Assemble lane results in chunk order without sorting

This commit is contained in:
2026-11-22 09:49:08 +00:00
parent c8250089b1
commit f069a10c78
2 changed files with 33 additions and 8 deletions

View File

@@ -21,7 +21,8 @@ is substantially complete. Findings 1–2 come from the initial review. Findings
Finding 1 come from a stage-ordered algorithmic pass. The latter are refactoring
opportunities for consideration, not measured production bottlenecks or new
performance guarantees. None calls for another compatibility layer or application
execution abstraction. This document records findings, not implemented fixes.
execution abstraction. The evidence below describes the reviewed baselines;
per-finding completion markers record the subsequent remediation work.
## Finding 1: Retain Genuine Native Timeouts During Concurrent Error Selection
@@ -460,6 +461,11 @@ add a mixed-resource case only if needed to verify equivalent mask routing.
## Finding 9: Traverse Dense Chunk Results Without Sorting Their Keys
**Status: Complete.** Lane assembly traverses the materializer's dense ordinals
directly, retaining artifact/diagnostic order, fallback counts, and reuse
eligibility without allocating or sorting a temporary key slice. Pipeline
concurrency/ready-job tests and race checks pass.
Priority: P3. Relevant stages: 11, 25, and 37.
### Evidence And Complexity
@@ -575,3 +581,27 @@ production model quality or performance. Intentional changes such as the hard
configuration/CLI cutover, native retry ownership, content-only cache identity,
no semantic reassessment on hits, explicit permissive fallback, and native
diagnostic visibility are part of the agreed target, not regressions.
## Remediation Completion
All nine findings are addressed in focused commits, with completion markers at
their owning findings above. Final verification after the code changes passed:
- `GOWORK=off GOPROXY=off go test ./...`.
- `GOWORK=off GOPROXY=off go vet ./...`.
- A fresh `GOWORK=off GOPROXY=off go build` to a temporary binary.
- Race tests for `internal/framework/pipeline`, `internal/framework/chunkmap`,
`internal/core/source`, `internal/cli`, and
`internal/modules/dnd/extract/scenedescriptions`.
- Executable `version`, offline pipeline validation of both maintained D&D
examples, and native spell prompt-requirements inspection.
- `git diff --check`, this document's local link destinations, and the affected
configuration-reference anchors.
The scene-cache regression covers both repartitioning directions, bypass
controls, current IDs, actual reuse without reassessment, and unusable hits.
The fallback regression exercises a real typed spell pipeline with a fake long
provider failure; focused checks retain full causes and module diagnostics.
Source/cache/capture regressions cover nonmonotonic unit order, concurrent hits,
and exact sensitivity routing without native snapshot mutation. No production
inference, new permanent validation gate, or performance guarantee was added.

View File

@@ -5,7 +5,6 @@ import (
"errors"
"fmt"
"path"
"sort"
"strings"
"sync"
"time"
@@ -333,12 +332,8 @@ func (r *Runner) runExtractJob(ctx context.Context, input RunInput, doc *source.
}
func finalizeLaneExtract(state *laneExtractState) {
indexes := make([]int, 0, len(state.results))
for index := range state.results {
indexes = append(indexes, index)
}
sort.Ints(indexes)
for _, index := range indexes {
// Materialization assigns dense ordinals; finalization follows all lane jobs.
for index := 0; index < len(state.results); index++ {
result := state.results[index]
state.values = append(state.values, result.value)
state.diagnostics = append(state.diagnostics, result.diagnostics...)