tools-retrieval-eval

Sprint 3.39 retrieval eval: scores hybrid RRF search against a frozen, DB-anchored gold set. recall.rs is a pure precision@k/recall@k evaluator, baseline.rs a pure keyed-line ratchet (no DB, no embedder, both fully unit-tested); the gold set is checked-in fixture data. main.rs is the documented Gate-2 DB-shell: connects to the live index, runs the frozen gold queries, and enforces the ratchet.

What it is for

Sprint 3.39 retrieval eval: scores hybrid RRF search against a frozen, DB-anchored gold set. recall.rs is a pure precision@k/recall@k evaluator, baseline.rs a pure keyed-line ratchet (no DB, no embedder, both fully unit-tested); the gold set is checked-in fixture data. main.rs is the documented Gate-2 DB-shell: connects to the live index, runs the frozen gold queries, and enforces the ratchet.

Capabilities

baseline (other)

Pure baseline-ratchet logic (sprint 3.39 Phase 0 task 1, DB-shell binary

Regression

Pure baseline-ratchet logic (sprint 3.39 Phase 0 task 1, DB-shell binary

gold_books_v1 (other)

Frozen, DB-anchored gold set — sprint 3.39 Class A (books, v1).

recall (other)

Pure retrieval-quality scorer (sprint 3.39 Phase 0 task 1). No DB, no

CaseResult

Pure retrieval-quality scorer (sprint 3.39 Phase 0 task 1). No DB, no

CorpusAggregate

Pure retrieval-quality scorer (sprint 3.39 Phase 0 task 1). No DB, no

EvalReport

Pure retrieval-quality scorer (sprint 3.39 Phase 0 task 1). No DB, no

GoldCase

Pure retrieval-quality scorer (sprint 3.39 Phase 0 task 1). No DB, no

How to use it

No examples/ target and no doctest in this crate's rustdoc. The tests listed under Verification are the closest executable usage.

Module structure

tools_retrieval_eval

• baseline
• gold_books_v1
• recall

flowchart TD
  n_tools_retrieval_eval["tools_retrieval_eval"]
  n_tools_retrieval_eval --> n_baseline["baseline"]
  n_tools_retrieval_eval --> n_gold_books_v1["gold_books_v1"]
  n_tools_retrieval_eval --> n_recall["recall"]

Public surface

`baseline`

`gold_books_v1`

`recall`

Re-exports. Exported here, defined elsewhere.

Boundary

Reaches into infrastructure.

Shares tier tools with 84 other crates: tools-advisory-reach, tools-archive-guard, tools-artifact-scaffold, tools-ask-ai-core, tools-ask-ais, tools-ask-gemini, tools-book, tools-book-report, … (84 total).

_What this crate deliberately does NOT own is a judgment. No committed registry records one for it, so none is stated here._

Where it sits

Tier flow. Which tiers this crate's own edges cross.

flowchart LR
  n_tools["tools"] --> n_infrastructure["infrastructure"]

Dependencies

Runtime, in this workspace.

Runtime, from outside the workspace.

Development, in this workspace.

Build. None.

Depended on by. Nothing in this workspace.

Signal flow — what reaches this crate, and what it reaches.

flowchart LR
  SELF["tools-retrieval-eval"]
  SELF -->|development| n_tools_cli_conformance["tools-cli-conformance"]
  SELF -->|runtime| n_infrastructure_doc_ingest["infrastructure-doc-ingest"]
  SELF -->|runtime| n_infrastructure_knowledge_index["infrastructure-knowledge-index"]
  classDef self fill:#1f883d,stroke:#1f883d,color:#fff;
  class SELF self;

Feature flags

flowchart LR
  n_ort["ort"] --> n_infrastructure_doc_ingest_ort["infrastructure-doc-ingest/ort"]

Targets

Error model

No public error type was detected: no public item declares a type named *Error, and no public signature returns one.

Operational characteristics

No unsafe block, unsafe fn, unsafe impl or unsafe trait was found by the parser anywhere in this crate's source.

Configuration

Related capabilities

No workspace crate depends on this one.

Verification

Evidence by module. How often each public module is named by something executable.

What the tests establish, by name:

• dropped_value_is_a_regression — src/baseline.rs
• exact_epsilon_boundary_is_not_a_regression — src/baseline.rs
• flatten_omits_recall_key_for_true_negative_case — src/baseline.rs
• improvement_is_not_a_regression — src/baseline.rs
• key_vanishing_entirely_is_a_regression_not_silently_ignored — src/baseline.rs
• new_key_not_in_baseline_is_growth_not_a_regression — src/baseline.rs
• no_regression_when_current_matches_baseline — src/baseline.rs
• parse_rejects_duplicate_key — src/baseline.rs
• parse_rejects_malformed_line — src/baseline.rs
• parse_rejects_non_numeric_value — src/baseline.rs
• parse_skips_comments_and_blank_lines — src/baseline.rs
• render_precision_quantization_is_not_a_regression — src/baseline.rs
• render_then_parse_round_trips — src/baseline.rs
• tiny_float_noise_is_not_a_regression — src/baseline.rs
• all_source_refs_are_book_prefixed — src/gold_books_v1.rs
• apache_cases_share_the_same_three_row_gold_set — src/gold_books_v1.rs
• case_ids_are_unique — src/gold_books_v1.rs
• exactly_one_true_negative_case — src/gold_books_v1.rs
• six_cases_all_library_corpus — src/gold_books_v1.rs
• cli_conforms — src/main.rs
• corpora_scored_independently — src/recall.rs
• corpus_means_are_the_real_average_not_the_sum_times_count — src/recall.rs
• dedupe_happens_before_k_truncation — src/recall.rs
• dedupe_preserves_first_occurrence_order — src/recall.rs
• duplicate_case_id_panics_in_debug — src/recall.rs
• empty_gold_slice_produces_empty_report_no_panic — src/recall.rs
• k_zero_scores_every_case_as_nothing_retrieved_no_panic — src/recall.rs
• missing_case_in_retrieved_map_scores_as_nothing_retrieved — src/recall.rs
• per_case_results_survive_even_when_corpus_aggregate_looks_healthy — src/recall.rs
• positive_case_exact_match_scores_perfect — src/recall.rs
• _… 4 more_

Documentation coverage

pie showData
    title Public items with rustdoc
    "Documented" : 9
    "No rustdoc detected" : 2

Metrics

pie showData
    title Public API by kind
    "enum" : 1
    "function" : 6
    "struct" : 4

pie showData
    title Rust source composition
    "Code" : 815
    "Blank or comment" : 224

Generation

Rendered by tools-corpus corpus readme from repository evidence alone, renderer schema 2, lexicon current. No model, network service or database was consulted. Regenerate with tools-corpus corpus readme --write; verify with --check.