e304dbaae1fc33f48e1ee26bf8d608b295602ed3
152 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Brummel
|
e304dbaae1 |
feat(aura-core): name input ports
PortSpec gains a non-load-bearing `name: String`, so an input port is named just as FieldSpec.name (output) and ParamSpec.name (param) already are — input ports were the lone unnamed member of the node signature. Identity stays positional by slot (C23); the name is render/debug only, never read by bootstrap or the run loop. PortSpec drops Copy (String is not Copy), exactly as ParamSpec already does. - Every aura-std node names its input slots: SMA/EMA "series", Sub/Add "lhs"/"rhs", Exposure "signal", SimBroker "exposure"/"price" (the slots become self-documenting), LinComb "term[i]" and Recorder "col[i]" generated in their build loops (mirroring LinComb's existing weights[i] param loop). - derive_signature carries a composite's Role.name into the derived input port (it was dropped before — the output side already carried FieldSpec.name), so the graph model is homogeneously named at both levels. - model_to_json (port_json + the composite-header inputs in scope_json) emits the name as a third tuple element: ["f64","any","exposure"]. The byte golden was re-captured (machine bytes) and its substring twins updated; the model is now fully named across inputs/outputs/params. - All 16 PortSpec construction sites threaded in one compile-gate change; test fixtures carry fixture names. C8 realization note added to the design ledger. Why name-only, no validation: the name is a pure debug symbol. Wire-by-name was rejected (it would be a C23 contract change). Bootstrap slot-wiring validation (which would close #21's same-kind swap footgun) is deferred to its own cycle — a name alone does not catch the swap; it makes the slots self-documenting and gives a future validation something to check against. Verified: cargo test --workspace 168 green; clippy --all-targets -D warnings clean; cargo build --workspace clean. Read-only render path (C9), no serde (C14), scalar kinds unchanged (C4). closes #50 refs #21 refs #51 |
||
|
Brummel
|
5288249b44 |
plan: 0027 name input ports
Four tasks for cycle 0027 (spec docs/specs/0027-name-input-ports.md): 1. Add name: String to PortSpec (drop Copy) and thread all 16 construction sites in one compile-gate task — aura-std nodes get real slot names, fixtures get fixture names, derive_signature carries Role.name; port_json untouched so the byte golden stays green and the full suite passes. 2. port_json appends the name; re-capture the model byte golden and update its two substring twins (sink_has_empty_outs witnesses a leaf PortSpec.name in the model, multi_input_composite witnesses a composite Role.name carried through). 3. Lock the per-node input-slot names (8 aura-std pins). 4. C8 realization note in the design ledger (cross-links C23). refs #50 |
||
|
Brummel
|
55cfb29c74 |
spec: 0027 name input ports
Give a node's input ports a name. PortSpec { kind, firing } is the lone unnamed
member of the node signature today (FieldSpec.name / ParamSpec.name already
exist); a leaf node's input slots have no declared semantics. Add a
non-load-bearing name: String to PortSpec (drops Copy, mirrors ParamSpec), name
every input slot across aura-std nodes + fixtures, carry Role.name into
derive_signature's derived composite port (it is dropped today), and make
model_to_json emit the name in each port tuple. Identity stays positional by
slot (C23); the name is render/debug only, never read by bootstrap or the run
loop.
Surfaced by the 0026 graph-render redesign: a homogeneous pin-graph needs the
name to label input pins instead of inventing "a"/"b". Single iteration.
Design ratified interactively (brainstorm); grounding-check PASS (every
load-bearing current-state assumption ratified by a named green test); parse
gate a no-op (no spec_validation parser configured). Forks resolved: name is a
pure debug symbol, not wire-by-name (C23); String not &'static str (variadic
nodes generate term[i]/col[i]); no bootstrap validation this cycle.
refs #21
refs #50
|
||
|
Brummel
|
288f58953e |
feat(aura-engine): graph model serializer (0026 it1)
Iteration 1 of the graph render redesign: a read-only model_to_json(&Composite) that serializes the harness root + every distinct composite type into the canonical, deterministic JSON model the browser viewer will consume. New crates/aura-engine/src/graph_model.rs; lib.rs re-exports model_to_json. - House style: hand-rolled JSON like RunReport::to_json, NO serde (C14). - Model shape (faithful to the types, resolving the spec's prototype-flavoured example): node keys are indices (C23, the blueprint has no unique names); input ports carry kind+firing only, no name (PortSpec has none — acceptance criterion 3); a vec![] output is the C8 sink; bound root source-roles are minted as synthetic src_<role> source nodes; composite boundaries use @role (input) and #N (output) endpoints; distinct composites collected once. - Improvement over the plan: a composite's input kind is read from the actually fed interior slot (matching blueprint::derive_signature) rather than a hardcoded f64 — invents nothing. - Read-only (C9): &Composite -> String, no eval/compile/bootstrap on the path. - 10 new tests green: byte golden on the sample harness, determinism, structural mis-wire differs (param swaps are invisible to the pre-compile model — the property is carried by a structural re-target), read-only witness, sink / two-input / distinct-once structural assertions. Workspace green, clippy clean. aura graph still renders via ascii-dag (untouched); iteration 2 ports the viewer JS, vendors the WASM-Graphviz asset, emits the self-contained HTML, and retires ascii-dag. |
||
|
Brummel
|
bbe2266b9e |
plan: 0026 graph model serializer
Iteration 1 of the graph render redesign: a read-only model_to_json(&Composite) in a new crates/aura-engine/src/graph_model.rs, hand-rolled deterministic JSON (RunReport::to_json house style, no serde). Six tasks: helpers, primitive record, scope (index keys + synthetic source nodes from bound roles), composite defs (@role/#N endpoints, distinct-once walk), top-level + byte golden + determinism, structural assertions + structural-miswire-differs + read-only. Decisions: home in aura-engine; node keys are indices (C23); input ports carry kind+firing, no name (per acceptance criterion 3); bound root source-roles minted as synthetic source nodes. |
||
|
Brummel
|
cdb6313ee8 |
spec: 0026 graph render redesign
Replace the ascii-dag aura graph view with a homogeneous pin-graph: aura emits a deterministic JSON model (hand-rolled, RunReport::to_json house style, no serde); a vendored viewer JS (genDot, ported from the prototype) turns it into DOT; Graphviz-WASM lays out + draws it in the browser. aura stays a read-only serializer (C9), ships no layout engine. The golden-tested contract is the JSON model. Iteration 1: the model serializer + golden/determinism/read-only tests. Iteration 2: viewer + WASM vendoring + self-contained HTML, retire ascii-dag. Grounding-check PASS; design ratified interactively against the 0026 prototype. |
||
|
Brummel
|
7f485bbe72 |
docs(design): graph-render redesign prototype
Interactive, throwaway prototype of the aura graph render redesign — the visual language ratified for cycle 0026, replacing the ascii-dag text view. Homogeneous pin-nodes (body + n input pins + m output pins) rendered via Graphviz-WASM in the browser; pin-to-pin edges, type-as-colour, drill-down + inline-expand of composites, per-element styled tooltips, source/sink colouring, top-rank input ordering. index.html is the artifact; the ~1.4 MB WASM dep is git-ignored and restored by fetch-deps.sh. Visual companion to docs/specs/0026. |
||
|
Brummel
|
63af2d1095 |
audit: cycle 0025 (#49) — drift-clean; root renders like any composite
Architect drift review (d6f59d7..12b1bce): NO code drift, no contract weakened,
no ledger edit needed.
- C9 (read-only render): the change touches only label/entry assembly
(render_blueprint, leaf_label, render_graph signature); no eval, no run-path
code. 150 tests green (same count), clippy clean, build green.
- C12 ("mis-wiring visible before a run"): realized at the root, not overstated —
a top-level fan-in's wiring was invisible (bare [SimBroker]); it now surfaces
which producer feeds which slot ([SimBroker(#E,#price)]). The C8 label-render
refinement (INDEX.md:250, "label() surfaces a mis-wiring") is extended to the
root, not contradicted.
- C23 (names dissolve post-inline): render_compilat byte-untouched (still emits
source:{kind} from SourceSpec.kind); the [price] pre-inline / [source:F64]
post-inline split now renders C23's boundary-dissolution visibly, with
compiled_view_golden as the negative control.
- C3 (sources bind at ingestion only): root entries filtered to source.is_some()
bound roles — the one semantic root-vs-interior distinction, correctly retained.
- #49 acceptance: the Option<&Composite> drop unifies both render_graph callers
onto one stub path; no dead arm, no second/root-only stub function, no scope
creep beyond graph.rs (production) + main.rs (test-only goldens/assertions).
No ledger prose names the root source:{kind} marker as canonical; the C9
cycle-0017 realization (where: definitions render) is not stale. No new invariant
introduced — the cycle realizes existing contracts more fully, so no realization
note is manufactured.
Regression: none configured in the profile (no-op) — the architect review is the
gate. Resolution: carry-on (drift-clean). NOT a milestone close.
Tracker reconciliation done this cycle (no code, orchestrator-applied):
- #36 closed — 0024 resolved it (params declared once on the recipe; the 8
lockstep tests deleted), but Gitea's `closes #43 #36` only auto-closed #43.
- #25 closed — 0024 removed the dyn Node::schema() re-call + bootstrap-derivation
duplication this issue named (signatures gathered once into FlatGraph).
- #24 retitled to derive_signature()/signature() — the panic-vs-typed-error
divergence persists under 0024's renamed symbols; still open, low-priority.
|
||
|
Brummel
|
12b1bcec22 |
feat(aura-cli): render the root composite like any other composite
Close #49 and remove the last two render special-cases the blueprint root still carried, both pre-0024 vestiges. Since cycle 0024 the root is an ordinary Composite with input_roles, so the render no longer needs to treat it apart: (A) Fan-in slot stubs at the root. A composite-interior multi-input leaf already renders its wired slots as #… stubs; a top-level leaf did not, because render_blueprint threaded stub_ctx: None. It now passes the root composite (it IS a &Composite, carrying roles + edges), and stub_ctx drops its Option — both render_graph callers pass &Composite. The existing slot_source/ fan_in_identifiers/signature_of serve a top-level leaf verbatim; no second stub path (#49 acceptance). SimBroker now renders [SimBroker(#E,#price)] (#E = the Exposure producer's sibling-unique signature prefix, #price = the price source role name). (B) Role-named root entries. render_blueprint built entry markers from format!("source:{kind}") while render_definition uses role.name — the marker/stub asymmetry. The root now builds entries from role.name (filtered to bound roles, source.is_some()), identical to the interior, so the source marker reads [price] and matches the #price slot stub it feeds. render_compilat is deliberately untouched: post-inline the role name has dissolved (C23), so the compiled view keeps [source:F64] from the flat SourceSpec.kind — [price] pre-inline / [source:F64] post-inline is C23 made visible, and compiled_view_golden is the byte-unchanged negative control. Design call (orchestrator, with the user): the marker/stub asymmetry was fixed at its source (the entry naming) rather than by special-casing the stub to match the kind-named marker — the latter would have been a root-only stub behaviour, violating the "no second stub path" acceptance. The user chose full symmetry ([price], dropping the kind annotation) over a name+kind marker, prioritising structural cleanliness; the only remaining root-vs-interior distinction is the bound-role filter (C3), which is semantic, not cosmetic. Scope: crates/aura-cli/src/graph.rs only; read-only render (C9), behaviour-preserving for the run path (C1), no engine change. blueprint_view_golden re-captured from the live `aura graph` output (the where: section stays byte-identical — only the main graph re-flows); the SimBroker needle, a root-SimBroker-stub assertion on the macd view, and a [src] role-name-passthrough assertion are added. Verification (orchestrator-run, not agent-reported): cargo build --workspace green; cargo test --workspace 150 passed / 0 failed (same count, no run-path test moved); cargo clippy --workspace --all-targets -D warnings clean. compiled_view_golden and render_compilat byte-untouched. closes #49 |
||
|
Brummel
|
cd569aa6d0 |
plan: 0025 render root like any composite
Two-task plan for spec 0025 (#49). Task 1 is one compile unit in crates/aura-cli/src/graph.rs: thread the root composite as stub_ctx (drop the Option, update both render_graph callers) and name root entries by role.name instead of source:{kind}; gate is `cargo build -p aura-cli` (goldens stay red until Task 2 — the golden-recapture exception). Task 2 re-captures blueprint_view_golden from the live `aura graph` output, updates the SimBroker needle, adds a root-SimBroker-stub assertion to the macd test and a [src] role-name-passthrough assertion to reused_composite_defined_once; gate is `cargo test --workspace` + clippy. compiled_view_golden is the byte-unchanged negative control (render_compilat path, C23). plan-recon mapped exact line numbers and flagged the source:{kind} golden twin (blueprint changes / compiled must not) and the stale, out-of-scope render_clustered.txt fixture. |
||
|
Brummel
|
ed1d22bbfa |
spec: 0025 render root like any composite (slot stubs + role-name entries)
Settled source: issue #49, enabled by cycle 0024 (
|
||
|
Brummel
|
d6f59d7a52 |
audit: cycle 0024 (#43, #36) — drift-clean; ledger reconciled to the pre-build signature
Architect drift review (862882b..1b39093): NO code drift, no contract weakened. C1 (behaviour-preserving: 150 tests green, render goldens byte-identical, no behavioural assertion altered), C8 (sink output: vec![] preserved), C9/C23 (read-only render touches no eval/build; derive_signature's Box::leak is cold-path-only, leaked names non-load-bearing) all hold. Regression scripts: none configured (no-op) — the architect review is the gate. The only drift was design-ledger prose, anticipated and deferred to this audit by the plan. Resolved here (fix path, orchestrator-applied — docwriter is barred from the design ledger): - docs/design/INDEX.md C8 Guarantee: rewritten — a node's signature (NodeSchema) is declared pre-build on the value-empty recipe; the built node implements lookbacks() (the one param-dependent sizing quantity) + eval(); schema() is gone. - INDEX.md C8 cycle-0015 note: Blueprint::param_space -> Composite::param_space; the #36 lockstep-debt clause marked closed by 0024. - INDEX.md: added a C8 cycle-0024 realization (signature lives once on the recipe, the signature/sizing split, #43/#36 closed) and a C19 cycle-0024 realization (struct Blueprint collapsed into the root Composite; Role.source/runnable-iff- bound/UnboundRootRole; FlatGraph as the named compilat). Stale symbol names in the dated 0016/0017 notes annotated in place with their 0024 renames. - aura-std/src/lincomb.rs module doc: Blueprint::param_space -> Composite::param_space. Ledger-gap (four new load-bearing invariants previously unrecorded) closed by the two new realization notes. Green baseline re-confirmed after the edits: cargo test --workspace 150 passed / 0 failed; cargo clippy --all-targets -D warnings clean. refs #43 #36 |
||
|
Brummel
|
1b3909316e |
feat(aura): node signature lives in the blueprint; collapse Blueprint into Composite
Consolidate the node data structure so every node's signature (NodeSchema:
inputs/output/params) is declared once and exists in the blueprint pre-build,
and dissolve the special "root graph" type. Behaviour-preserving (C1).
Signature vs sizing
- NodeSchema is now the static signature only: InputSpec -> PortSpec{kind,firing},
with lookback removed. The signature is fully static per blueprint (input
kinds/firing, output fields, params); LinComb's variable arity is a builder arg,
not an injected param.
- The one param-dependent quantity, an input's buffer lookback (e.g. Sma's window =
its injected length), moves out of the signature to Node::lookbacks() -> Vec<usize>,
read only by bootstrap for sizing. Node::schema() is removed.
- LeafFactory -> PrimitiveBuilder, which carries the full NodeSchema. The built node
no longer re-declares it: closes the params-declared-twice drift (#36, the 8
per-node factory_params_match_built_node_schema lockstep tests are deleted — their
subject is now structurally impossible) and a value-empty recipe exposes its full
I/O interface pre-build (#43).
Root is just a bound composite
- struct Blueprint is deleted; its compile/bootstrap/param_space methods move onto
Composite. Role gains source: Option<ScalarKind> (None = open interior port,
Some = bound ingestion feed). A composite is runnable iff every root role is bound;
the "main graph" is no longer a category, only the fully-source-bound composite.
New error CompileError::UnboundRootRole for an open root role.
- BlueprintNode::signature() answers uniformly for both arms: Primitive returns the
builder's declared schema, Composite derives it from the interior (role kinds in,
OutField kinds out, aggregated params), pre-build, no build.
compile -> FlatGraph -> bootstrap
- compile validates structure pre-build via signature() (validate_wiring: range +
kind, returning the same variants as before, so an edge kind fault is now caught
before any build closure fires) and emits FlatGraph{nodes,signatures,sources,edges}.
- bootstrap consumes the FlatGraph: kinds/firing/output from the carried signatures,
buffer depth from node.lookbacks(). SourceSpec survives as the flat descriptor.
Renames: BlueprintNode::Leaf -> Primitive, LeafFactory -> PrimitiveBuilder.
Render (aura-cli/src/graph.rs) is migrated compile-only: it takes &Composite, maps
bound roles to the same source-entry shape, so both render goldens reproduce
byte-identical output (no re-capture needed). Render-fidelity tuning is the next cycle.
Verification (orchestrator-run, not agent-reported): cargo build --workspace green;
cargo test --workspace 150 passed / 0 failed; cargo clippy --workspace --all-targets
-D warnings clean. All pinned determinism/run-output tests pass with values unchanged;
no behavioural assertion was altered to go green. 5 new tests assert the signature is
pre-build and uniform, that compile rejects a kind mismatch without building (via a
panicking builder), UnboundRootRole, and lookbacks()/signature arity agreement.
Deferred to cycle-close audit (per plan): docs/design/INDEX.md and some aura-std
module docs still name the old Node::schema()/LeafFactory/BlueprintNode::Leaf/
Blueprint::param_space contracts; prose reconciliation is the architect's at audit.
closes #43 #36
|
||
|
Brummel
|
c7fc2f6a37 |
plan: 0024 node signature in blueprint
Five-task, compile-gate-sequenced plan for the behaviour-preserving refactor: aura-core types (PortSpec/PrimitiveBuilder/NodeSchema/lookbacks) -> aura-std 8 nodes -> aura-engine lib (Composite absorbs Blueprint, signature/derive_ signature, FlatGraph, pre-build validate_wiring, bootstrap reshape) -> engine tests -> aura-cli/ingest + compile-only render. Per-crate partial build gates; workspace gate only in the final task. One working-tree unit (committed once after Task 5 green). refs #43 #36 |
||
|
Brummel
|
78d68fa8ad |
spec: 0024 node signature in blueprint
Consolidate the node data structure so every node's signature (NodeSchema: inputs/output/params) exists in the blueprint pre-build, declared once. - Signature vs sizing split: NodeSchema becomes the static signature (InputSpec -> PortSpec, lookback removed); the one param-dependent quantity (input buffer lookback) moves to a build-time Node::lookbacks() query. Node::schema() is removed. - PrimitiveBuilder (ex-LeafFactory) carries the schema; the built node no longer re-declares it -> closes the params-declared-twice drift. - Blueprint collapses into Composite: Role gains source: Option<ScalarKind>; the root is the fully-bound composite (no "main graph"); new error UnboundRootRole. - compile -> FlatGraph -> bootstrap: FlatGraph carries node + signature in parallel; bootstrap sizes from lookbacks(), kind-checks from the signatures. - Renames: BlueprintNode::Leaf -> Primitive, LeafFactory -> PrimitiveBuilder. Behaviour-preserving (C1). Render is out of scope beyond compiling (next cycle). refs #43 #36 |
||
|
Brummel
|
862882bc04 |
audit: cycle 0023 (#48) — drift reconciled; render paths unified
Architect drift review (bb90c42..481172a): no contract drift. C9 (render reads structure + label()/params()/output() only, never eval), C8 (sink = zero-output leaf, no special case), C12 (blueprint = root composite is render-structural only; types stay distinct), C23 (consumer-prefix mirrors the := binding), #38 (composites stay opaque) — all hold. Three fidelity items, resolved: - [high, fixed] spec acceptance over-claimed: the SimBroker slot-stub box read as in-scope though the work is deferred. Spec amended — the stub acceptance is annotated against #49, the met boxes checked. - [medium, recorded] no docs/plans/0023: this cycle ran spike→refactor under user steering instead of planner→implement, because the edge-label-vs- consumer-side fork needed an empirical probe (ascii-dag silently drops edge labels on collision) before a placeholder-free plan was possible. A plan RECORD (not a task plan) now holds the 0023 slot so the counter pairing stays intact and the next cycle takes 0024. - [low, carry-on] multi_output_field_name's leaf-producer fallback is latent and untested (no multi-output leaf in the corpus). Carried as debt. Regression scripts: none configured (no-op). Build/test/clippy green. Deferred stub work is tracked in #49 (user-signed). closes #48 |
||
|
Brummel
|
481172ae2e |
feat(aura-cli): unify blueprint main-graph render through one shared core
render_blueprint and render_definition were two divergent paths: the main graph drew bare factory.label() leaves and bare edges, the composite interior drew enriched leaves (params, slot stubs, output bindings). They now delegate to one shared render_graph over borrowed slices — the blueprint is the root composite, differing only at the borders (ParamNames::Factory vs Aliases, Entry unifying SourceSpec and Role, empty OutField list = no bindings). LeafFactory holds a Box<dyn Fn>, so it is not Clone — an owned root-composite adapter is impossible; the shared core takes borrowed slices instead. The main graph now shows what the strategy does: a multi-output producer's selected field surfaces as a consumer-side prefix ([histogram -> Exposure(scale)]), mirroring the := output-binding form. Edge labels are deliberately avoided — ascii-dag 0.9.1 silently drops an edge label it cannot place without collision (arena_render.rs can_place_label), unreliable in a dense graph. Deferred: top-level blueprint multi-input leaves render without #-slot stubs (stub_ctx None) — fan_in_identifiers is still composite-coupled via signature_of. refs #48 |
||
|
Brummel
|
5dd9503e40 |
spec: 0023 unify blueprint main-graph render
The CLI blueprint main-graph render is a separate, poorer path than the composite-definition render: bare leaves, bare edges, dropped from_field. Unify both through the composite machinery — the blueprint is the root composite, differing only at the borders (sources, factory params, sinks as zero-output terminal leaves). Harness signature header deferred. refs #48 |
||
|
Brummel
|
bb90c42028 |
audit: cycle 0022 (#46) — drift reconciled; output bindings shipped
Architect drift review (range 69d2094..HEAD), regression gate empty (no scripts configured). Status: drift_found, all resolved here or queued. What holds: C8/C23 intact — output_binding folds OutField.name onto the producer label as a pure render symbol; compiled_view_golden byte-identical, no name reaches the compilat; the drawn where: graph is now exactly the computation DAG (false terminals + node-count inflation gone). Resolved (doc reconciliation, this commit): - docs/design/INDEX.md: two stale render descriptions brought current — the C9/0018 realization said output names render as `[out:<name>]` markers; the C19/0017 realization said `[in:k]`/`[out]` port markers. Both superseded by the `name := producer` binding form (the `[out]` staleness is cycle-0022's; the adjacent `[in:k]` was pre-existing drift from 0019/0020 and is reconciled in the same clause while here). - docs/specs/0022: post-ship note added — its Components/Testing strategy under-counted the blast radius, missing the full-render golden blueprint_view_golden (forced re-capture, caught at implement). Queued (not fixed): output_binding's tuple arm `(a, b) := …` is spec'd + shipped but unexercised (no fixture re-exports >1 field from one node) — filed as #47 (idea). cycle 0022 drift-clean after this reconciliation (not a milestone close). |
||
|
Brummel
|
3b496883e6 |
feat(aura): render composite output re-exports as producer bindings
In the blueprint view's `where:` section, a composite's output re-exports now fold onto their producing node's label as a binding (`[macd := Sub(#Ef,#Es)]`) instead of each becoming a standalone terminal node wired from its producer. An OutField re-exports an existing interior node's value — it is never a new node — so the old form drew false terminals (MACD's macd line feeds the signal EMA and histogram internally yet rendered as a dead-end leaf) and inflated the node count by the output arity (MACD where: 8 -> 6 nodes; sma_cross drops its [cross] stub + edge). The drawn graph is now exactly the computation DAG; the `:=` prefix is the visual signal that a node's value escapes the boundary. Input roles stay standalone entry nodes (no producer to annotate) — the asymmetry is deliberate. render_definition drops its per-OutField node+edge loop; a new output_binding helper yields the `name := ` / tuple `(a, b) := ` prefix. Pure render layer: C8/C23 untouched, OutField.name never reaches the compilat, compiled_view_golden byte-identical, MACD run deterministic and unchanged in metrics. Test blast radius was wider than spec 0022 §Components / the plan's Scope note counted: besides the MACD pinning test, four more sites assert a producer that carries an OutField and so gain the `:=` prefix — blueprint_view_defines_each_composite_once, the two fan-in identifier tests, the cli_run integration test, and (missed by the plan, caught at implement) the full-render blueprint_view_golden. All re-pins are forced by the design, zero judgement. The output_binding tuple arm is unexercised by current fixtures (no composite re-exports >1 field from one node). Verified: cargo test --workspace 0 failed; clippy --all-targets -D warnings clean. closes #46 |
||
|
Brummel
|
b2f27f8590 |
plan: 0022 composite output binding render
RED-first: re-pin all five render assertions whose producer carries an OutField (macd, sma_cross cross, two fan-in `o` outputs — across main.rs + cli_run.rs) to the `:= ` binding form, then fold output_binding onto the producer label in render_definition. Blast radius wider than spec §Components named (flagged for audit). refs #46 |
||
|
Brummel
|
7d4740e8b2 |
spec: 0022 composite output binding render
Render composite output re-exports as producer-label bindings (`name := <producer-label>`) instead of standalone terminal nodes: folds the output name onto its producing node, dropping the false terminals and the node-count inflation (MACD where: 8 -> 6). Pure render layer; C8/C23 untouched, compiled view byte-identical. refs #46 |
||
|
Brummel
|
69d20949c0 |
tidy(aura-engine): single-own alias-validity + shared alias-count anchor
Collapse the two correctness-neutral debt items the 0021 fan-in pre-pass left behind (architect drift review at cycle close). Alias-validity: the `BadInteriorIndex` check was raised in two places — the structural pre-pass `check_composite_fan_in` and `inline_composite`. Since `compile_with_params` runs the pre-pass over every composite before any lowering, `inline_composite`'s copy was dead for that error path. The check now lives in one helper `check_alias_indices`, called solely by the pre-pass; `inline_composite` drops its copy (and the now-unused `param_aliases` binding — the overlay is a pure naming layer, unused in lowering, which is driven by the injected scalar vector). Alias-count: the per-node `a.node == node` predicate was re-derived in three spots (signature base, the unaliased-param test, the CLI render base-length). All three now route through one exported anchor `aliases_on`, so an alias-semantics change touches one site. Behaviour-preserving: the full workspace suite is the guard (15+6 cli, 25 core, 69 engine, 6+1+1 ingest/misc, 29 std — 0 failed), `out_of_range_param_alias_rejected` still green (now raised by the pre-pass), clippy -D warnings clean. No ledger change (the C9 refinement landed in 0021). closes #45 |
||
|
Brummel
|
04c2280dd8 |
audit: cycle 0021 (#44) — drift-noted; fan-in distinguishability shipped
Architect drift review over efbe0f4..3f4d756 (the two un-audited interim render commits 32ac8a3/b73d707 plus the 0021 fan-in cycle). Holds: - C23 intact — the IndistinguishableFanIn check is a construction-phase pre-pass; the compilat stays name-free (compiled_view_golden byte-stable). - C9 boundary clean — signature distinguishability lives at the blueprint layer and dissolves at inline; the C9 ledger refinement is accurate and in-format. - Pre-pass placement (before the arity gate, not inside inline_composite) is the spec-aligned home, not drift: a no-param compile() of a param-bearing composite would hit ParamArity first. Regression: commands.regression is empty (no gate) — architect is the sole gate; clean of contradictions. Debt (correctness-neutral, not blocking) tracked in #45 for a focused tidy iteration rather than rushed at cycle tail: - inline_composite's alias-validity loop is now dead for BadInteriorIndex (the pre-pass raises it first for every composite). - per-node alias count is re-derived in three sites (signature_of base, leaf_has_unaliased_param, signature_base_len). refs #45 |
||
|
Brummel
|
3f4d756ed2 |
feat(aura): fan-in input distinguishability — construction constraint + source-derived render
A fan-in node (>1 input) whose colliding sources hide an unnamed configuration axis is now illegal at construction, and the definition view renders each fan-in input as a source-derived recursive-signature identifier instead of the positional, meaningless #A/#B. The root defect was sma_cross: two Sma into a Sub with unaliased length params, rendering sma_cross() -> (cross) with two indistinguishable [SMA] and [Sub(#A,#B)] — the author meant fast vs slow but the identity hid it. Now it renders sma_cross(fast:i64, slow:i64) with [SMA(fast)]/[SMA(slow)] and [Sub(#Sf,#Ss)]. Shape (single source of truth for "signature" shared by engine + CLI): - aura-engine signature_of(): a node's recursive authoring identity — type initial + alias initials + each wired input's signature (recursing into interior leaves, stopping at named roles/composites at their initial). - aura-cli leaf_label/fan_in_identifiers: shortest sibling-unique prefix of a source's signature, never below its base (type + alias initials); a role-fed slot renders its name verbatim (#price); equal-signature interchangeable inputs keep the positional letter. - aura-engine IndistinguishableFanIn: a signature collision is a fault only when a colliding source carries an unaliased param (the unnamed axis); param-less interchangeable sources (fan_composite's Pass/Pass) stay legal. Param-aware criterion (refined during design): keeps the blast radius to the param-bearing alias-less fixtures (sma_cross CLI + engine, the nested fast_slow); fan_composite and the hand-wired flat fixtures stay green. Placement decision (deviates from the plan): the constraint runs as a structural pre-pass (check_fan_in_distinguishability) at the head of compile_with_params, BEFORE the param-arity gate — not inside inline_composite as the plan drafted. Reason: the no-param compile() of a param-bearing composite would hit ParamArity first and preempt the fault; the spec mandates a structural check needing no param values, so the pre-pass is the spec-aligned home. Alias-validity ordering (BadInteriorIndex before the fan-in fault) is preserved at the pre-pass head. C23 untouched: the check is construction-phase; the compilat stays name-free (compiled_view_golden byte-stable). Ledger C9 carries the refinement. Known debt (non-gating): the alias-index validity check now exists in both inline_composite and the pre-pass (the pre-pass reaches every composite first, making inline_composite's copy effectively dead). Left for a separate tidy — a 5-line, correctness-neutral removal with its own test surface. closes #44 |
||
|
Brummel
|
3aa124f815 |
plan: 0021 fan-in distinguishability
Four tasks: shared recursive signature_of helper (aura-engine); CLI source-derived fan-in identifiers + sma_cross aliases + render goldens (aura-cli); the IndistinguishableFanIn construction constraint + engine fixture aliases (aura-engine); the C9 ledger refinement. Ordered so the workspace test suite stays green at every task boundary. Refs #44 |
||
|
Brummel
|
22a690361a |
spec: 0021 refine fan-in constraint to a param-aware criterion
A signature collision is a fault only when at least one colliding source carries an unaliased param slot — the configuration axis the author left unnamed (sma_cross's length). Equal-signature sources with no param are genuinely interchangeable (fan_composite's Pass/Pass, add(price,price)) and stay legal; the render uses the positional letter for them. Keeps the construction blast radius to the param-bearing alias-less fixtures. Refs #44 |
||
|
Brummel
|
14d91035ec |
spec: 0021 fan-in distinguishability
A construction-phase constraint (CompileError::IndistinguishableFanIn, raised in inline_composite) makes a fan-in node whose sources have identical recursive signatures illegal; the definition view then renders each fan-in input as the shortest unique prefix of its source's signature (replacing positional #A/#B); and the sma_cross fixture gains its missing fast/slow aliases. Refs #44 — scope extended from render-only to a construction-phase invariant during design (the positional #A was a symptom of unnamed, indistinguishable fan-in sources, which is the actual fault to forbid). |
||
|
Brummel
|
b73d7076c3 |
feat(aura-cli): TTY-gated ANSI edge colouring + blank line after composite signature
Two presentation refinements to the `aura graph` views, render-only (no
engine change, C8/C9/C23 untouched).
Edge colouring: thread a `Color { Plain, Ansi }` through render_flat /
render_definition / render_blueprint / render_compilat. `Ansi` uses
ascii-dag's colored scanline pass (per-edge palette colours) so crossing
edges stay traceable; `Plain` is the existing monochrome `g.render()`.
The CLI selects `Ansi` only when stdout is a TTY (`IsTerminal`), so a
redirect to a file or pipe stays byte-clean — `aura graph | …` carries no
escape codes. ascii-dag colours only edges; node-label text is unaffected.
Tests render `Color::Plain` explicitly, so both goldens stay byte-stable
(compiled_view_golden remains the C23 guard); a new test pins that `Ansi`
emits escapes and `Plain` does not, and that labels survive colouring.
Blank line: render_definition now separates the typed signature title from
the graph body with an empty line. blueprint_view_golden re-captured.
Considered but rejected this round: per-node role highlighting of the
signature identifiers — needs either an ascii-dag fork (node colouring is
hard-disabled upstream) or a per-graph string-surgery pass that does not
generalise beyond hand-known labels. Only edge colouring survives here.
|
||
|
Brummel
|
32ac8a30ea |
feat(aura-cli): de-prefix input-role markers ([in:price] -> [price])
Symmetric with the output de-prefix shipped in
|
||
|
Brummel
|
efbe0f4a66 |
audit: cycle 0020 tidy (clean) — typed-signature render, render-only
Architect drift review over ebe2e71..HEAD (spec |
||
|
Brummel
|
2f4916596d |
feat(aura-cli): composite definition renders as a typed signature
Refines #41's blueprint-definition render. The [param:<name>] marker nodes #41 added bloated the ASCII MACD graph (three extra nodes + fan-in edges); this moves the interface into the title line and folds names into the leaf labels that already exist: - title is the composite's typed signature, e.g. macd(fast:i64, slow:i64, signal:i64) -> (macd, signal, histogram) (param kinds from the aliased leaf's factory params via a new ScalarKind->lowercase kind_str; output NAMES only — output kinds need a pre-build factory interface, deferred to #43) - leaf labels fold aliased param names: [EMA] -> [EMA(fast)] - unnamed interior input slots render as ordered stubs: [Sub] -> [Sub(#A,#B)] (count/order derived render-side from c.edges() + c.input_roles(), no engine schema needed; arity-1 nodes get no stub) - outputs de-prefixed: [out:macd] -> [macd]; the [param:*] marker nodes are gone - two stale doc comments corrected: render_definition's [param:] prose and node.rs LeafFactory::label (the renderer went flat in 0017, so the cited ascii-dag cluster-garble rationale no longer applies — wide labels are safe; the factory label stays bare because alias names are composite-level) Render-only: no engine/ParamAlias/param_space change. compiled_view_golden byte-identical (C23 guard — verified untouched in the diff); aura run --macd deterministic and unchanged (total_pips 0.1637945563898923, 3 sign flips). The title format change repinned five .matches("name:")->.matches("name(") definition-count asserts (sma_cross/outer/inner/dup/macd); the stub separator is "," (no space) to match the [Sub(#A,#B)] surface. Verification (orchestrator-run): cargo build/test/clippy --workspace -D warnings all green; the redesigned MACD render confirmed by eye. refs #41 #43 |
||
|
Brummel
|
71f50330db |
plan: 0020 composite signature render
Two-task render-only plan executing spec 0020:
- T1 (graph.rs + node.rs): add `signature` (typed title line, with a new
ScalarKind->lowercase `kind_str` match — none exists today, {:?} gives
PascalCase) and `leaf_label` (fold aliased param names + ordered
input-slot stubs); edit render_definition (title->signature,
leaf->leaf_label, drop [param:*] loop, de-prefix outputs); fix two stale
doc comments (the render_definition [param:] description + the
node.rs:93-101 cluster rationale). Gate: cargo build -p aura-cli (the
goldens go red until T2 re-captures; cargo test is NOT a T1 gate).
- T2 (main.rs): repin the FIVE title asserts name:->name( (the blast
radius: sma_cross/outer/inner/dup/macd, four beyond the spec's named
one); update the definition needle ([Sub]->[Sub(#A,#B)], [out:cross]->
[cross]); rewrite the MACD render assertions (drop [param:*], add the
signature + [EMA(fast)] + [Sub(#A,#B)] + [macd] + [param:/[out: absence);
re-capture blueprint_view_golden wholesale; confirm compiled_view_golden
byte-identical (C23); full --workspace triple -D warnings.
Render-only: no engine/ParamAlias/param_space change; compiled_view_golden
byte-identical; aura run --macd unchanged. Output kinds deferred to #43.
refs #41 #43
|
||
|
Brummel
|
42eb62771d |
spec: 0020 composite signature render
Render-only refinement of #41's composite blueprint-definition view. The [param:<name>] marker nodes #41 added bloat the ASCII graph; this moves the interface into a typed signature title line and folds names into the node labels that already exist: - title: macd(fast:i64, slow:i64, signal:i64) -> (macd, signal, histogram) (param kinds from factory().params()[slot].kind; OUTPUT NAMES ONLY) - leaf labels fold aliased param names: [EMA] -> [EMA(fast)] - unnamed interior input slots as positional stubs: [Sub] -> [Sub(#A,#B)] (count/order derived render-side from c.edges() + c.input_roles()) - outputs de-prefixed: [out:macd] -> [macd]; [param:*] marker nodes removed - fix stale node.rs:93-101 cluster rationale (renderer went flat in 0017) Output KINDS are deferred: a value-empty LeafFactory exposes no output schema pre-build (the mc_4/#42 finding), so the typed arrow (-> macd:f64) waits on #43. Render-only: no engine/ParamAlias/param_space change; compiled_view_golden byte-identical (C23); aura run --macd unchanged. Gates green: feature-acceptance (the worked MACD before->after is the evidence), placeholder scan clean, parse-every-block no-op (no spec_validation parser), grounding-check PASS (10 assumptions ratified; both load-bearing premises — no pre-build factory output schema, flat renderer — confirmed). refs #41 #43 |
||
|
Brummel
|
ebe2e71349 |
audit: cycle 0019 (#41) — drift-clean; C9 boundary-uniform realization note
Architect drift review over 8bc429f..HEAD (spec |
||
|
Brummel
|
41cbb5506f |
feat(aura-engine): name the composite boundary — input roles + param aliases
Brings the other two composite-boundary edge-kinds to the named-projection shape #40 gave outputs. input_roles changes from a bare Vec<Vec<Target>> to Vec<Role { name, targets }> (rendered [in:<name>]); a composite gains params: Vec<ParamAlias { name, node, slot }> that relabels an interior leaf param slot's surface name in param_space() (rendered [param:<name>]). Param aliasing is a PURE NAMING OVERLAY, not curation (the load-bearing decision, per spec 0019): every interior param slot stays in param_space() and sweepable; the alias only relabels in place, never reorders or hides. Proven empirically — the MACD run is byte-identical (total_pips 0.1637945563898923, 3 sign flips), only the param labels improved: param_space() now surfaces [macd.fast, macd.slow, macd.signal] instead of three indistinguishable macd.length, and the manifest reads ema_fast/ ema_slow/ema_signal. C23 honoured: role/param/output names are non-load-bearing debug symbols dropped at lowering; identity is positional (role index, param slot, output field). compiled_view_golden is byte-identical (verified: the golden region is untouched in the diff). An out-of-range alias (missing/ non-leaf node or slot past the leaf's param count) is rejected at compile_with_params as BadInteriorIndex, mirroring the output range-check (no new variant). Orthogonal to #36 — purely additive at the composite level. Aliasing is demonstrated on the CLI MACD site only (the spec's worked example + a new E2E test macd_param_space_surfaces_the_three_named_aliases); sma_cross, the engine test fixtures, and the construction-layer fieldtests get the forced role-name + empty params, so the param_space C23 anchor goldens (param_space_mirrors_compiled_flat_node_param_order + siblings) stay byte-identical. Verification (orchestrator-run, not trusted from the agent report): cargo build/test/clippy --workspace -D warnings all green (engine 66, cli 12); the separate-workspace construction-layer fieldtest crate builds (guards the #42 latent-drift recurrence); compiled_view_golden + MACD determinism unchanged. Two faithful repairs to the plan's literal test/code bodies, no semantic change: the out-of-range test uses .err()/Some(BadInteriorIndex) (the Ok arm Vec<Box<dyn Node>> is not Debug, so .unwrap_err() would not compile), and the inline_composite destructure binds params as `param_aliases` to avoid shadowing the injected `params: &[Scalar]` arg. closes #41 |
||
|
Brummel
|
c9115e3e0f |
plan: 0019 name composite boundary
Four-task plan executing spec 0019, sequenced like cycle 0018 (type-shape change rippling engine -> CLI): - T1 engine type migration, behaviour-preserving: Role/ParamAlias types, Composite struct/new/accessors, inline_composite role-walk, lib.rs re-export, all engine test Composite::new sites. Gate per-crate (cargo test -p aura-engine, NOT --workspace; aura-cli compiles in T3). The new params field is dormant -> param_space byte-identical, C23 anchor goldens green. - T2 param aliasing RED-first: collect_params alias relabel + inline_composite alias range-validation (-> BadInteriorIndex, reusing the variant), with 4 new unit tests (relabel, out-of-range, unaliased regression, partial). - T3 CLI: render_definition [in:name]/[param:name] markers; MACD author site (named role + fast/slow/signal aliases, the worked example); sma_cross named role only; blueprint_view_golden re-capture; compiled_view_golden stays byte-identical (C23 guard). - T4 fieldtests sweep (separate workspace root -> explicit cargo build gate, guarding the #42 latent-drift recurrence) + full --workspace triple (-D warnings). Aliasing demonstrated on the CLI MACD site only (the spec's evidence); every other composite site gets the forced role-name + empty params, so the param_space C23 anchor goldens stay byte-identical. refs #41 |
||
|
Brummel
|
03f2dc4c51 |
spec: 0019 name composite boundary
Sibling of #40 (composite output as a named multi-field record). Brings the other two composite-boundary edge-kinds to the same named-projection shape: input roles (Vec<Role { name, targets }>, rendered [in:<name>]) and a param-alias overlay (Vec<ParamAlias { name, node, slot }>) that relabels an interior leaf param slot's surface name in param_space(). Load-bearing decision recorded in the spec: param aliasing is a pure naming overlay, NOT curation — every interior slot stays in param_space() and sweepable; the alias only relabels in place, never reorders/hides (forced by the issue's "legibility not capability" framing + C23). The injected point vector is unchanged; MACD surfaces macd.fast/slow/signal instead of three indistinguishable macd.length. Gates green: feature-acceptance (worked MACD before->after is the evidence), placeholder scan clean, parse-every-block no-op (profile declares no spec_validation), grounding-check PASS (7 load-bearing assumptions each ratified by a named currently-green test; compiled_view + param_space slot-order goldens stand as the C23 regression anchors). refs #41 |
||
|
Brummel
|
241bb626e6 |
fix(fieldtests): port construction-layer fixtures to current authoring API
The four standalone construction-layer fieldtest bins (mc_1..mc_4) no longer compiled: they are their own workspace root, so the engine's `cargo build --workspace` never touched them and two waves of API drift went latent. Two breakage classes, both confined to the fixture files (no engine change): - Stale cycle-0016 authoring. `BlueprintNode::from(<Node>::new(..))` relied on the `From<NodeType>` impls retired in the value-empty migration; only `From<LeafFactory>` survives. Ported to `<Node>::factory().into()` — nodes are value-empty blueprint items, params bound at compile. Knock-on in mc_4 `describe_node`: a blueprint leaf is now a `&LeafFactory` with no pre-build schema, so leaf introspection reports the render label + declared param count (inputs / outputs exist only on the compiled flat node, post-build). - Cycle-0018 (#40) OutPort -> OutField slice drift. `Composite::output()` now returns `&[OutField]`; the mc_4 read sites were still treating it as a single port. Ported to index the record; the walk assertion now also pins the arity (one re-exported field), which is the #40 shape. Faithful ports, not assertion-gutting: each fixture still exercises its axis (composite build+run / miswire render / nested composite / graph introspection), verified by running all four bins to their `OK:` line. One genuine semantic drift flagged in mc_2: the blueprint-view label is now the bare value-empty type ("SMA"), so two same-type leaves share a label and are disambiguated by the slot/edge table; the valued SMA(2)/SMA(4) label lives on the compiled view. The fixture asserts what the blueprint view actually exposes and keeps the load-bearing edge-table observability check untouched. closes #42 |
||
|
Brummel
|
8bc429f367 |
audit: cycle 0018 (#40) — drift-clean; C9 multi-output realization note
Architect drift review over a4cfe5c..HEAD (covers the previously-unaudited EMA node and MACD PoC plus the #40 composite multi-output cycle): status clean. C8/C7/C4 preserved (one port, one row per eval, K co-fresh base columns — structurally identical to OHLCV); C23 honoured (ItemLowering:: Composite.output is Vec<(usize,usize)>, no name in the compilat; the compiled-view render stayed bit-identical). EMA and MACD PoC carry no ledger drift. Resolution of the three minors: - Ledger lagged the new behaviour: added a "Realization (cycle 0018)" note under C9 recording that a composite's output is now a named K-field record (Vec<OutField>), the same arity C8 already grants a leaf, names dropped at lowering (C23). Amended here (ledger amendment is the audit's job). - blueprint.rs module-doc / Composite struct-doc / new-doc still said "one output port" singular — updated to "output record". - Non-workspace fieldtest From<Sma> debt is pre-existing (cycle-0016) and already tracked as #42; not re-filed. No regression scripts configured (profile regression: []), so the architect review is the sole gate. Carry-on: the next natural iteration is the #41 legibility sibling (input-role + param naming at the composite boundary). |
||
|
Brummel
|
784e6c917a |
feat(aura-engine): composite output is a named multi-field record
Replace a composite's single output port (OutPort { node, field }) with
an ordered, named record (Vec<OutField { node, field, name }>). A
composite can now re-export K interior fields as one output; a consumer
selects one via the existing Edge::from_field — the same field-wise
selector that already works for multi-output leaf producers (OHLCV).
Why: multi-line indicators (MACD, Bollinger, Stochastic, Ichimoku) could
not be authored as a composition and re-exported as a unit — only one
line escaped the boundary. The MACD PoC was forced to expose only the
histogram. This lifts the three `field == 0` / `from_field == 0` caps at
the composite boundary (inline_composite nested arm, rewrite_edge
composite arm), range-checking the index instead.
Boundary completion, not an invariant change:
- C8/C7/C4 untouched — one port, one row per eval, K base columns (a
3-line MACD is identical in kind to OHLCV).
- C23 honoured — re-export names live at the blueprint boundary only and
are dropped in the compilat (raw index wiring). compiled_view_golden
stayed byte-identical (the regression guard): no name leaked into the
flat graph.
The MACD PoC now re-exports macd / signal / histogram as a record; the
strategy still trades the histogram, selected via from_field: 2. The
render shows K [out:<name>] markers per multi-output composite (input
roles stay [in:<index>] — naming them is the dependent #41).
Output naming ships with the capability (OutField is born name-ready) so
#41 — composite param aliasing + input-role naming — does not reopen the
type.
Verification: cargo build/test/clippy --workspace -- -D warnings all
green; aura-engine 62 tests (+3 capability, +1 through-run E2E), aura-cli
unchanged-count green; compiled_view_golden byte-identical.
Known debt (out of scope, pre-existing): the non-workspace construction-
layer fieldtests (fieldtests/milestone-construction-layer/mc_1..mc_4)
carry their OutField sweep but still do not compile standalone — they use
the Sma::new / BlueprintNode::from(Sma) API retired in the cycle-0016
value-empty migration, never propagated to these fixtures. Tracked as a
follow-up.
closes #40
|
||
|
Brummel
|
2c33a8d74f |
plan: 0018 composite multi-output record
Four tasks: engine type migration (behaviour-preserving, caps kept) → cap-lift with RED-first capability tests → CLI render + author sites + golden re-capture → non-workspace fieldtest sweep + workspace gate. refs #40 |
||
|
Brummel
|
9ddeab8b7e |
spec: 0018 composite multi-output record
Composite::output: OutPort -> Vec<OutField { node, field, name }> so
multi-line indicators (MACD/Bollinger/Stochastic/Ichimoku) can be
authored as a composition and re-exported as a named record. Output
half only; param/input-role naming is the dependent sibling.
refs #40
|
||
|
Brummel
|
d8b2a2880d |
feat(aura-cli): MACD strategy PoC over the EMA node
Author MACD as a nested composite -- price -> fast/slow EMA -> Sub (MACD line) -> signal EMA -> Sub (histogram), the histogram exposed as the single output the strategy trades. A richer fixture than sma_cross: an EMA-of-EMA chain with interior fan-out (the MACD line feeds both the signal EMA and the histogram), exercising the nested-composite render shipped in cycle 0017. It runs over the real path: the composite blueprint is compiled to a flat harness via compile_with_params + Harness::bootstrap (the same machinery as the SMA compiled view), not hand-flattened. New surfaces: aura run --macd (runs the strategy, prints metrics) and aura graph --macd [--compiled]. main's arg parsing is rewritten to a whole-argv match, preserving the #16 strict contract (trailing token / unknown subcommand -> usage, exit 2). MACD gets its own longer synthetic stream because the SMA-seeded EMAs warm up; the SMA sample's stream and goldens are untouched. This PoC makes two parameter-space gaps concrete for the milestone: the strategy's param_space is [macd.length, macd.length, macd.length, scale] -- three identical names distinguishable only by slot (the named-param case, blueprint #30) -- and a composite exposes only one output port, so the MACD/signal/histogram tuple cannot all be tapped for display (the tuple-output case). The compiled view's valued labels (EMA(2)/EMA(4)/EMA(3)) are what currently disambiguate the three EMAs. Tested: MACD compiles from the nested composite and runs deterministically (C1), the trace is non-trivial (>=1 exposure sign flip), and the blueprint view renders the composite definition once. |
||
|
Brummel
|
ae1d4564f5 |
feat(aura-std): EMA node (SMA-seeded, O(1) per cycle)
Add Ema, the std-lib's first recursive/stateful producer: exponential moving average with alpha = 2/(length+1). The building block MACD (and DEMA, MACD-histogram, etc.) needs, and a worked example of a node whose param sizes its math, not its input window. Seeding is ratified as SMA-seeded (ta-lib convention): the EMA stays silent until it has seen length samples, seeds with their SMA, then runs the recurrence. Chosen over a first-value seed for three substantive reasons -- warm-up consistency with Sma (both emit None until length samples), parity with the EMA traders expect (ta-lib MACD seeds this way), and statistical honesty (no average claimed from a single observation). A first-value seed was the proof-of-concept convenience; rejected. Performance: recursive state means lookback = 1 (length sizes alpha, not the window); eval is O(1) time and state via ema += alpha*(x - ema), with no hot-path allocation (the output buffer is reused). Tested: warm-up-then-smooth (a step input separates it from a plain SMA), length-1 identity, label, and factory/schema agreement. |
||
|
Brummel
|
a4cfe5c53f |
audit: cycle 0017 (#38) — render_flat dedup + ledger #38 realization note
Architect drift review of the #38 cycle (a70c5fa..cd31447) against the design ledger. No ledger-contract drift: C23 holds (render_compilat byte-identical, compiled_view_golden green), C9/C12 honoured (the new main-graph + where:- definitions view renders a composite as an opaque authoring-level node with its body defined once — a faithful blueprint/source view vs. the inlined compiled form), the nested-composite unimplemented! is genuinely removed and tested, and no orphaned references to the removed ItemDisplay/producer_id/consumer_ids remain in crates/ (only frozen historical plan docs mention them). Two debt items, both fixed here (not carried): - [medium] crates/aura-cli/src/graph.rs — render_compilat open-coded the same Graph::with_mode/add_node/add_edge/render idiom the new render_flat helper wraps. Fixed: render_compilat now builds its edge-pairs (its Edge structs + source targets) and delegates to render_flat, so render_flat is the single flat-build point shared by all three render functions. Behaviour-preserving — same node and edge insertion order — verified by compiled_view_golden staying byte-identical. - [low] the retired cluster-box blueprint-render model and its substantive cause (ascii-dag 0.9.1's subgraph /2 centering bug; flat-only being the fix) lived only in the superseded spec 0013, not in the durable contract layer. Fixed: added a "Realization (cycle 0017 — blueprint render = main graph + definitions)" note to the ledger (INDEX.md, under the C22 blueprint-view detail) recording the opaque-node + where:-definitions model, the authoring-vs-compiled split, the ascii-dag-bug rationale, the scale/render-once/nested benefits, and the #37 playground (enter/focus) counterpart vs. #38 static CLI form. regression: profile declares no regression scripts and no architect_sweeps — the architect review is the sole gate. No baseline to update. Cycle 0017 is drift-clean after these fixes. NOT a milestone close — that needs the end-to-end milestone fieldtest, still deferred until the sweep root (#32-#33) lands. |
||
|
Brummel
|
cd31447d98 |
feat(aura-cli): blueprint view = main graph + composite definitions (#38)
Rewrite the `aura graph` blueprint view from ascii-dag subgraph cluster boxes to
a "program with subroutines" model: a flat main graph that wires the harness with
each composite shown as a single opaque node, plus a `where:` section that defines
each distinct composite type once (its interior with [in:k]/[out] port markers).
`render_compilat` (flat, fully-inlined, C23) is byte-for-byte unchanged.
Why (not effort):
- Correctness under width. ascii-dag 0.9.1's subgraph level-centering rounds
sibling x-positions with `/2`, overlapping wide sibling labels (a
width/parity-sensitive bug with no config/padding dodge that survives
unequal-width siblings; verified by reproduction). The flat layout is
collision-free; this view renders only flat graphs, so the bug cannot arise.
- Scale. A composite is one opaque node in the main graph, so blueprint size
tracks top-level wiring, not inlined node count — real strategies stay
displayable.
- Render-once. A composite reused N times has its body rendered once
(collect_distinct_composites dedups by name(), recursively).
- Removes the nested-composite `unimplemented!` — the definitions pass recurses,
so nested composites render as opaque nodes with their own definitions.
Mechanics: ItemDisplay/producer_id/consumer_ids are gone (a composite is now one
display node, so boundary fan-resolution collapses); new render_flat (the same
no-subgraph idiom render_compilat uses), collect_distinct_composites, and
render_definition. The now-unused `Target` import is dropped.
Divergence from the plan's literal text: the plan's `collect_distinct_composites`
used a nested `if let { if .. }`; this toolchain's clippy (collapsible_if, rust
1.94) rejects it under -D warnings, so it is the behaviour-identical let-chain form
`if let BlueprintNode::Composite(c) = item && !seen.contains(&c.name())`.
Tests: the two cluster-asserting blueprint tests are replaced by four behavioural
tests (opaque-node main graph; defines-each-composite-once; nested-renders-without-
panic; reused-composite-defined-once) plus a recaptured blueprint_view_golden
(captured verbatim from `aura graph`, not hand-authored). The four must-stay-green
tests pass; compiled_view_golden is byte-identical (render_compilat untouched).
Verified: `cargo test --workspace` all green, `cargo clippy --workspace
--all-targets -D warnings` clean.
The interactive enter/focus navigation counterpart is the playground's, tracked
separately as #37.
closes #38
|
||
|
Brummel
|
870dfcec5b |
plan: 0017 blueprint view as main graph + composite definitions
Two tasks, CLI-render-only (graph.rs + main.rs tests): - Task 1: rewrite render_blueprint to the main-graph + where:-definitions model (composite = opaque node; collect_distinct_composites recursive/deduped by name; render_definition with [in:k]/[out] port markers); drop ItemDisplay/producer_id/ consumer_ids and the nested-composite unimplemented!; behavioural tests RED->GREEN (opaque-node, defines-once, nested-no-panic, reuse-defined-once). - Task 2: recapture the blueprint golden from `aura graph` stdout; full-workspace test + clippy gate. render_compilat untouched (its golden stays byte-identical). refs #38 |
||
|
Brummel
|
2d3792e45f |
spec: 0017 blueprint view as main graph + composite definitions
Redesign the `aura graph` blueprint view (render_blueprint) from ascii-dag subgraph cluster boxes to a "program with subroutines" model: a small main graph that wires the harness with each composite shown as a single opaque node, plus a `where:` section rendering each distinct composite type's interior once. render_compilat (flat, fully-inlined, C23) is unchanged. Design ratified in-session. The 3a-vs-3b fork was resolved by medium: the interactive enter/focus model (3a) is the playground's, parked as #37; the static main+definitions model (3b) is the CLI's, this cycle. Substance: - Correctness under width: ascii-dag 0.9.1's subgraph level-centering rounds sibling x-positions with `/2`, overlapping wide sibling labels (a width/parity-sensitive bug with no config/padding dodge that survives unequal-width siblings). The flat layout is collision-free; the new model renders only flat graphs, so the bug cannot arise. - Scale: a composite is one opaque node in the main graph, so blueprint size tracks top-level wiring, not inlined node count — real strategies stay displayable. - Render-once: a composite reused N times has its body rendered once. - Removes the nested-composite `unimplemented!` at graph.rs:74-77 (the definitions pass is recursive). Defaults baked (not forks): composite-type dedup key = name() (assumes same name => same structure, the authoring convention); opaque-node ports shown as [in:k] / [out] markers in a definition. grounding-check PASS — all nine load-bearing assumptions ratified by green tests (Composite/Blueprint API, the flat render_compilat path, the unimplemented! site, the two replaced cluster tests, the four must-stay-green tests). spec_validation parse gate is a confirmed no-op (none configured). refs #38 |
||
|
Brummel
|
a70c5faab7 |
audit: cycle B (0016) — ledger 0016 realization note (C8/C19), debt #36 filed
Architect drift review of the #31 cycle (2a9a141..4b64409) against the design ledger. The feature is clean: C19/C23 realized literally (LeafFactory recipe; compile_with_params builds-then-wires slot-by-slot in the same walk param_space() projects — #34's dual-traversal hazard genuinely subsumed, one traversal, both mirror tests green incl. nesting); C12 "no recompile per param-set" holds (value-empty blueprint, vector-bound, bit-identity green); the removed Composite::schema/BlueprintNode::schema confirmed caller-free. ledger (fixed here): - C8: the 0015 note's "binding a value to a slot (#31) ... deferred" line was stale (shipped). Updated to record #31 landed in 0016, and that the param declaration's authoring home moved to LeafFactory.params() (read pre-build) alongside the built node's schema().params (the duplication is debt #36). - C19: added a "Realization (cycle 0016 — param-set injection)" note (the per-cycle pattern C8/C10 already carry for 0005/0006/0007/0015): the value-empty leaf, build-then-wire bootstrap_with_params/compile_with_params, the typed kind/arity errors, the bit-identical compilat, and the C22 blueprint-view bare-type label (value-bearing SMA(2) now only in the compiled view). debt (filed, carry-on): - Every param-bearing node declares its ParamSpecs twice (factory() and schema()), kept in lockstep only by a per-node test; drift compiles. Filed as #36 (sibling of #34's traversal-duplication concern). Not active drift — the agreement holds and is tested per node. regression: profile declares no regression scripts and no architect_sweeps — the architect review is the sole gate. No baseline to update. Cycle B is drift-clean after these amendments. NOT a milestone close — that needs the end-to-end milestone fieldtest, deferred until the sweep root (#32-#33) lands. |