
"deflated-positive"); tightened to the JSON key.
- OpenSlot doc comment backticked (rustdoc read strategies[0] as a link;
doc gate back to 0 warnings).
Verification: cargo test --workspace 898/0; clippy -D warnings clean;
cargo doc --no-deps 0 warnings. Tasks 10-12 (CLI verb families, final
gates) follow.
refs #189
User veto (2026-07-03) of the per-cell tagged Scalar draft: the kind is a
property of the parameter, not of each value. An axis is now
{"kind": "I64", "values": [8, 12, 16]} — mixed-kind axes are
unrepresentable, canonical form normalizes value spelling, and the
referential kind check is one comparison per axis. Op-script binds keep
their tagged form (single-value slots). Decision log: #189.
refs #189
The campaign example wrote bare JSON numbers in the axes while the spec's
own typed-cell clause (op-script bind parity) requires the tagged Scalar
wire form. Example now matches the clause; no assumption changed.
refs #189
Two doc-tightenings from the green milestone fieldtest (F3, F6 in
fieldtests/milestone-project-environment/FINDINGS.md): the glossary
manifest entry now names the topology hash and the project provenance
block {namespace, dylib_sha256, commit} a project-hosted run carries;
project-layout.md's Aura.toml annotation now matches what the scaffold
actually emits today ([paths] runs only — the data archive root joins
once real data enters).
refs #180
Resolves the #181 design pass (option c: ledger declaration, no lockstep
mechanism). The aura-new templates (scaffold.rs) are the canonical
authoring shape and evolve with the engine; the cycle-0102 demo-project
fixture is an intentionally frozen known-good twin for the load-boundary
tests. Deliberately NOT lockstep-guarded: no consumer requires the copies
to match (skeptic-verified — nothing treats the fixture as what aura new
emits), each is e2e-guarded on its fitness for purpose (build/load/
charter/deterministic run; blueprint wiring is pinned in neither, stated
honestly after an adversarial skeptic pass refuted the stronger claim),
and an equality guard would convert deliberate template improvements into
forced churn of the frozen fixture — the same cross-purpose coupling that
rules out regenerating the fixture from the scaffolder.
closes#181, refs #180
Architect drift review (range 7b429f9..57f401f): drift_found (low/medium
only), resolved inline as close-fixes:
- crates/aura-std/src/vocabulary.rs — the roster-site doc now names BOTH
count pins a node addition trips (the in-crate shape test and aura-cli's
cross-boundary --vocabulary count e2e); the singular phrasing understated
the cross-crate lockstep the extra e2e introduced.
- docs/design/INDEX.md — the C24 enforcement-shift passage gains the 0105
delivery note: resolver-vs-list drift closed by construction via the
roster macro; the un-rostered-node residual stays fail-safe.
Noted, no action: spec/plan predicted 884 (no new test) but delivery added
one e2e (885) — consciously superseded, disclosed in the iter commit body;
the artifacts are ephemeral and removed below.
What holds (architect): byte-preserving refactor confirmed against the
diff (22 keys/order exact, signatures and module doc untouched, every
consumer unchanged); invariant 9 / C24 preserved (compile-time expansion,
no registry); the new e2e count pin is genuinely roster-tied.
Regression gates (all green): cargo build clean; cargo test --workspace
885 passed / 0 failed (884 baseline + 1 new e2e); clippy --all-targets
-D warnings clean; cargo doc --no-deps 0 warnings.
Ephemeral cycle artifacts removed per project convention (git rm):
docs/specs/0105-std-vocabulary-roster-macro.md,
docs/plans/0105-std-vocabulary-roster-macro.md.
refs #180
Two tasks: (1) the private std_vocabulary_roster! macro + single 22-key
invocation replacing the two hand-written fns in aura-std/vocabulary.rs
(byte-identical signatures/keys/order; docs generated with the fns), plus
the two unit tests reshaped to iterate the generated list instead of
carrying an inline roster copy (oracle: PrimitiveBuilder::label(); count
pin kept as deliberate friction); (2) full regression — suite green
UNCHANGED at 884 (no test added or removed).
Recon-verified isolation: lib.rs re-export untouched (private in-module
macro, same pub fns), no other roster copy anywhere in the workspace, no
doc/ledger reference stales, first macro_rules in the crate, no
missing_docs gate.
refs #180, refs #160
Boss-signed via grounding-check PASS (fresh-context agent): all seven
load-bearing current-behaviour assumptions ratified by named green tests —
the two vocabulary unit tests (label round-trip + negatives; count==22 +
non-members), the PrimitiveBuilder::label() oracle, and the four consumer
pins (graph introspect --vocabulary e2e, engine loader UnknownNodeType,
the 0102 merged-vocabulary charter suite, the canonical golden).
Design basis: the mechanism recorded on #160 (declarative macro as single
source for resolver match + enumerable list) plus the cycle-0105
reconciliation comment there (single pair-generating invocation; the
test's inline roster copy replaced by iterating the generated list with
label() as independent oracle; the un-rostered-node residual accepted as
fail-safe and documented; public surface byte-identical).
refs #180, refs #160
Four tasks: (1) engine identity projection — factor build_doc/serialize_doc
out of blueprint_to_json (byte-preserving, guarded by the canonical golden),
add blueprint_identity_json + strip_debug_symbols + 4 property tests
(renamed twins, openness, bound values, edge swap); (2) CLI --identity-id
sibling flag — composite_from_str factored out of build_from_str, the
exactly-one introspect dispatch deliberately relaxed so the two id flags
combine (one build, both ids, content id first), plus the in-crate
cross-path twin test (Rust sma_signal vs op-script twin: distinct content
ids, one identity id — placed beside the existing cross-surface pins since
sma_signal is private to the bin); (3) four e2e tests incl. the previously
uncovered count!=1 usage path; (4) full regression (873 -> 882 expected).
Plan-recon corrections folded in: the spec sketch's BlueprintData does not
exist — the real DTO is CompositeData; engine re-export + CLI import are a
lockstep pair.
refs #180, refs #171
Boss-signed via grounding-check PASS (fresh-context agent): all five
load-bearing assumptions about current behaviour are ratified by named
currently-green tests — the byte-canonical golden
(signal_serializes_to_canonical_golden), the --content-id CLI contract
(graph_introspect_content_id_is_deterministic_and_distinguishes and the
bad-document refusal), the three topology_hash roles (introspect
content id, blueprint-store round-trip key, reproduce fetch anchor —
each with its own green test), the I64:4-vs-5 distinguishing property,
and the bound-array openness encoding (bound slot textually present,
open slot absent).
Design carried from the #171 reconciliation (adversarially reviewed):
the identity hash is an additive SIBLING of topology_hash —
introspection-only this cycle, no manifest field, no store key; the
byte-canonical form and every consumer of it stay byte-for-byte
untouched. Reviewer note carried to planning: allowing --content-id
and --identity-id together relaxes the current exactly-one flag
dispatch in graph_construct.rs — the usage tests must be adjusted
deliberately, not incidentally.
refs #180, refs #171
Architect review of b672a37..HEAD. What holds: emitted templates match
the settled contracts (Aura.toml paths-only per C17, cdylib + empty
[workspace] per C16, ::-namespaced ids per the charter, the C14 exit
partition in dispatch_new); the load-bypass guard is narrow and sound
(only the new-project verb exempted, the load arm byte-unchanged for
every other verb); e2e coverage is real (scaffold -> build -> run twice
byte-identical, namespace stamped, introspection, four refusals, the
unbuilt-tree bypass, plus the additive namespace-override test).
Regression: cargo build --workspace rc=0; cargo test --workspace 873
passed / 0 failed (project_new 6/6); clippy --workspace --all-targets
-D warnings rc=0; cargo doc --workspace --no-deps 0 warnings. No
baselines exist to move, so nothing to ratify.
Drift resolved in this commit: three doc mirrors still framing the
scaffolder as future — project-layout.md's 'the future aura new
scaffolder will emit this line; until then, add it by hand', the C24
status paragraph's 'what remains open is the aura new scaffolder (the
milestone's next cycle)', and the #109 open-thread bullet's 'the aura
new scaffolder and the experiment-builder API remain open' — all
rewritten to the landed reading (only the experiment-builder API stays
open in that layer).
Carried debt, filed forward: the scaffold templates and the
demo-project fixture encode one project shape twice with no lockstep
guard and deliberate cosmetic divergences (#181, idea — needs a design
pass, not a mechanical edit).
Process note: one mid-cycle plan-fix commit (derive(Debug) on a
plan-prescribed struct whose own test code required it) — the
implement loop's spec gate correctly blocked the necessary deviation;
resolution followed the fix-plan/commit-subset/re-run path.
Ephemeral cycle artifacts removed per convention: spec 0103, plan 0103.
refs #180
The Task-1 unit tests call unwrap_err() on Result<ScaffoldSpec, String>,
which requires ScaffoldSpec: Debug; the prescribed struct lacked the
derive, so the plan's own bytes could not compile. The implement loop
correctly blocked on the necessary deviation (spec-compliance holds
verbatim plan code); this aligns the plan with the only compiling form.
refs #180
Grounding-check PASS as the autonomous signature: 8 load-bearing
current-behaviour assumptions each ratified by a named green test
(the templates are the cycle-0102 fixture verbatim, itself e2e-green);
greenfield scaffolder surfaces excluded per contract. Fork decisions:
the cycle-0103 reconciliation comment on the milestone reference issue.
refs #180
Architect review of d7c935d..HEAD. What holds: C13/C16 separation
verified by diff (descriptor in aura-core::project, loader entirely in
aura-cli::project, aura-engine gains only the additive provenance
field); the C-tier-before-Rust-tier discipline is enforced in load()
(magic -> version -> stamps, fn pointers touched only after Ok);
C17/C24/invariant-9 hold (paths-only Aura.toml, injected merged
resolver, charter at the one seam); outside-a-project byte-identity
confirmed by the full green suite incl. every golden-bearing test.
Regression: cargo build --workspace rc=0; cargo test --workspace 862
passed / 0 failed (cli_run 133, project_load 7 e2e); clippy
--workspace --all-targets -D warnings rc=0; cargo doc --workspace
--no-deps 0 warnings. No baselines exist to move, so nothing to
ratify.
Drift resolved in this commit: two stale project-as-crate ledger
mirrors — the C24 status paragraph still calling the layer
sequencing-coupled/unbuilt, and the #109 open-thread bullet naming it
an unbuilt half — rewritten to record the landed load boundary (the
aura new scaffolder and the experiment-builder API stay open).
Carried holds (plan-prescribed bytes, cosmetic): the unreachable
rsplit fallback in node_name, the unreachable! build closure in one
aura-core test.
Ephemeral cycle artifacts removed per convention: spec 0102, plan 0102.
refs #180
A research project is now a loadable external cdylib crate. Inside a
directory whose ancestry holds an Aura.toml, aura discovers the project
root cargo-style, locates the compiled dylib via cargo metadata (debug
default, --release opt-in), loads it load-and-hold, and refuses
mismatches before trusting anything: the AURA_PROJECT descriptor
(aura-core::project, #[repr(C)]) carries a C-ABI stamp prefix (rustc +
aura-core version, baked per consuming build by the new aura-core
build.rs) validated before any Rust-ABI field is read. The vocabulary
charter gates the merged resolution: project type ids are ::-namespaced
(std stays bare), duplicates refuse, and the enumerable type-id list
must agree with the resolver, so introspection can never silently omit
a project type.
All blueprint verbs resolve through the merged project + std vocabulary
via a per-invocation Env threaded through the dispatch chains;
registry, trace-store, and data paths anchor at the project runs root
(Aura.toml [paths], paths-only by design — instrument geometry stays
the recorded sidecar, C15). RunManifest gains the Tier-1 project
provenance field (namespace + dylib sha256 + best-effort commit),
stamped beside topology_hash on the blueprint-run paths; pre-0102
registry lines load unchanged. Default node names strip the namespace,
so :: never reaches the param-path address space.
Proven by the demo-project fixture (built by the e2e via cargo,
path-dep on this workspace): run twice bit-identical, provenance
recorded, introspection lists demo::* beside std, registry anchors at
the discovered root from a subdirectory; the badcharter fixture proves
the charter refusal through the real libloading path; a never-built
project refuses with a cargo-build hint. Outside a project every path
collapses to the previous literals — goldens and manifest pins
byte-identical.
Verification: cargo build --workspace clean; cargo test --workspace 862
passed / 0 failed (incl. 7 project_load e2e); clippy -D warnings clean
(one precedent-matching allow(too_many_arguments) on run_oos_blueprint,
whose arity the Env threading raised to 8); doc build unchanged.
Docs/ledger aligned: Aura.toml field lists are paths-only in
project-layout.md, glossary, C16/C17; new C13 realization note records
the per-invocation-reload reading and the load-and-hold one-shot scope
boundary.
New deps, per-case review (aura-cli leaf binary only, never the frozen
artifact): libloading, toml.
refs #180
Grounding-check PASS as the autonomous signature: 7 load-bearing
current-behaviour assumptions each ratified by a named green test;
greenfield surfaces (descriptor, loader, Aura.toml) excluded per
contract. Design decisions and provenance: the decision-log on the
milestone reference issue.
refs #180
Architect review of 8814e295..HEAD. What holds: the cosmetic-only claim is
verified (every -/+ pair in the code diff is a string literal; no exit(),
channel, or control-flow byte moved; the C14 usage=2/runtime=1 partition
preserved at every touched site); grep gates exact (zero lowercase usage:
literals, 11 'Usage: aura' source lines = 10 edited + the pre-conforming
run_args_from); fieldtests corpus and refusal diagnostics byte-identical.
The recorded spec deviation (3 additive house-style pins) strengthens
coverage over a real pin gap and is decision-logged on the issue.
Regression: cargo build rc=0, cargo test --workspace rc=0 (cli_run 133
passed / 0 failed), clippy -D warnings rc=0, doc build rc=0. No baselines
exist to move, so nothing to ratify.
Drift resolved in this commit: the C14 ledger note still described the
casing normalization as deferred after #179 landed - rewritten to record
the landed house style (usage lines 'Usage: aura <verb> ...', refusal
diagnostics deliberately unprefixed).
Ephemeral cycle artifacts removed per convention: spec 0101, plan 0101.
refs #179
One lockstep task: 10 byte-exact literal edits (6 lowercase usage: flips,
4 bare closures gain the 'Usage: aura ' prefix, mc built-in gets the program
name in both alternatives) + the single casing-sensitive pin flip in
cli_run.rs, then build / targeted test / full suite / clippy / grep gates /
diff-shape gate / sweep smoke.
refs #179
Single house style for every hand-rolled usage line: 'Usage: aura <verb> ...'
(clap's capital prefix + program name), 10 literal edits + the one
casing-sensitive test pin in lockstep. Refusal diagnostics, the conforming
run_args_from site, clap output, and the fieldtests corpus stay byte-identical.
Grounding-check PASS is the autonomous signature; scope-fork decisions are
recorded on the issue.
refs #179
Architect review of 88e9c9a..HEAD. What holds: token purity of the rename
(removed + mapping == added, 33 sanctioned prose rewordings, numeric golden
bytes untouched); CLAUDE.md invariant 7 now matches the ledger C10 section
clause-by-clause; no silent alias for the old selectors (unknown-selector
exit-2 path is tested).
Regression: cargo build / clippy -D warnings / doc build clean; cargo test
--workspace rc=0, 51 targets, 0 failures. No baselines exist to move, so
nothing to ratify.
Drift resolved in this commit: the C10 terminology note (INDEX.md) still
called Stage-1 a surviving identifier name after the glossary recorded the
rename - aligned to name the r-family rename (#174). Remaining low items:
the spec's own survivor-list contradiction was ratified and recorded on the
issue; the RGrid const-seeding debt is recorded on the harness-retirement
issue (refs #159).
Ephemeral cycle artifacts removed per convention: spec 0100, plan 0100, and
the spent prior-milestone fieldtest spec.
refs #174
The stage1 ordinal has been dead vocabulary since the C10 reframe dropped
the two-stage research model: a 1 structurally implies a 2 that no longer
exists. The family is renamed by its live discriminator - the R yardstick -
with members named by their signal, uniform with their signal-named
siblings (sma, macd, momentum):
- selectors: stage1-r -> r-sma, stage1-breakout -> r-breakout,
stage1-meanrev -> r-meanrev (old tokens are usage errors, exit 2 - no
silent alias)
- identifiers: Strategy::RSma/RBreakout/RMeanRev, HarnessKind::RSma,
r_sma_*/r_breakout_*/r_meanrev_*, wrap_r, run_signal_r, RGrid, R_SMA_*
- persisted identity: the sma_signal composite (param prefix
sma_signal.fast.length / .slow.length; fixtures regenerated; content-ids
shift - no test pins a literal hash, the registry parses no record names)
- e2e test files git-mv'd to r_sma_e2e / r_breakout_e2e / r_meanrev_e2e
- dead Stage-1/Stage-2 prose reworded to post-C10 vocabulary across
rustdoc, Cargo.tomls, ledger live lines, and the glossary (historical
entries stay; fieldtests corpus untouched)
- CLAUDE.md invariant 7 rewritten to record the ratified C10 reframe
faithfully (the token-swap alone would have laundered the retired
gated-currency/realistic-broker design into unmarked live prose); the
unbacked account-mode clause dropped
Verification: cargo build/test --workspace green (51 targets), clippy
-D warnings clean, doc build clean, acceptance grep gate leaves exactly
the one resampling-stage false positive (harness.rs), smoke: --harness
r-sma runs, --harness stage1-r exits 2 with the new usage line.
Decision log: forks and rationale recorded on the issue (reconciliation
+ implementation-phase comments).
closes#174
Five ordered tasks: aura-cli source + include_str-coupled fixtures, the
cli_run suite, engine e2e git-mvs + doc-refs, dead-ordinal prose across
rustdoc/CLAUDE.md/glossary/ledger live lines, and a workspace grep gate.
Substitutions are ordered longest-token-first; every task carries its own
verification gate.
refs #174
The stage1 ordinal is dead vocabulary since the C10 reframe; the spec
renames the selector/identifier family to r-sma / r-breakout / r-meanrev
(signal-named members under the R-yardstick marker), reworders dead
Stage-1/Stage-2 doc prose, and pins the survivors (history, fieldtests).
Signed autonomously under /boss on the grounding-check PASS; fork
decisions recorded on the reference issue.
refs #174
Three polish items surfaced by the World/C21 milestone fieldtest:
- A sweep of a fully-bound (closed) blueprint is refused up front with a clear
"this blueprint is fully bound; nothing to sweep" message — the symmetric
inverse of blueprint_mc_family's closed-blueprint guard — instead of leaking a
misleading UnknownKnob for a knob that is not unknown but bound out.
blueprint_sweep_family's error contract widens to String; the sweep terminal's
BindError (a genuine unknown/kind-mismatch axis) still surfaces verbatim.
- mc reproduce lines now carry each member's seed=<N> label. Monte-Carlo members
hold no tuning params, so the member label was blank; the seed is each draw's
realization identity. Sweep / walk-forward labels (which echo params) unchanged.
- docs (design ledger + glossary): state that every open knob --list-axes prints
is mandatory on sweep / walkforward — a subset is refused with the missing knob
named (BindError::MissingKnob), there is no default; pin a knob you do not want
to vary with a single-value axis.
RED-first for the two behaviour items. One existing unknown-axis E2E is re-pointed
from the closed fixture (which now hits the new "nothing to sweep" pre-check) to
the open fixture; it still exercises UnknownKnob("nope") specifically — resolve
raises UnknownKnob in phase 1 before MissingKnob in phase 2 — so the property is
preserved, not weakened.
closes#178
Architect drift review (scope 780d823..HEAD, the sole gate — no regression
script) returned one medium ledger-gap, now resolved; otherwise drift-clean with
a positive What-holds:
- invariant 8 / C16 engine-domain separation preserved: clap is confined to
crates/aura-cli/Cargo.toml; the whole diff touches only aura-cli/ + Cargo.lock
+ ephemeral docs; no engine/std/composites/analysis/registry/core/ingest crate
mentions clap, so the frozen deploy artifact structurally cannot pick it up
(aura-cli is a leaf binary). The 16 new lock entries are exactly clap's tree.
- C16 per-case admission honest: clap admitted with a documented rationale at the
Cargo.toml site (replaces the hand-rolled parser + ten help surfaces; dev-loop
tax, not frozen-artifact tax), the same admission form as sha2/libc.
- C14 automation-face served, execution layer intact: the usage=2/runtime=1
partition, scoped --help, --version, and GNU flags match the spec; the domain
fns keep their signatures (arg-plumbing via thin *_from adapters); new
behaviour is pinned (partition property test, version, scoped-help, dual-grammar
stray-positional guard).
Ledger refreshed: the C14 realization block now records the clap adoption + the
exit-code partition (usage=2/runtime=1) as a durable automation contract, before
the ephemeral spec that first stated it is removed (the drift item the architect
raised).
Deferred/forward: error-message casing normalization (#179, idea); the
machine-first help surface stays on the #157/C21 track (Fork B settled this cycle
as human/GNU convention compliance).
Verified green (orchestrator, this session): cargo build --workspace clean; cargo
clippy --workspace --all-targets -- -D warnings clean; cargo test --workspace
green. Cycle drift-clean.
closes#175
Iteration-2 plan for #175: apply the clean exit-code partition (deviation #8) on top of the clap migration — runtime failures exit 1, usage errors exit 2, no same-class inconsistency. Uses the attribution principle (command-line fault = 2, missing-environment/bad-stdin = 1) to resolve the 6 boundary cases the spec under-specified. refs #175
Iteration-1 plan for #175: replace the hand-rolled aura-cli argv parser with a
clap derive parser (scoped `aura <sub> --help`, `--version`/`-V`, per-flag
Options section, `--flag=value`/`--`/long-opt abbreviation), behaviour-preserving
on exit codes. Task 1 adds clap + RED tests for the new behaviour; Task 2 is the
atomic migration + renegotiation of the help/usage pins the migration inverts
(the four dual-grammar subcommands mapped as optional [blueprint] positional +
post-parse is_file() dispatch; execution layer untouched). The exit-code split
is iteration 2.
refs #175
Replace the hand-rolled aura-cli argv parser with a clap derive parser:
scoped `aura <sub> --help`, `--version`/`-V`, a per-flag Options section, and
`--flag=value`/`--`/long-opt abbreviation for free. Two iterations — (1) clap
migration, behaviour-preserving on exit codes; (2) exit-code split (usage=2,
runtime=1). clap is admitted under the C16 per-case review (research-side CLI,
invariant 8 untouched).
Forks ratified by the user (clap over hand-rolled; GNU-compliance over the
machine-first reframe; exit-code Option A) and the three spec-time derived
decisions (dual-grammar clap mapping, parse-vs-runtime exit classification,
two-iteration split) are recorded on #175.
Boss-signed on grounding-check PASS (independent, fresh-context; 13
current-behaviour assumptions all ratified by named green tests).
refs #175
Milestone-close validation of the World/C21 blueprint-data family surface, run
from the PUBLIC interface only (design ledger + op-script grammar; blueprints
authored as a consumer via `aura graph build`, no crates/ source read). Binary
built from 4710fcc.
The milestone's FUNCTIONAL PROMISE HOLDS (3 working findings): a consumer-authored
blueprint round-trips the whole verb family (graph build → list-axes → sweep →
rank → reproduce; walkforward → reproduce; mc → reproduce); all three FamilyKinds
(Sweep 4/4, MonteCarlo 5/5, WalkForward 3/3) reproduce bit-identically through the
one shared content-addressed store (the C18 core promise); list-axes→sweep→rank
composes and self-corrects.
Findings surfaced for follow-on (NOT fixed here — filed to the tracker): 2 bugs
(aura run on an open blueprint PANICS exit 101 instead of a clean exit-2 like mc;
closed→walkforward --axis prints the rejection twice), 2 friction (sweep-side
closed error terser than mc's exemplary message; mc reproduce lines omit the
seed), 2 spec-gaps (every open knob is mandatory on sweep but the docs frame
list-axes as a menu; the whole blueprint-data verb family is invisible from
`--help` / no README — empirically confirms #159). Detail per finding in the spec.
fieldtests/world-c21-milestone/ carries the op-scripts, authored blueprints,
captured outputs, and run_all.sh (regenerates the gitignored runs/ telemetry).
refs #170
cycle 0097 tidy (clean). Architect drift review over 485f3c8..HEAD: no code
drift, no debt. Regression: no dedicated script (architect is the sole gate);
its "What holds" is non-empty (design commitments confirmed against the diff):
- Inv. 8 / 9: the cycle touches only crates/aura-cli (main.rs + cli_run.rs +
the ephemeral spec/plan); walk_forward/WindowRoller/FamilyKind::WalkForward/
append_family/put_blueprint are read-only reuse, no engine/registry change.
- Inv. 1 / 2: blueprint_walkforward_family reuses the generic walk_forward roller
(windows disjoint-parallel, across-sim); each IS-sweep/OOS-run sees only its
window's windowed_sources; IS precedes OOS per window — no look-ahead.
- Reproduce lockstep: the reproduce_family_in WalkForward arm rebuilds each OOS
slice from stored.manifest.window (before the _ => run_sources fallthrough that
would rebuild the wrong full-window source); winner params via the shared
manifest->cells recovery; pinned by the reproduces_bit_identically E2E.
- Structural mirror + panic-safety: one-substitution-deep twin of the hard-wired
Stage1R arm (select_winner + walk_forward reused, metric sqn_normalized);
run_blueprint_walkforward follows the content-addressed sibling pattern (no
ensure_name_free); blueprint_sweep_over returns Result<_,BindError>, a bad axis
is in-closure exit 2 (never a panic); run_oos_blueprint derives pip internally
(7 args, no #[allow]).
Ledger: refreshed the C24 realization block (docs/design/INDEX.md) — replaced the
now-false "Walk-forward is deferred (#173, dep #169)" sentence with the "IS-refit
walk-forward shipped (cycle 0097)" note; and extended the C18 reproduction note —
reproduce now spans the third family kind (WalkForward), so all three FamilyKind
variants persist AND reproduce through the one shared topology_hash+put_blueprint
hook.
Milestone: the World/C21 blueprint-data family surface (run/sweep/mc/walkforward/
list-axes/reproduce) is coherent and complete per the architect review — no
structural gap. This audit proves drift-clean; a green end-to-end MILESTONE
FIELDTEST remains the deliberate gate to formally close the World/C21 milestone.
Ephemeral spec/plan git-rm'd per the lifecycle convention.
refs #173
Four tasks, one iteration: (1) the windowed IS-sweep + OOS-run helpers +
blueprint_walkforward_family (mirrors the hard-wired Stage1R walkforward arm one
substitution deep — loaded blueprint via blueprint_axis_probe); (2) the
--axis/--select parse grammar + IO wrapper (persist via put_blueprint +
append_family, content-addressed like aura mc) + the .json walkforward dispatch
arm; (3) the reproduce_family_in WalkForward branch (persist+reproduce land
together); (4) the E2Es (persist shape, reproduce bit-identical, no-axis reject,
malformed-safety) + the full clippy/suite gate.
Panic-safety: blueprint_sweep_over returns Result<_, BindError> (user --axis
fallible); a bad axis → clean in-closure exit 2 (mirrors the hard-wired arm's
select_winner handling), never a panic. reduce-mode members carry R-metrics (no
raw pip curve) → empty stitched equity, oos_r is the meaningful summary (C10
R-first). Closes the World/C21 milestone's last piece.
refs #173
Brummel