llmbic 1.2.0 → 1.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -5,6 +5,35 @@ All notable changes to this project will be documented in this file.
5
5
  The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
6
6
  and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
7
7
 
8
+ ## [1.4.0] - 2026-04-18
9
+
10
+ Non-breaking. Normalizers can now read the same caller-provided `context` the rules see, so post-merge cross-field fix-ups no longer have to be closed over at extractor-declaration time. Typical use: a normalizer that reconciles extracted fields against the `sourceUrl` or per-tenant configuration passed to `extract`.
11
+
12
+ ### Added
13
+
14
+ - `Normalizer<T, TContext = unknown>` - second optional generic type parameter describing the shape of the per-call context forwarded to the normalizer's third argument. Defaults to `unknown`, so context-unaware normalizers and legacy code compile unchanged.
15
+ - `Normalizer(data, content, context?)` - third optional argument, left `undefined` when the caller passes no context.
16
+ - `MergeApplyOptions<T, TContext = unknown>` - second optional generic parameter shared with `Normalizer`, surfacing as `normalizers?: Normalizer<T, TContext>[]`.
17
+ - `merge.apply<S, TContext>(schema, rulesResult, llmResult, content, options?, context?)` - sixth optional argument forwarded verbatim to every normalizer.
18
+ - `ExtractorConfig<S, TContext>.normalizers` now types as `Normalizer<z.infer<S>, TContext>[]`, so the context flowing through rules reaches normalizers with the same compile-time shape.
19
+ - `Extractor.merge(partial, llmResult, content, context?)` - fourth optional argument. Rules are still not re-evaluated, but normalizers run here too; accepting `context` keeps them consistent with `Extractor.extract` / `Extractor.extractSync`.
20
+
21
+ ## [1.3.0] - 2026-04-18
22
+
23
+ Non-breaking. Rules can now read a caller-provided `context` object alongside `content`, so per-call metadata (locale, tenant configuration, feature flags) no longer has to be captured in rule closures at declaration time.
24
+
25
+ ### Added
26
+
27
+ - `ExtractionRule<TContext = unknown>` - optional generic type parameter describing the shape of a per-call context forwarded to `extract`. Defaults to `unknown`, so context-unaware rules and legacy code compile unchanged.
28
+ - `ExtractionRule.extract(content, context?)` - second optional argument, forwarded verbatim by `rule.apply` / `Extractor.extract` / `Extractor.extractSync`. Left `undefined` when the caller passes no context.
29
+ - `rule.create<TContext>(field, extract, options?)` - `create` is now generic over `TContext`, so typed contexts flow from the callback signature to the returned `ExtractionRule<TContext>`. `rule.regex` stays context-unaware and remains assignable to any `ExtractionRule<TContext>[]` via contextual parameter contravariance.
30
+ - `rule.apply<S, TContext>(content, rules, schema, logger?, context?)` - fifth optional argument passed through to every rule's `extract` callback.
31
+ - `ExtractorConfig<S, TContext = unknown>` and `Extractor<T, TContext = unknown>` - second optional generic parameter shared with the rules array. `Extractor.extract(content, context?)` and `Extractor.extractSync(content, context?)` forward `context` to `rule.apply`. `Extractor.merge` does not re-evaluate rules and accepts no `context`.
32
+
33
+ ### Docs
34
+
35
+ - `CONTRIBUTING.md` - documents the 5-step release procedure (tests, bump, doc, tag, publish) to keep future releases aligned with the SemVer + npm publish lifecycle.
36
+
8
37
  ## [1.2.0] - 2026-04-16
9
38
 
10
39
  Non-breaking. Production-readiness pass: per-field provenance, per-field merge policy, and pre/post LLM transformers. Token / cost tracking deliberately stays out of scope - `LlmProvider` keeps observability as a caller concern; wrap your `complete` for telemetry.
@@ -46,18 +75,18 @@ Non-breaking. Unblocks hybrid workflows that rely on nested schemas, agreement/c
46
75
  - `ExtractorConfig<S>` gains optional `normalizers`, `validators`, `policy`, `logger`.
47
76
  - `ExtractorLlmConfig` gains optional `mode`, `crossCheckHints`.
48
77
 
49
- ## [1.0.0] 2026-04-15
78
+ ## [1.0.0] - 2026-04-15
50
79
 
51
80
  Initial public release.
52
81
 
53
82
  ### Added
54
83
 
55
- - `createExtractor(config)` factory binding a Zod schema, deterministic rules and an optional LLM fallback into an extractor with `extract`, `extractSync`, `prompt`, `parse` and `merge` methods. Covers both one-shot async extraction and 4-step batch flows (extractSync prompt external LLM call parse merge).
56
- - `rule` namespace `rule.create(field, extractFn)`, `rule.regex(field, pattern, score, transform?)`, `rule.confidence(value, score)`, `rule.apply(content, rules, schema, logger?)`. Deterministic rules are pure synchronous functions returning typed matches with a confidence score in `[0, 1]`.
57
- - `merge` namespace `merge.apply(schema, rulesResult, llmResult, content, options?)` fuses rules output with LLM output, detects per-field conflicts, runs normalizers, re-validates against the Zod schema, and runs custom validators. `merge.defaultFieldPolicy` exposes the built-in fusion rules.
58
- - `prompt` namespace `prompt.build(schema, partial, options?)` emits an `LlmRequest` (`systemPrompt`, `userContent`, `responseSchema`, `knownValues`) restricted to fields missing from the deterministic pass. `prompt.parse(raw, missing, schema)` is a permissive parser that validates each field individually via Zod, drops invalid or unexpected keys, and never throws.
59
- - `validator` namespace `validator.of<T>()` returns `{ field, crossField }` factories bound to the data shape `T`, so predicates are fully typed from the field name.
60
- - `LlmProvider` contract single-method interface (`complete(request) { values }`) consumers implement to wire any backend (OpenAI, Anthropic, Ollama, custom HTTP, ...). No vendor SDK is pulled into the import graph.
84
+ - `createExtractor(config)` - factory binding a Zod schema, deterministic rules and an optional LLM fallback into an extractor with `extract`, `extractSync`, `prompt`, `parse` and `merge` methods. Covers both one-shot async extraction and 4-step batch flows (extractSync -> prompt -> external LLM call -> parse -> merge).
85
+ - `rule` namespace - `rule.create(field, extractFn)`, `rule.regex(field, pattern, score, transform?)`, `rule.confidence(value, score)`, `rule.apply(content, rules, schema, logger?)`. Deterministic rules are pure synchronous functions returning typed matches with a confidence score in `[0, 1]`.
86
+ - `merge` namespace - `merge.apply(schema, rulesResult, llmResult, content, options?)` fuses rules output with LLM output, detects per-field conflicts, runs normalizers, re-validates against the Zod schema, and runs custom validators. `merge.defaultFieldPolicy` exposes the built-in fusion rules.
87
+ - `prompt` namespace - `prompt.build(schema, partial, options?)` emits an `LlmRequest` (`systemPrompt`, `userContent`, `responseSchema`, `knownValues`) restricted to fields missing from the deterministic pass. `prompt.parse(raw, missing, schema)` is a permissive parser that validates each field individually via Zod, drops invalid or unexpected keys, and never throws.
88
+ - `validator` namespace - `validator.of<T>()` returns `{ field, crossField }` factories bound to the data shape `T`, so predicates are fully typed from the field name.
89
+ - `LlmProvider` contract - single-method interface (`complete(request) -> { values }`) consumers implement to wire any backend (OpenAI, Anthropic, Ollama, custom HTTP, ...). No vendor SDK is pulled into the import graph.
61
90
  - Per-field confidence scoring, conflict detection (`flag` / `prefer-rule` / `prefer-llm` strategies), and extraction metadata (`durationMs`, rule/LLM field counts).
62
91
  - Full TypeScript `.d.ts` output with JSDoc on every public type, method and configuration field.
63
92
  - Example wiring a local Ollama runtime under `examples/ollama.ts`.
package/README.md CHANGED
@@ -5,13 +5,13 @@
5
5
  [![license](https://img.shields.io/npm/l/llmbic.svg)](./LICENSE)
6
6
  [![node](https://img.shields.io/node/v/llmbic.svg)](https://nodejs.org)
7
7
 
8
- Hybrid data extraction deterministic rules + LLM fallback, with per-field confidence scoring.
8
+ Hybrid data extraction - deterministic rules + LLM fallback, with per-field confidence scoring.
9
9
 
10
10
  The name folds **LLM** into [*lambic*](https://en.wikipedia.org/wiki/Lambic), the Belgian beer made by blending wild fermentation with a controlled process. Same idea here: LLMs are unpredictable, rules are rigid, and the mix produces something reliable.
11
11
 
12
12
  ## Why
13
13
 
14
- Extracting structured data from unstructured text is a solved problem until you need it to be *reliable*. Rules (regex, parsers) are deterministic but brittle. LLMs understand context but hallucinate. Neither is enough alone.
14
+ Extracting structured data from unstructured text is a solved problem - until you need it to be *reliable*. Rules (regex, parsers) are deterministic but brittle. LLMs understand context but hallucinate. Neither is enough alone.
15
15
 
16
16
  Llmbic combines both: deterministic rules extract what they can with full confidence, the LLM fills in the gaps, and a merge layer detects conflicts between the two. Every field carries a confidence score. You know exactly what's trustworthy and what needs review.
17
17
 
@@ -21,7 +21,7 @@ Llmbic combines both: deterministic rules extract what they can with full confid
21
21
  npm install llmbic
22
22
  ```
23
23
 
24
- Llmbic has a single dependency: [Zod](https://zod.dev). No vendor SDK is pulled in you bring your own LLM provider via the 1-method `LlmProvider` interface (see "Writing a provider" below).
24
+ Llmbic has a single dependency: [Zod](https://zod.dev). No vendor SDK is pulled in - you bring your own LLM provider via the 1-method `LlmProvider` interface (see "Writing a provider" below).
25
25
 
26
26
  ## Quick start
27
27
 
@@ -111,7 +111,7 @@ console.log(result.confidence);
111
111
  // { total: 1.0, currency: 1.0, vendor: 0.7, date: 0.7 }
112
112
 
113
113
  console.log(result.conflicts);
114
- // [] no disagreement between rules and LLM
114
+ // [] - no disagreement between rules and LLM
115
115
  ```
116
116
 
117
117
  ### Batch / async mode (for OpenAI Batch API, job queues, etc.)
@@ -119,19 +119,19 @@ console.log(result.conflicts);
119
119
  When you manage the LLM call yourself (batching, polling, custom transport), use the 4-step API:
120
120
 
121
121
  ```typescript
122
- // Step 1 Deterministic extraction (sync, instant)
122
+ // Step 1 - Deterministic extraction (sync, instant)
123
123
  const partial = extractor.extractSync(markdown);
124
124
 
125
- // Step 2 Build the LLM request (you send it however you want)
125
+ // Step 2 - Build the LLM request (you send it however you want)
126
126
  const llmRequest = extractor.prompt(markdown, partial);
127
- // { systemPrompt, userContent, responseSchema, knownValues }
127
+ // -> { systemPrompt, userContent, responseSchema, knownValues }
128
128
 
129
129
  // ... submit to OpenAI Batch API, poll later, get the response ...
130
130
 
131
- // Step 3 Parse the raw LLM response
131
+ // Step 3 - Parse the raw LLM response
132
132
  const llmResult = extractor.parse(rawJsonResponse);
133
133
 
134
- // Step 4 Merge everything (fusion + conflict detection + validation)
134
+ // Step 4 - Merge everything (fusion + conflict detection + validation)
135
135
  const result = extractor.merge(partial, llmResult, markdown);
136
136
  ```
137
137
 
@@ -181,12 +181,12 @@ End-to-end runnable example (upload + poll + download + merge): [`examples/opena
181
181
 
182
182
  ### Per-field confidence scoring
183
183
 
184
- Every field in the result carries a confidence score (0.01.0):
184
+ Every field in the result carries a confidence score (0.0-1.0):
185
185
 
186
186
  | Source | Confidence |
187
187
  |--------|-----------|
188
188
  | Deterministic rule, exact match | 1.0 |
189
- | Deterministic rule, partial match | 0.70.9 (you decide) |
189
+ | Deterministic rule, partial match | 0.7-0.9 (you decide) |
190
190
  | LLM only | configurable default (0.7) |
191
191
  | Rule + LLM agree | 1.0 |
192
192
  | Rule + LLM disagree | 0.3 (flagged as conflict) |
@@ -223,7 +223,7 @@ result.conflicts;
223
223
  // [{ field: 'total', ruleValue: 1250, ruleConfidence: 1.0, llmValue: 1520 }]
224
224
  ```
225
225
 
226
- Three conflict strategies: `'flag'` (default keep rule value, record conflict), `'prefer-rule'`, or `'prefer-llm'`.
226
+ Three conflict strategies: `'flag'` (default - keep rule value, record conflict), `'prefer-rule'`, or `'prefer-llm'`.
227
227
 
228
228
  In the default `'fill-gaps'` mode the LLM is only asked about fields the rules could not resolve, so conflicts are impossible. To actually trigger conflict detection, opt into cross-check (see below).
229
229
 
@@ -263,6 +263,35 @@ const extractor = createExtractor({
263
263
 
264
264
  The merge step now sees two candidates per field and surfaces real disagreements through `result.conflicts`. `crossCheckHints: 'bias'` re-exposes the rule values as hints to save tokens, at the cost of confirmation bias (the LLM tends to agree with what it was shown).
265
265
 
266
+ ### Per-call context
267
+
268
+ Rules can accept a second, caller-provided argument alongside `content` so they can read per-call metadata (locale, tenant configuration, feature flags) without having to capture it in a closure at declaration time:
269
+
270
+ ```typescript
271
+ import { createExtractor, rule } from 'llmbic';
272
+ import { z } from 'zod';
273
+
274
+ type Region = { region: 'us' | 'uk' };
275
+
276
+ const schema = z.object({ price: z.string() });
277
+
278
+ const priceRule = rule.create<Region>('price', (content, context) => {
279
+ const pattern = context?.region === 'uk' ? /£\s*(\d+)/ : /\$\s*(\d+)/;
280
+ const match = content.match(pattern);
281
+ return match ? rule.confidence(match[1]!, 1) : null;
282
+ });
283
+
284
+ const extractor = createExtractor<typeof schema, Region>({
285
+ schema,
286
+ rules: [priceRule],
287
+ });
288
+
289
+ await extractor.extract('Listed at £42', { region: 'uk' });
290
+ // -> { price: '42' }
291
+ ```
292
+
293
+ The type parameter on `rule.create<TContext>` flows to the generic on `createExtractor<Schema, TContext>` and is enforced at every call site. `context` is forwarded verbatim to every rule's `extract` callback AND to every normalizer as their optional third argument; callbacks that ignore it still compile and work. `extractSync(content, context?)` behaves the same way for batch workflows. `Extractor.merge(partial, llmResult, content, context?)` does not re-evaluate rules (it reuses the partial's values) but normalizers still run, so it accepts the same optional `context`.
294
+
266
295
  ### Rich schemas
267
296
 
268
297
  The JSON Schema handed to the LLM supports the Zod constructs that show up in real-world extraction targets:
@@ -274,22 +303,35 @@ The JSON Schema handed to the LLM supports the Zod constructs that show up in re
274
303
 
275
304
  ### Normalizers
276
305
 
277
- Post-merge transformations. Run in sequence, receive the merged data + original content:
306
+ Post-merge transformations. Run in sequence, receive the merged data + original content, and optionally the same per-call `context` the rules see (see [Per-call context](#per-call-context)):
278
307
 
279
308
  ```typescript
280
- const extractor = createExtractor({
309
+ type Ctx = { sourceUrl: string };
310
+
311
+ const extractor = createExtractor<typeof MySchema, Ctx>({
281
312
  schema: MySchema,
282
313
  rules: [...],
283
314
  normalizers: [
284
315
  (data, content) => {
285
- // Fix a known data quality issue
316
+ // Rules/content-only normalizer: no context needed
286
317
  if (data.price && data.price < 100) data.price = null;
287
318
  return data;
288
319
  },
320
+ (data, _content, context) => {
321
+ // Context-aware: cross-field fix-up that depends on where the content came from
322
+ if (context && !data.city && /\/liege\//.test(context.sourceUrl)) {
323
+ data.city = 'Liège';
324
+ }
325
+ return data;
326
+ },
289
327
  ],
290
328
  });
329
+
330
+ await extractor.extract(markdown, { sourceUrl: 'https://example.be/liege/123' });
291
331
  ```
292
332
 
333
+ Context-unaware normalizers keep working unchanged - the third argument is optional and left `undefined` when the caller passes no context.
334
+
293
335
  ### Validators (invariants)
294
336
 
295
337
  Check the final output for logical consistency:
@@ -339,7 +381,7 @@ Common patterns:
339
381
 
340
382
  ## Writing a provider
341
383
 
342
- Llmbic does not ship vendor-specific adapters. The `LlmProvider` contract is a single method wiring to any backend (OpenAI, Anthropic, Ollama, vLLM, Gemini, custom HTTP, ...) is ~10 lines you write and own.
384
+ Llmbic does not ship vendor-specific adapters. The `LlmProvider` contract is a single method - wiring to any backend (OpenAI, Anthropic, Ollama, vLLM, Gemini, custom HTTP, ...) is ~10 lines you write and own.
343
385
 
344
386
  ```typescript
345
387
  import type { LlmProvider } from 'llmbic';
@@ -404,7 +446,7 @@ const provider: LlmProvider = {
404
446
  };
405
447
  ```
406
448
 
407
- **Ollama** (native `format` JSON Schema, requires Ollama 0.5+):
449
+ **Ollama** (native `format` - JSON Schema, requires Ollama 0.5+):
408
450
 
409
451
  ```typescript
410
452
  const client = new Ollama();
@@ -423,29 +465,29 @@ const provider: LlmProvider = {
423
465
  };
424
466
  ```
425
467
 
426
- Observability (token usage, latency, cost accounting) is out of scope wrap the `complete` call in whatever telemetry you already use.
468
+ Observability (token usage, latency, cost accounting) is out of scope - wrap the `complete` call in whatever telemetry you already use.
427
469
 
428
470
  ## Design decisions
429
471
 
430
- - **One dependency** Zod only. No vendor SDK ever enters the import graph; you bring your own LLM provider (see "Writing a provider").
431
- - **No retry** If the LLM returns invalid data, `parse()` does best-effort parsing (valid fields kept, invalid ignored). Retry is an orchestration concern.
432
- - **No streaming** Llmbic works with complete results. Streaming is a transport concern.
433
- - **No chunking** One content = one extraction. If your content is too long, split it before calling Llmbic.
434
- - **Normalizers mutate** For pragmatic reasons, normalizers receive and return the same object. The `merge()` function copies the data first, so the original is never modified.
435
- - **Rules are sync** Extraction rules are pure synchronous functions. If you need async lookups, do them before creating the rule.
472
+ - **One dependency** - Zod only. No vendor SDK ever enters the import graph; you bring your own LLM provider (see "Writing a provider").
473
+ - **No retry** - If the LLM returns invalid data, `parse()` does best-effort parsing (valid fields kept, invalid ignored). Retry is an orchestration concern.
474
+ - **No streaming** - Llmbic works with complete results. Streaming is a transport concern.
475
+ - **No chunking** - One content = one extraction. If your content is too long, split it before calling Llmbic.
476
+ - **Normalizers mutate** - For pragmatic reasons, normalizers receive and return the same object. The `merge()` function copies the data first, so the original is never modified.
477
+ - **Rules are sync** - Extraction rules are pure synchronous functions. If you need async lookups, do them before creating the rule.
436
478
 
437
479
  ## API reference
438
480
 
439
481
  ### `createExtractor(config)`
440
482
 
441
- Creates an extractor instance. Config:
483
+ Creates an extractor instance. Signature: `createExtractor<S, TContext = unknown>(config)`. `TContext` is optional and describes the per-call context passed to `Extractor.extract(content, context?)`; see [Per-call context](#per-call-context). Config:
442
484
 
443
485
  | Field | Type | Required | Description |
444
486
  |-------|------|----------|-------------|
445
487
  | `schema` | `ZodObject` | yes | Output schema (drives field enumeration and re-validation). |
446
- | `rules` | `ExtractionRule[]` | yes | Deterministic extraction rules. |
488
+ | `rules` | `ExtractionRule<TContext>[]` | yes | Deterministic extraction rules. |
447
489
  | `llm` | `ExtractorLlmConfig` | no | LLM fallback. Omit for rules-only mode. See below. |
448
- | `normalizers` | `Normalizer<T>[]` | no | Post-merge transformations, run in declared order. |
490
+ | `normalizers` | `Normalizer<T, TContext>[]` | no | Post-merge transformations, run in declared order. Each normalizer receives `(data, content, context?)`; `TContext` is shared with the rules array. |
449
491
  | `validators` | `Validator<ExtractedData<T>>[]` | no | Invariants populating `result.validation`. |
450
492
  | `policy` | `Partial<FieldMergePolicy>` | no | Overrides the per-field merge policy (conflict strategy, confidence defaults, equality) for every field. |
451
493
  | `policyByField` | `{ [K in keyof T]?: Partial<FieldMergePolicy> }` | no | Per-field overrides applied on top of `policy`. Precedence: defaults < `policy` < `policyByField[field]`. |
@@ -466,10 +508,10 @@ Creates an extractor instance. Config:
466
508
 
467
509
  | Member | Signature | Description |
468
510
  |---|---|---|
469
- | `rule.create` | `(field, extract, options?) => ExtractionRule` | Declare a rule. `extract(content)` returns a `RuleMatch` or `null`. `options.id` sets the stable identifier surfaced in `result.sources`. |
511
+ | `rule.create` | `<TContext = unknown>(field, extract, options?) => ExtractionRule<TContext>` | Declare a rule. `extract(content, context?)` returns a `RuleMatch` or `null`. `options.id` sets the stable identifier surfaced in `result.sources`. `TContext` is inferred from the callback when present. |
470
512
  | `rule.regex` | `(field, pattern, score, transform?, options?) => ExtractionRule` | Regex-based rule. On match, capture group 1 (or the full match) is fed to `transform`. `options.id` sets the stable identifier surfaced in `result.sources`. |
471
513
  | `rule.confidence` | `(value, score) => RuleMatch` | Wrap a value and a confidence score; sugar for custom `extract` callbacks. |
472
- | `rule.apply` | `(content, rules, schema, logger?) => RulesResult` | Run every rule, pick the highest-confidence match per field, type-check against the schema. |
514
+ | `rule.apply` | `<S, TContext = unknown>(content, rules, schema, logger?, context?) => RulesResult` | Run every rule, pick the highest-confidence match per field, type-check against the schema. `context` is forwarded verbatim to each rule's `extract` callback. |
473
515
 
474
516
  ### `validator.of<T>()`
475
517
 
@@ -484,11 +526,11 @@ Binding `T` once lets TypeScript infer each field's type from the field name, so
484
526
 
485
527
  | Method | Sync | Description |
486
528
  |--------|------|-------------|
487
- | `extract(content)` | async | Full pipeline: rules -> LLM (if configured) -> merge -> normalize -> validate. |
488
- | `extractSync(content)` | sync | Rules only. Returns the partial result + `missing` fields. |
529
+ | `extract(content, context?)` | async | Full pipeline: rules -> LLM (if configured) -> merge -> normalize -> validate. `context` is forwarded verbatim to every rule's `extract` callback. |
530
+ | `extractSync(content, context?)` | sync | Rules only. Returns the partial result + `missing` fields. `context` is forwarded verbatim to every rule's `extract` callback. |
489
531
  | `prompt(content, partial)` | sync | Builds the LLM request. Covers `partial.missing` in fill-gaps mode, every schema field in cross-check mode. |
490
532
  | `parse(raw)` | sync | Parses a raw LLM JSON response, validating each field individually. Never throws. |
491
- | `merge(partial, llmResult, content)` | sync | Merges rules + LLM, detects conflicts, normalizes, validates. |
533
+ | `merge(partial, llmResult, content, context?)` | sync | Merges rules + LLM, detects conflicts, normalizes, validates. Does not re-evaluate rules, but normalizers still run and receive `context` verbatim. |
492
534
 
493
535
  ## License
494
536
 
@@ -15,11 +15,13 @@ import type { Extractor, ExtractorConfig } from './types/extractor.types.js';
15
15
  * is parsed with {@link prompt.parse} and fused through {@link merge.apply}.
16
16
  *
17
17
  * @typeParam S - A Zod object schema describing the target data shape.
18
+ * @typeParam TContext - Shape of the optional per-call context forwarded to
19
+ * every rule's `extract` callback. Defaults to `unknown`.
18
20
  * @param config - Schema, deterministic rules, and optional LLM fallback,
19
21
  * plus `policy`, `normalizers`, `validators` and `logger` forwarded to
20
22
  * every internal {@link merge.apply} call. The logger is also forwarded
21
23
  * to {@link rule.apply} so schema-rejection warnings stay visible.
22
24
  * @returns An {@link Extractor} bound to `config.schema`.
23
25
  */
24
- export declare function createExtractor<S extends z.ZodObject<z.ZodRawShape>>(config: ExtractorConfig<S>): Extractor<z.infer<S>>;
26
+ export declare function createExtractor<S extends z.ZodObject<z.ZodRawShape>, TContext = unknown>(config: ExtractorConfig<S, TContext>): Extractor<z.infer<S>, TContext>;
25
27
  //# sourceMappingURL=extractor.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"extractor.d.ts","sourceRoot":"","sources":["../src/extractor.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAI7B,OAAO,KAAK,EAAE,SAAS,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAC;AAmD7E;;;;;;;;;;;;;;;;;;;;GAoBG;AACH,wBAAgB,eAAe,CAAC,CAAC,SAAS,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC,EAClE,MAAM,EAAE,eAAe,CAAC,CAAC,CAAC,GACzB,SAAS,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CA4EvB"}
1
+ {"version":3,"file":"extractor.d.ts","sourceRoot":"","sources":["../src/extractor.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAI7B,OAAO,KAAK,EAAE,SAAS,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAC;AAmD7E;;;;;;;;;;;;;;;;;;;;;;GAsBG;AACH,wBAAgB,eAAe,CAC7B,CAAC,SAAS,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC,EACpC,QAAQ,GAAG,OAAO,EAElB,MAAM,EAAE,eAAe,CAAC,CAAC,EAAE,QAAQ,CAAC,GACnC,SAAS,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,QAAQ,CAAC,CA4EjC"}
package/dist/extractor.js CHANGED
@@ -55,6 +55,8 @@ function stampDuration(result, startedAt) {
55
55
  * is parsed with {@link prompt.parse} and fused through {@link merge.apply}.
56
56
  *
57
57
  * @typeParam S - A Zod object schema describing the target data shape.
58
+ * @typeParam TContext - Shape of the optional per-call context forwarded to
59
+ * every rule's `extract` callback. Defaults to `unknown`.
58
60
  * @param config - Schema, deterministic rules, and optional LLM fallback,
59
61
  * plus `policy`, `normalizers`, `validators` and `logger` forwarded to
60
62
  * every internal {@link merge.apply} call. The logger is also forwarded
@@ -79,10 +81,10 @@ export function createExtractor(config) {
79
81
  logger: config.logger,
80
82
  };
81
83
  return {
82
- async extract(content) {
84
+ async extract(content, context) {
83
85
  const startedAt = performance.now();
84
- const rulesResult = rule.apply(content, config.rules, config.schema, config.logger);
85
- const partial = merge.apply(config.schema, rulesResult, null, content, mergeOptions);
86
+ const rulesResult = rule.apply(content, config.rules, config.schema, config.logger, context);
87
+ const partial = merge.apply(config.schema, rulesResult, null, content, mergeOptions, context);
86
88
  const shouldCallLlm = config.llm !== undefined &&
87
89
  (buildOptions.mode === 'cross-check' || partial.missing.length > 0);
88
90
  if (!shouldCallLlm) {
@@ -98,13 +100,13 @@ export function createExtractor(config) {
98
100
  const llmResult = config.llm.transformResponse
99
101
  ? await config.llm.transformResponse(parsedLlmResult, request)
100
102
  : parsedLlmResult;
101
- const final = merge.apply(config.schema, rulesResult, llmResult, content, mergeOptions);
103
+ const final = merge.apply(config.schema, rulesResult, llmResult, content, mergeOptions, context);
102
104
  return stampDuration(final, startedAt);
103
105
  },
104
- extractSync(content) {
106
+ extractSync(content, context) {
105
107
  const startedAt = performance.now();
106
- const rulesResult = rule.apply(content, config.rules, config.schema, config.logger);
107
- const partial = merge.apply(config.schema, rulesResult, null, content, mergeOptions);
108
+ const rulesResult = rule.apply(content, config.rules, config.schema, config.logger, context);
109
+ const partial = merge.apply(config.schema, rulesResult, null, content, mergeOptions, context);
108
110
  return stampDuration(partial, startedAt);
109
111
  },
110
112
  prompt(content, partial) {
@@ -113,10 +115,10 @@ export function createExtractor(config) {
113
115
  parse(raw) {
114
116
  return prompt.parse(config.schema, allFields, raw);
115
117
  },
116
- merge(partial, llmResult, content) {
118
+ merge(partial, llmResult, content, context) {
117
119
  const startedAt = performance.now();
118
120
  const rulesResult = rulesResultFromPartial(partial, allFields);
119
- const result = merge.apply(config.schema, rulesResult, llmResult, content, mergeOptions);
121
+ const result = merge.apply(config.schema, rulesResult, llmResult, content, mergeOptions, context);
120
122
  return stampDuration(result, startedAt);
121
123
  },
122
124
  };
@@ -1 +1 @@
1
- {"version":3,"file":"extractor.js","sourceRoot":"","sources":["../src/extractor.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,IAAI,EAAE,MAAM,YAAY,CAAC;AAClC,OAAO,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AACnC,OAAO,EAAE,MAAM,EAAE,MAAM,aAAa,CAAC;AAKrC;;;;;GAKG;AACH,SAAS,sBAAsB,CAC7B,OAA4B,EAC5B,SAA+B;IAE/B,MAAM,MAAM,GAAe,EAAE,CAAC;IAC9B,MAAM,UAAU,GAAqC,EAAE,CAAC;IACxD,MAAM,SAAS,GAAqC,EAAE,CAAC;IACvD,KAAK,MAAM,KAAK,IAAI,SAAS,EAAE,CAAC;QAC9B,MAAM,KAAK,GAAG,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QAClC,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;YACnB,SAAS;QACX,CAAC;QACD,MAAM,CAAC,KAAK,CAAC,GAAG,KAAmB,CAAC;QACpC,MAAM,eAAe,GAAG,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,CAAC;QAClD,IAAI,eAAe,KAAK,IAAI,EAAE,CAAC;YAC7B,UAAU,CAAC,KAAK,CAAC,GAAG,eAAe,CAAC;QACtC,CAAC;QACD,MAAM,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;QACtC,IAAI,MAAM,KAAK,IAAI,IAAI,QAAQ,IAAI,MAAM,EAAE,CAAC;YAC1C,SAAS,CAAC,KAAK,CAAC,GAAG,MAAM,CAAC,MAAM,CAAC;QACnC,CAAC;IACH,CAAC;IACD,OAAO,EAAE,MAAM,EAAE,UAAU,EAAE,SAAS,EAAE,OAAO,EAAE,CAAC,GAAG,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC;AAC1E,CAAC;AAED;;;;;GAKG;AACH,SAAS,aAAa,CACpB,MAA2B,EAC3B,SAAiB;IAEjB,OAAO;QACL,GAAG,MAAM;QACT,IAAI,EAAE,EAAE,GAAG,MAAM,CAAC,IAAI,EAAE,UAAU,EAAE,WAAW,CAAC,GAAG,EAAE,GAAG,SAAS,EAAE;KACpE,CAAC;AACJ,CAAC;AAED;;;;;;;;;;;;;;;;;;;;GAoBG;AACH,MAAM,UAAU,eAAe,CAC7B,MAA0B;IAG1B,MAAM,SAAS,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,KAAK,CAAmB,CAAC;IAErE,IAAI,SAAS,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC3B,MAAM,IAAI,KAAK,CAAC,yDAAyD,CAAC,CAAC;IAC7E,CAAC;IAED,MAAM,YAAY,GAAG;QACnB,YAAY,EAAE,MAAM,CAAC,GAAG,EAAE,YAAY;QACtC,IAAI,EAAE,MAAM,CAAC,GAAG,EAAE,IAAI,IAAI,WAAW;QACrC,eAAe,EAAE,MAAM,CAAC,GAAG,EAAE,eAAe,IAAI,UAAU;KAClD,CAAC;IAEX,MAAM,YAAY,GAA4B;QAC5C,MAAM,EAAE,MAAM,CAAC,MAAM;QACrB,aAAa,EAAE,MAAM,CAAC,aAAa;QACnC,WAAW,EAAE,MAAM,CAAC,WAAW;QAC/B,UAAU,EAAE,MAAM,CAAC,UAAU;QAC7B,MAAM,EAAE,MAAM,CAAC,MAAM;KACtB,CAAC;IAEF,OAAO;QACL,KAAK,CAAC,OAAO,CAAC,OAAO;YACnB,MAAM,SAAS,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;YACpC,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,MAAM,CAAC,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,MAAM,CAAC,CAAC;YACpF,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,WAAW,EAAE,IAAI,EAAE,OAAO,EAAE,YAAY,CAAC,CAAC;YAErF,MAAM,aAAa,GACjB,MAAM,CAAC,GAAG,KAAK,SAAS;gBACxB,CAAC,YAAY,CAAC,IAAI,KAAK,aAAa,IAAI,OAAO,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;YACtE,IAAI,CAAC,aAAa,EAAE,CAAC;gBACnB,OAAO,aAAa,CAAC,OAAO,EAAE,SAAS,CAAC,CAAC;YAC3C,CAAC;YAED,MAAM,YAAY,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,EAAE,OAAO,EAAE,YAAY,CAAC,CAAC;YACjF,MAAM,OAAO,GAAG,MAAM,CAAC,GAAI,CAAC,gBAAgB;gBAC1C,CAAC,CAAC,MAAM,MAAM,CAAC,GAAI,CAAC,gBAAgB,CAAC,YAAY,EAAE,OAAO,CAAC;gBAC3D,CAAC,CAAC,YAAY,CAAC;YACjB,MAAM,UAAU,GAAG,MAAM,MAAM,CAAC,GAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC;YAChE,MAAM,eAAe,GACnB,YAAY,CAAC,IAAI,KAAK,aAAa,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC;YACpE,MAAM,eAAe,GAAG,MAAM,CAAC,KAAK,CAClC,MAAM,CAAC,MAAM,EACb,eAAe,EACf,UAAU,CAAC,MAAM,CAClB,CAAC;YACF,MAAM,SAAS,GAAG,MAAM,CAAC,GAAI,CAAC,iBAAiB;gBAC7C,CAAC,CAAC,MAAM,MAAM,CAAC,GAAI,CAAC,iBAAiB,CAAC,eAAe,EAAE,OAAO,CAAC;gBAC/D,CAAC,CAAC,eAAe,CAAC;YACpB,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,WAAW,EAAE,SAAS,EAAE,OAAO,EAAE,YAAY,CAAC,CAAC;YACxF,OAAO,aAAa,CAAC,KAAK,EAAE,SAAS,CAAC,CAAC;QACzC,CAAC;QAED,WAAW,CAAC,OAAO;YACjB,MAAM,SAAS,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;YACpC,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,MAAM,CAAC,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,MAAM,CAAC,CAAC;YACpF,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,WAAW,EAAE,IAAI,EAAE,OAAO,EAAE,YAAY,CAAC,CAAC;YACrF,OAAO,aAAa,CAAC,OAAO,EAAE,SAAS,CAAC,CAAC;QAC3C,CAAC;QAED,MAAM,CAAC,OAAO,EAAE,OAAO;YACrB,OAAO,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,EAAE,OAAO,EAAE,YAAY,CAAC,CAAC;QACrE,CAAC;QAED,KAAK,CAAC,GAAG;YACP,OAAO,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,SAAS,EAAE,GAAG,CAAC,CAAC;QACrD,CAAC;QAED,KAAK,CAAC,OAAO,EAAE,SAAS,EAAE,OAAO;YAC/B,MAAM,SAAS,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;YACpC,MAAM,WAAW,GAAG,sBAAsB,CAAC,OAAO,EAAE,SAAS,CAAC,CAAC;YAC/D,MAAM,MAAM,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,WAAW,EAAE,SAAS,EAAE,OAAO,EAAE,YAAY,CAAC,CAAC;YACzF,OAAO,aAAa,CAAC,MAAM,EAAE,SAAS,CAAC,CAAC;QAC1C,CAAC;KACF,CAAC;AACJ,CAAC"}
1
+ {"version":3,"file":"extractor.js","sourceRoot":"","sources":["../src/extractor.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,IAAI,EAAE,MAAM,YAAY,CAAC;AAClC,OAAO,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AACnC,OAAO,EAAE,MAAM,EAAE,MAAM,aAAa,CAAC;AAKrC;;;;;GAKG;AACH,SAAS,sBAAsB,CAC7B,OAA4B,EAC5B,SAA+B;IAE/B,MAAM,MAAM,GAAe,EAAE,CAAC;IAC9B,MAAM,UAAU,GAAqC,EAAE,CAAC;IACxD,MAAM,SAAS,GAAqC,EAAE,CAAC;IACvD,KAAK,MAAM,KAAK,IAAI,SAAS,EAAE,CAAC;QAC9B,MAAM,KAAK,GAAG,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QAClC,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;YACnB,SAAS;QACX,CAAC;QACD,MAAM,CAAC,KAAK,CAAC,GAAG,KAAmB,CAAC;QACpC,MAAM,eAAe,GAAG,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,CAAC;QAClD,IAAI,eAAe,KAAK,IAAI,EAAE,CAAC;YAC7B,UAAU,CAAC,KAAK,CAAC,GAAG,eAAe,CAAC;QACtC,CAAC;QACD,MAAM,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;QACtC,IAAI,MAAM,KAAK,IAAI,IAAI,QAAQ,IAAI,MAAM,EAAE,CAAC;YAC1C,SAAS,CAAC,KAAK,CAAC,GAAG,MAAM,CAAC,MAAM,CAAC;QACnC,CAAC;IACH,CAAC;IACD,OAAO,EAAE,MAAM,EAAE,UAAU,EAAE,SAAS,EAAE,OAAO,EAAE,CAAC,GAAG,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC;AAC1E,CAAC;AAED;;;;;GAKG;AACH,SAAS,aAAa,CACpB,MAA2B,EAC3B,SAAiB;IAEjB,OAAO;QACL,GAAG,MAAM;QACT,IAAI,EAAE,EAAE,GAAG,MAAM,CAAC,IAAI,EAAE,UAAU,EAAE,WAAW,CAAC,GAAG,EAAE,GAAG,SAAS,EAAE;KACpE,CAAC;AACJ,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;GAsBG;AACH,MAAM,UAAU,eAAe,CAI7B,MAAoC;IAGpC,MAAM,SAAS,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,KAAK,CAAmB,CAAC;IAErE,IAAI,SAAS,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC3B,MAAM,IAAI,KAAK,CAAC,yDAAyD,CAAC,CAAC;IAC7E,CAAC;IAED,MAAM,YAAY,GAAG;QACnB,YAAY,EAAE,MAAM,CAAC,GAAG,EAAE,YAAY;QACtC,IAAI,EAAE,MAAM,CAAC,GAAG,EAAE,IAAI,IAAI,WAAW;QACrC,eAAe,EAAE,MAAM,CAAC,GAAG,EAAE,eAAe,IAAI,UAAU;KAClD,CAAC;IAEX,MAAM,YAAY,GAAsC;QACtD,MAAM,EAAE,MAAM,CAAC,MAAM;QACrB,aAAa,EAAE,MAAM,CAAC,aAAa;QACnC,WAAW,EAAE,MAAM,CAAC,WAAW;QAC/B,UAAU,EAAE,MAAM,CAAC,UAAU;QAC7B,MAAM,EAAE,MAAM,CAAC,MAAM;KACtB,CAAC;IAEF,OAAO;QACL,KAAK,CAAC,OAAO,CAAC,OAAO,EAAE,OAAO;YAC5B,MAAM,SAAS,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;YACpC,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,MAAM,CAAC,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;YAC7F,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,WAAW,EAAE,IAAI,EAAE,OAAO,EAAE,YAAY,EAAE,OAAO,CAAC,CAAC;YAE9F,MAAM,aAAa,GACjB,MAAM,CAAC,GAAG,KAAK,SAAS;gBACxB,CAAC,YAAY,CAAC,IAAI,KAAK,aAAa,IAAI,OAAO,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;YACtE,IAAI,CAAC,aAAa,EAAE,CAAC;gBACnB,OAAO,aAAa,CAAC,OAAO,EAAE,SAAS,CAAC,CAAC;YAC3C,CAAC;YAED,MAAM,YAAY,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,EAAE,OAAO,EAAE,YAAY,CAAC,CAAC;YACjF,MAAM,OAAO,GAAG,MAAM,CAAC,GAAI,CAAC,gBAAgB;gBAC1C,CAAC,CAAC,MAAM,MAAM,CAAC,GAAI,CAAC,gBAAgB,CAAC,YAAY,EAAE,OAAO,CAAC;gBAC3D,CAAC,CAAC,YAAY,CAAC;YACjB,MAAM,UAAU,GAAG,MAAM,MAAM,CAAC,GAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC;YAChE,MAAM,eAAe,GACnB,YAAY,CAAC,IAAI,KAAK,aAAa,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC;YACpE,MAAM,eAAe,GAAG,MAAM,CAAC,KAAK,CAClC,MAAM,CAAC,MAAM,EACb,eAAe,EACf,UAAU,CAAC,MAAM,CAClB,CAAC;YACF,MAAM,SAAS,GAAG,MAAM,CAAC,GAAI,CAAC,iBAAiB;gBAC7C,CAAC,CAAC,MAAM,MAAM,CAAC,GAAI,CAAC,iBAAiB,CAAC,eAAe,EAAE,OAAO,CAAC;gBAC/D,CAAC,CAAC,eAAe,CAAC;YACpB,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,WAAW,EAAE,SAAS,EAAE,OAAO,EAAE,YAAY,EAAE,OAAO,CAAC,CAAC;YACjG,OAAO,aAAa,CAAC,KAAK,EAAE,SAAS,CAAC,CAAC;QACzC,CAAC;QAED,WAAW,CAAC,OAAO,EAAE,OAAO;YAC1B,MAAM,SAAS,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;YACpC,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,MAAM,CAAC,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;YAC7F,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,WAAW,EAAE,IAAI,EAAE,OAAO,EAAE,YAAY,EAAE,OAAO,CAAC,CAAC;YAC9F,OAAO,aAAa,CAAC,OAAO,EAAE,SAAS,CAAC,CAAC;QAC3C,CAAC;QAED,MAAM,CAAC,OAAO,EAAE,OAAO;YACrB,OAAO,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,EAAE,OAAO,EAAE,YAAY,CAAC,CAAC;QACrE,CAAC;QAED,KAAK,CAAC,GAAG;YACP,OAAO,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,SAAS,EAAE,GAAG,CAAC,CAAC;QACrD,CAAC;QAED,KAAK,CAAC,OAAO,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO;YACxC,MAAM,SAAS,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;YACpC,MAAM,WAAW,GAAG,sBAAsB,CAAC,OAAO,EAAE,SAAS,CAAC,CAAC;YAC/D,MAAM,MAAM,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,WAAW,EAAE,SAAS,EAAE,OAAO,EAAE,YAAY,EAAE,OAAO,CAAC,CAAC;YAClG,OAAO,aAAa,CAAC,MAAM,EAAE,SAAS,CAAC,CAAC;QAC1C,CAAC;KACF,CAAC;AACJ,CAAC"}
package/dist/index.d.ts CHANGED
@@ -1,5 +1,5 @@
1
1
  /**
2
- * Llmbic public entry point.
2
+ * Llmbic - public entry point.
3
3
  *
4
4
  * Re-exports the five namespaces that make up the library (`createExtractor`,
5
5
  * `rule`, `merge`, `prompt`, `validator`) and every public type consumers need
package/dist/index.js CHANGED
@@ -1,5 +1,5 @@
1
1
  /**
2
- * Llmbic public entry point.
2
+ * Llmbic - public entry point.
3
3
  *
4
4
  * Re-exports the five namespaces that make up the library (`createExtractor`,
5
5
  * `rule`, `merge`, `prompt`, `validator`) and every public type consumers need
package/dist/merge.d.ts CHANGED
@@ -43,7 +43,7 @@ export declare const merge: {
43
43
  * @param field - Name of the field being merged.
44
44
  * @param ruleMatch - Value proposed by a deterministic rule, or `null` if none.
45
45
  * @param llmValue - Value proposed by the LLM, or `null` if none. Cast to `T`
46
- * without runtime type-check callers that expose `merge.field` via
46
+ * without runtime type-check - callers that expose `merge.field` via
47
47
  * `merge.apply` rely on the final Zod re-validation to reject invalid LLM values.
48
48
  * @param policy - Optional strategy and confidence overrides.
49
49
  * @param logger - Optional logger notified of unexpected runtime situations
@@ -58,19 +58,22 @@ export declare const merge: {
58
58
  * Passing `llmResult = null` runs in rules-only mode: every field keeps
59
59
  * whatever the rules produced and `meta.llmCalled` is `false`.
60
60
  *
61
- * Orchestration only the three phases (fusion, normalization, validation)
61
+ * Orchestration only - the three phases (fusion, normalization, validation)
62
62
  * each live in their own private helper above.
63
63
  *
64
64
  * Runtime fields of `meta` (`durationMs`, `tokensUsed`) are populated by
65
65
  * later slices; for now `durationMs` is `0`.
66
66
  *
67
67
  * @typeParam S - A Zod object schema.
68
+ * @typeParam TContext - Shape of the optional context forwarded to every
69
+ * normalizer. Defaults to `unknown`.
68
70
  * @param schema - Zod object schema describing the target data shape.
69
71
  * @param rulesResult - Output of {@link rule.apply} for the same schema.
70
72
  * @param llmResult - Parsed LLM response, or `null` for rules-only mode.
71
73
  * @param content - Original text the rules and LLM were derived from; forwarded to normalizers so they can cross-reference the source.
72
74
  * @param options - Optional behavior overrides (policy, normalizers, validators, logger).
75
+ * @param context - Optional caller-defined value forwarded to every normalizer's third argument. Left `undefined` when omitted.
73
76
  */
74
- apply<S extends z.ZodObject<z.ZodRawShape>>(schema: S, rulesResult: RulesResult<z.infer<S>>, llmResult: LlmResult | null, content: string, options?: MergeApplyOptions<z.infer<S>>): ExtractionResult<z.infer<S>>;
77
+ apply<S extends z.ZodObject<z.ZodRawShape>, TContext = unknown>(schema: S, rulesResult: RulesResult<z.infer<S>>, llmResult: LlmResult | null, content: string, options?: MergeApplyOptions<z.infer<S>, TContext>, context?: TContext): ExtractionResult<z.infer<S>>;
75
78
  };
76
79
  //# sourceMappingURL=merge.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"merge.d.ts","sourceRoot":"","sources":["../src/merge.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAC7B,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,yBAAyB,CAAC;AACtD,OAAO,KAAK,EAAE,SAAS,EAAE,WAAW,EAAE,MAAM,uBAAuB,CAAC;AAEpE,OAAO,KAAK,EAGV,gBAAgB,EAChB,gBAAgB,EAChB,gBAAgB,EAEhB,SAAS,EACT,iBAAiB,EAElB,MAAM,wBAAwB,CAAC;AAuKhC;;;;;GAKG;AACH,eAAO,MAAM,KAAK;IAChB;;;;;;OAMG;;QAED,6CAA6C;;QAE7C,yDAAyD;;QAEzD,sDAAsD;;QAEtD,wDAAwD;;QAExD,qGAAqG;qBACxF,OAAO,KAAK,OAAO,KAAG,OAAO;;IAQ5C;;;;;;;;;;;;;;;;;;;;OAoBG;UACG,CAAC,SACE,MAAM,aACF,SAAS,CAAC,CAAC,CAAC,GAAG,IAAI,YACpB,OAAO,WACR,OAAO,CAAC,gBAAgB,CAAC,WACzB,MAAM,GACd,gBAAgB,CAAC,CAAC,CAAC;IAgEtB;;;;;;;;;;;;;;;;;;;;OAoBG;UACG,CAAC,SAAS,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC,UAChC,CAAC,eACI,WAAW,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,aACzB,SAAS,GAAG,IAAI,WAClB,MAAM,YACL,iBAAiB,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,GACtC,gBAAgB,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;CAqChC,CAAC"}
1
+ {"version":3,"file":"merge.d.ts","sourceRoot":"","sources":["../src/merge.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAC7B,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,yBAAyB,CAAC;AACtD,OAAO,KAAK,EAAE,SAAS,EAAE,WAAW,EAAE,MAAM,uBAAuB,CAAC;AAEpE,OAAO,KAAK,EAGV,gBAAgB,EAChB,gBAAgB,EAChB,gBAAgB,EAEhB,SAAS,EACT,iBAAiB,EAElB,MAAM,wBAAwB,CAAC;AA0KhC;;;;;GAKG;AACH,eAAO,MAAM,KAAK;IAChB;;;;;;OAMG;;QAED,6CAA6C;;QAE7C,yDAAyD;;QAEzD,sDAAsD;;QAEtD,wDAAwD;;QAExD,qGAAqG;qBACxF,OAAO,KAAK,OAAO,KAAG,OAAO;;IAQ5C;;;;;;;;;;;;;;;;;;;;OAoBG;UACG,CAAC,SACE,MAAM,aACF,SAAS,CAAC,CAAC,CAAC,GAAG,IAAI,YACpB,OAAO,WACR,OAAO,CAAC,gBAAgB,CAAC,WACzB,MAAM,GACd,gBAAgB,CAAC,CAAC,CAAC;IAgEtB;;;;;;;;;;;;;;;;;;;;;;;OAuBG;UACG,CAAC,SAAS,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC,EAAE,QAAQ,oBAC1C,CAAC,eACI,WAAW,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,aACzB,SAAS,GAAG,IAAI,WAClB,MAAM,YACL,iBAAiB,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,QAAQ,CAAC,YACvC,QAAQ,GACjB,gBAAgB,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;CAqChC,CAAC"}
package/dist/merge.js CHANGED
@@ -12,7 +12,7 @@ function fuseAllFields(schemaKeys, rulesResult, llmResult, policy, policyByField
12
12
  let rulesMatched = 0;
13
13
  for (const field of schemaKeys) {
14
14
  const hasRuleValue = field in rulesResult.values;
15
- // hasRuleValue implies confidence[field] is defined rule.apply only writes
15
+ // hasRuleValue implies confidence[field] is defined - rule.apply only writes
16
16
  // to `confidence` when it also writes to `values`.
17
17
  const ruleMatch = hasRuleValue
18
18
  ? {
@@ -83,12 +83,14 @@ function deriveSource(fused, ruleMatch, llmValue, policy, ruleId) {
83
83
  /**
84
84
  * Apply every configured {@link Normalizer} to the merged data in declared
85
85
  * order. Normalizers may mutate their argument; the returned reference is
86
- * what the rest of the pipeline observes.
86
+ * what the rest of the pipeline observes. The caller-provided `context` is
87
+ * forwarded verbatim to every normalizer (left `undefined` when the caller
88
+ * passed none).
87
89
  */
88
- function runNormalizers(data, normalizers, content) {
90
+ function runNormalizers(data, normalizers, content, context) {
89
91
  let current = data;
90
92
  for (const normalizer of normalizers ?? []) {
91
- current = normalizer(current, content);
93
+ current = normalizer(current, content, context);
92
94
  }
93
95
  return current;
94
96
  }
@@ -167,7 +169,7 @@ export const merge = {
167
169
  * @param field - Name of the field being merged.
168
170
  * @param ruleMatch - Value proposed by a deterministic rule, or `null` if none.
169
171
  * @param llmValue - Value proposed by the LLM, or `null` if none. Cast to `T`
170
- * without runtime type-check callers that expose `merge.field` via
172
+ * without runtime type-check - callers that expose `merge.field` via
171
173
  * `merge.apply` rely on the final Zod re-validation to reject invalid LLM values.
172
174
  * @param policy - Optional strategy and confidence overrides.
173
175
  * @param logger - Optional logger notified of unexpected runtime situations
@@ -239,23 +241,26 @@ export const merge = {
239
241
  * Passing `llmResult = null` runs in rules-only mode: every field keeps
240
242
  * whatever the rules produced and `meta.llmCalled` is `false`.
241
243
  *
242
- * Orchestration only the three phases (fusion, normalization, validation)
244
+ * Orchestration only - the three phases (fusion, normalization, validation)
243
245
  * each live in their own private helper above.
244
246
  *
245
247
  * Runtime fields of `meta` (`durationMs`, `tokensUsed`) are populated by
246
248
  * later slices; for now `durationMs` is `0`.
247
249
  *
248
250
  * @typeParam S - A Zod object schema.
251
+ * @typeParam TContext - Shape of the optional context forwarded to every
252
+ * normalizer. Defaults to `unknown`.
249
253
  * @param schema - Zod object schema describing the target data shape.
250
254
  * @param rulesResult - Output of {@link rule.apply} for the same schema.
251
255
  * @param llmResult - Parsed LLM response, or `null` for rules-only mode.
252
256
  * @param content - Original text the rules and LLM were derived from; forwarded to normalizers so they can cross-reference the source.
253
257
  * @param options - Optional behavior overrides (policy, normalizers, validators, logger).
258
+ * @param context - Optional caller-defined value forwarded to every normalizer's third argument. Left `undefined` when omitted.
254
259
  */
255
- apply(schema, rulesResult, llmResult, content, options) {
260
+ apply(schema, rulesResult, llmResult, content, options, context) {
256
261
  const schemaKeys = Object.keys(schema.shape);
257
262
  const fusion = fuseAllFields(schemaKeys, rulesResult, llmResult, options?.policy, options?.policyByField, options?.logger);
258
- const normalized = runNormalizers(fusion.data, options?.normalizers, content);
263
+ const normalized = runNormalizers(fusion.data, options?.normalizers, content, context);
259
264
  const violations = collectViolations(schema, normalized, fusion.missing, options?.validators);
260
265
  const valid = !violations.some((v) => v.severity === 'error');
261
266
  return {
package/dist/merge.js.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"merge.js","sourceRoot":"","sources":["../src/merge.ts"],"names":[],"mappings":"AAyBA;;;;GAIG;AACH,SAAS,aAAa,CACpB,UAAuB,EACvB,WAA2B,EAC3B,SAA2B,EAC3B,MAA6C,EAC7C,aAAyE,EACzE,MAA0B;IAE1B,MAAM,IAAI,GAAG,EAAsB,CAAC;IACpC,MAAM,UAAU,GAAG,EAAuC,CAAC;IAC3D,MAAM,OAAO,GAAG,EAA4C,CAAC;IAC7D,MAAM,SAAS,GAAe,EAAE,CAAC;IACjC,MAAM,OAAO,GAAgB,EAAE,CAAC;IAChC,IAAI,YAAY,GAAG,CAAC,CAAC;IAErB,KAAK,MAAM,KAAK,IAAI,UAAU,EAAE,CAAC;QAC/B,MAAM,YAAY,GAAG,KAAK,IAAI,WAAW,CAAC,MAAM,CAAC;QACjD,6EAA6E;QAC7E,mDAAmD;QACnD,MAAM,SAAS,GAA8B,YAAY;YACvD,CAAC,CAAC;gBACE,KAAK,EAAE,WAAW,CAAC,MAAM,CAAC,KAAK,CAAC;gBAChC,UAAU,EAAE,WAAW,CAAC,UAAU,CAAC,KAAK,CAAW;aACpD;YACH,CAAC,CAAC,IAAI,CAAC;QACT,IAAI,YAAY,EAAE,CAAC;YACjB,YAAY,IAAI,CAAC,CAAC;QACpB,CAAC;QAED,MAAM,QAAQ,GAAG,SAAS,EAAE,MAAM,CAAC,KAAe,CAAC,IAAI,IAAI,CAAC;QAE5D,MAAM,aAAa,GAAG,aAAa,EAAE,CAAC,KAAK,CAAC,CAAC;QAC7C,MAAM,cAAc,GAClB,aAAa,KAAK,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,GAAG,MAAM,EAAE,GAAG,aAAa,EAAE,CAAC;QACzE,MAAM,MAAM,GAAG,WAAW,CAAC,SAAS,EAAE,CAAC,KAAK,CAAC,CAAC;QAE9C,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,KAAe,EAAE,SAAS,EAAE,QAAQ,EAAE,cAAc,EAAE,MAAM,CAAC,CAAC;QAExF,IAAI,CAAC,KAAK,CAAC,GAAG,KAAK,CAAC,KAA0B,CAAC;QAC/C,UAAU,CAAC,KAAK,CAAC,GAAG,KAAK,CAAC,UAAU,CAAC;QACrC,OAAO,CAAC,KAAK,CAAC,GAAG,YAAY,CAAC,KAAK,EAAE,SAAS,EAAE,QAAQ,EAAE,cAAc,EAAE,MAAM,CAAC,CAAC;QAClF,IAAI,KAAK,CAAC,QAAQ,KAAK,SAAS,EAAE,CAAC;YACjC,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC;QACjC,CAAC;QACD,IAAI,KAAK,CAAC,KAAK,KAAK,IAAI,EAAE,CAAC;YACzB,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QACtB,CAAC;IACH,CAAC;IAED,OAAO,EAAE,IAAI,EAAE,UAAU,EAAE,OAAO,EAAE,SAAS,EAAE,OAAO,EAAE,YAAY,EAAE,CAAC;AACzE,CAAC;AAED;;;;;;;;;;;;;;;;;GAiBG;AACH,SAAS,YAAY,CACnB,KAAgC,EAChC,SAAoC,EACpC,QAAiB,EACjB,MAA6C,EAC7C,MAA0B;IAE1B,IAAI,KAAK,CAAC,KAAK,KAAK,IAAI,EAAE,CAAC;QACzB,OAAO,IAAI,CAAC;IACd,CAAC;IACD,MAAM,EAAE,GAAG,MAAM,IAAI,EAAE,CAAC;IACxB,IAAI,SAAS,KAAK,IAAI,EAAE,CAAC;QACvB,OAAO,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC;IACzB,CAAC;IACD,IAAI,QAAQ,KAAK,IAAI,IAAI,QAAQ,KAAK,SAAS,EAAE,CAAC;QAChD,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC;IACtC,CAAC;IACD,IAAI,KAAK,CAAC,QAAQ,KAAK,SAAS,EAAE,CAAC;QACjC,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC;IACtC,CAAC;IACD,IAAI,KAAK,CAAC,KAAK,KAAK,SAAS,CAAC,KAAK,EAAE,CAAC;QACpC,OAAO,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC;IACzB,CAAC;IACD,MAAM,OAAO,GAAG,MAAM,EAAE,OAAO,IAAI,KAAK,CAAC,kBAAkB,CAAC,OAAO,CAAC;IACpE,OAAO,OAAO,CAAC,SAAS,CAAC,KAAK,EAAE,QAAQ,CAAC;QACvC,CAAC,CAAC,EAAE,IAAI,EAAE,WAAW,EAAE,MAAM,EAAE,EAAE,EAAE;QACnC,CAAC,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC;AACnC,CAAC;AAED;;;;GAIG;AACH,SAAS,cAAc,CACrB,IAAsB,EACtB,WAAwC,EACxC,OAAe;IAEf,IAAI,OAAO,GAAG,IAAI,CAAC;IACnB,KAAK,MAAM,UAAU,IAAI,WAAW,IAAI,EAAE,EAAE,CAAC;QAC3C,OAAO,GAAG,UAAU,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC;IACzC,CAAC;IACD,OAAO,OAAO,CAAC;AACjB,CAAC;AAED;;;;GAIG;AACH,SAAS,iBAAiB,CACxB,MAAkC,EAClC,UAA4B,EAC5B,OAAoB,EACpB,UAA8C;IAE9C,MAAM,UAAU,GAAgB,EAAE,CAAC;IACnC,MAAM,UAAU,GAAG,IAAI,GAAG,CAAC,OAAmB,CAAC,CAAC;IAChD,MAAM,MAAM,GAAG,MAAM,CAAC,SAAS,CAAC,UAAU,CAAC,CAAC;IAC5C,IAAI,CAAC,MAAM,CAAC,OAAO,EAAE,CAAC;QACpB,KAAK,MAAM,KAAK,IAAI,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC;YACxC,MAAM,CAAC,SAAS,CAAC,GAAG,KAAK,CAAC,IAAI,CAAC;YAC/B,MAAM,KAAK,GAAG,OAAO,SAAS,KAAK,QAAQ,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC;YACpE,IAAI,KAAK,KAAK,SAAS,IAAI,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC;gBACjD,SAAS;YACX,CAAC;YACD,UAAU,CAAC,IAAI,CAAC;gBACd,KAAK;gBACL,IAAI,EAAE,QAAQ;gBACd,OAAO,EAAE,KAAK,CAAC,OAAO;gBACtB,QAAQ,EAAE,OAAO;aAClB,CAAC,CAAC;QACL,CAAC;IACH,CAAC;IACD,KAAK,MAAM,SAAS,IAAI,UAAU,IAAI,EAAE,EAAE,CAAC;QACzC,UAAU,CAAC,IAAI,CAAC,GAAG,SAAS,CAAC,UAAU,CAAC,CAAC,CAAC;IAC5C,CAAC;IACD,OAAO,UAAU,CAAC;AACpB,CAAC;AAED;;;;;GAKG;AACH,MAAM,CAAC,MAAM,KAAK,GAAG;IACnB;;;;;;OAMG;IACH,kBAAkB,EAAE;QAClB,6CAA6C;QAC7C,QAAQ,EAAE,MAAM;QAChB,yDAAyD;QACzD,oBAAoB,EAAE,GAAG;QACzB,sDAAsD;QACtD,iBAAiB,EAAE,GAAG;QACtB,wDAAwD;QACxD,mBAAmB,EAAE,GAAG;QACxB,qGAAqG;QACrG,OAAO,EAAE,CAAC,CAAU,EAAE,CAAU,EAAW,EAAE;YAC3C,IAAI,OAAO,CAAC,KAAK,QAAQ,IAAI,OAAO,CAAC,KAAK,QAAQ,EAAE,CAAC;gBACnD,OAAO,CAAC,CAAC,WAAW,EAAE,KAAK,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7C,CAAC;YACD,OAAO,CAAC,KAAK,CAAC,CAAC;QACjB,CAAC;KACyB;IAE5B;;;;;;;;;;;;;;;;;;;;OAoBG;IACH,KAAK,CACH,KAAa,EACb,SAA8B,EAC9B,QAAiB,EACjB,MAAkC,EAClC,MAAe;QAEf,MAAM,UAAU,GAAqB,EAAE,GAAG,KAAK,CAAC,kBAAkB,EAAE,GAAG,MAAM,EAAE,CAAC;QAChF,MAAM,aAAa,GAAG,QAAQ,IAAI,IAAI,CAAC;QAEvC,IAAI,SAAS,KAAK,IAAI,IAAI,aAAa,KAAK,IAAI,EAAE,CAAC;YACjD,OAAO;gBACL,KAAK,EAAE,SAAS,CAAC,KAAK;gBACtB,UAAU,EAAE,SAAS,CAAC,UAAU;gBAChC,QAAQ,EAAE,SAAS;aACpB,CAAC;QACJ,CAAC;QAED,IAAI,SAAS,KAAK,IAAI,IAAI,aAAa,KAAK,IAAI,EAAE,CAAC;YACjD,OAAO;gBACL,KAAK,EAAE,aAAkB;gBACzB,UAAU,EAAE,UAAU,CAAC,oBAAoB;gBAC3C,QAAQ,EAAE,SAAS;aACpB,CAAC;QACJ,CAAC;QAED,IAAI,SAAS,KAAK,IAAI,IAAI,aAAa,KAAK,IAAI,EAAE,CAAC;YACjD,OAAO,EAAE,KAAK,EAAE,IAAI,EAAE,UAAU,EAAE,IAAI,EAAE,QAAQ,EAAE,SAAS,EAAE,CAAC;QAChE,CAAC;QAED,IAAI,UAAU,CAAC,OAAO,CAAC,SAAS,CAAC,KAAK,EAAE,aAAa,CAAC,EAAE,CAAC;YACvD,OAAO;gBACL,KAAK,EAAE,SAAS,CAAC,KAAK;gBACtB,UAAU,EAAE,UAAU,CAAC,mBAAmB;gBAC1C,QAAQ,EAAE,SAAS;aACpB,CAAC;QACJ,CAAC;QAED,IAAI,UAAU,CAAC,QAAQ,KAAK,aAAa,EAAE,CAAC;YAC1C,OAAO;gBACL,KAAK,EAAE,SAAS,CAAC,KAAK;gBACtB,UAAU,EAAE,SAAS,CAAC,UAAU;gBAChC,QAAQ,EAAE,SAAS;aACpB,CAAC;QACJ,CAAC;QACD,IAAI,UAAU,CAAC,QAAQ,KAAK,YAAY,EAAE,CAAC;YACzC,OAAO;gBACL,KAAK,EAAE,aAAkB;gBACzB,UAAU,EAAE,UAAU,CAAC,oBAAoB;gBAC3C,QAAQ,EAAE,SAAS;aACpB,CAAC;QACJ,CAAC;QACD,IAAI,UAAU,CAAC,QAAQ,KAAK,MAAM,EAAE,CAAC;YACnC,MAAM,EAAE,IAAI,CAAC,iDAAiD,EAAE;gBAC9D,QAAQ,EAAE,UAAU,CAAC,QAAQ;gBAC7B,KAAK;aACN,CAAC,CAAC;QACL,CAAC;QACD,OAAO;YACL,KAAK,EAAE,SAAS,CAAC,KAAK;YACtB,UAAU,EAAE,UAAU,CAAC,iBAAiB;YACxC,QAAQ,EAAE;gBACR,KAAK;gBACL,SAAS,EAAE,SAAS,CAAC,KAAK;gBAC1B,cAAc,EAAE,SAAS,CAAC,UAAU;gBACpC,QAAQ,EAAE,aAAa;aACxB;SACF,CAAC;IACJ,CAAC;IAED;;;;;;;;;;;;;;;;;;;;OAoBG;IACH,KAAK,CACH,MAAS,EACT,WAAoC,EACpC,SAA2B,EAC3B,OAAe,EACf,OAAuC;QAGvC,MAAM,UAAU,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,KAAK,CAAmB,CAAC;QAE/D,MAAM,MAAM,GAAG,aAAa,CAC1B,UAAU,EACV,WAAW,EACX,SAAS,EACT,OAAO,EAAE,MAAM,EACf,OAAO,EAAE,aAAa,EACtB,OAAO,EAAE,MAAM,CAChB,CAAC;QAEF,MAAM,UAAU,GAAG,cAAc,CAAC,MAAM,CAAC,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,OAAO,CAAC,CAAC;QAE9E,MAAM,UAAU,GAAG,iBAAiB,CAClC,MAAM,EACN,UAAU,EACV,MAAM,CAAC,OAAO,EACd,OAAO,EAAE,UAAU,CACpB,CAAC;QACF,MAAM,KAAK,GAAG,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,OAAO,CAAC,CAAC;QAE9D,OAAO;YACL,IAAI,EAAE,UAAU;YAChB,UAAU,EAAE,MAAM,CAAC,UAAU;YAC7B,OAAO,EAAE,MAAM,CAAC,OAAO;YACvB,SAAS,EAAE,MAAM,CAAC,SAAS;YAC3B,OAAO,EAAE,MAAM,CAAC,OAAO;YACvB,UAAU,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE;YACjC,IAAI,EAAE;gBACJ,YAAY,EAAE,MAAM,CAAC,YAAY;gBACjC,SAAS,EAAE,SAAS,KAAK,IAAI;gBAC7B,UAAU,EAAE,CAAC;aACd;SACF,CAAC;IACJ,CAAC;CACF,CAAC"}
1
+ {"version":3,"file":"merge.js","sourceRoot":"","sources":["../src/merge.ts"],"names":[],"mappings":"AAyBA;;;;GAIG;AACH,SAAS,aAAa,CACpB,UAAuB,EACvB,WAA2B,EAC3B,SAA2B,EAC3B,MAA6C,EAC7C,aAAyE,EACzE,MAA0B;IAE1B,MAAM,IAAI,GAAG,EAAsB,CAAC;IACpC,MAAM,UAAU,GAAG,EAAuC,CAAC;IAC3D,MAAM,OAAO,GAAG,EAA4C,CAAC;IAC7D,MAAM,SAAS,GAAe,EAAE,CAAC;IACjC,MAAM,OAAO,GAAgB,EAAE,CAAC;IAChC,IAAI,YAAY,GAAG,CAAC,CAAC;IAErB,KAAK,MAAM,KAAK,IAAI,UAAU,EAAE,CAAC;QAC/B,MAAM,YAAY,GAAG,KAAK,IAAI,WAAW,CAAC,MAAM,CAAC;QACjD,6EAA6E;QAC7E,mDAAmD;QACnD,MAAM,SAAS,GAA8B,YAAY;YACvD,CAAC,CAAC;gBACE,KAAK,EAAE,WAAW,CAAC,MAAM,CAAC,KAAK,CAAC;gBAChC,UAAU,EAAE,WAAW,CAAC,UAAU,CAAC,KAAK,CAAW;aACpD;YACH,CAAC,CAAC,IAAI,CAAC;QACT,IAAI,YAAY,EAAE,CAAC;YACjB,YAAY,IAAI,CAAC,CAAC;QACpB,CAAC;QAED,MAAM,QAAQ,GAAG,SAAS,EAAE,MAAM,CAAC,KAAe,CAAC,IAAI,IAAI,CAAC;QAE5D,MAAM,aAAa,GAAG,aAAa,EAAE,CAAC,KAAK,CAAC,CAAC;QAC7C,MAAM,cAAc,GAClB,aAAa,KAAK,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,GAAG,MAAM,EAAE,GAAG,aAAa,EAAE,CAAC;QACzE,MAAM,MAAM,GAAG,WAAW,CAAC,SAAS,EAAE,CAAC,KAAK,CAAC,CAAC;QAE9C,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,KAAe,EAAE,SAAS,EAAE,QAAQ,EAAE,cAAc,EAAE,MAAM,CAAC,CAAC;QAExF,IAAI,CAAC,KAAK,CAAC,GAAG,KAAK,CAAC,KAA0B,CAAC;QAC/C,UAAU,CAAC,KAAK,CAAC,GAAG,KAAK,CAAC,UAAU,CAAC;QACrC,OAAO,CAAC,KAAK,CAAC,GAAG,YAAY,CAAC,KAAK,EAAE,SAAS,EAAE,QAAQ,EAAE,cAAc,EAAE,MAAM,CAAC,CAAC;QAClF,IAAI,KAAK,CAAC,QAAQ,KAAK,SAAS,EAAE,CAAC;YACjC,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC;QACjC,CAAC;QACD,IAAI,KAAK,CAAC,KAAK,KAAK,IAAI,EAAE,CAAC;YACzB,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QACtB,CAAC;IACH,CAAC;IAED,OAAO,EAAE,IAAI,EAAE,UAAU,EAAE,OAAO,EAAE,SAAS,EAAE,OAAO,EAAE,YAAY,EAAE,CAAC;AACzE,CAAC;AAED;;;;;;;;;;;;;;;;;GAiBG;AACH,SAAS,YAAY,CACnB,KAAgC,EAChC,SAAoC,EACpC,QAAiB,EACjB,MAA6C,EAC7C,MAA0B;IAE1B,IAAI,KAAK,CAAC,KAAK,KAAK,IAAI,EAAE,CAAC;QACzB,OAAO,IAAI,CAAC;IACd,CAAC;IACD,MAAM,EAAE,GAAG,MAAM,IAAI,EAAE,CAAC;IACxB,IAAI,SAAS,KAAK,IAAI,EAAE,CAAC;QACvB,OAAO,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC;IACzB,CAAC;IACD,IAAI,QAAQ,KAAK,IAAI,IAAI,QAAQ,KAAK,SAAS,EAAE,CAAC;QAChD,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC;IACtC,CAAC;IACD,IAAI,KAAK,CAAC,QAAQ,KAAK,SAAS,EAAE,CAAC;QACjC,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC;IACtC,CAAC;IACD,IAAI,KAAK,CAAC,KAAK,KAAK,SAAS,CAAC,KAAK,EAAE,CAAC;QACpC,OAAO,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC;IACzB,CAAC;IACD,MAAM,OAAO,GAAG,MAAM,EAAE,OAAO,IAAI,KAAK,CAAC,kBAAkB,CAAC,OAAO,CAAC;IACpE,OAAO,OAAO,CAAC,SAAS,CAAC,KAAK,EAAE,QAAQ,CAAC;QACvC,CAAC,CAAC,EAAE,IAAI,EAAE,WAAW,EAAE,MAAM,EAAE,EAAE,EAAE;QACnC,CAAC,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC;AACnC,CAAC;AAED;;;;;;GAMG;AACH,SAAS,cAAc,CACrB,IAAsB,EACtB,WAAkD,EAClD,OAAe,EACf,OAA6B;IAE7B,IAAI,OAAO,GAAG,IAAI,CAAC;IACnB,KAAK,MAAM,UAAU,IAAI,WAAW,IAAI,EAAE,EAAE,CAAC;QAC3C,OAAO,GAAG,UAAU,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,CAAC;IAClD,CAAC;IACD,OAAO,OAAO,CAAC;AACjB,CAAC;AAED;;;;GAIG;AACH,SAAS,iBAAiB,CACxB,MAAkC,EAClC,UAA4B,EAC5B,OAAoB,EACpB,UAA8C;IAE9C,MAAM,UAAU,GAAgB,EAAE,CAAC;IACnC,MAAM,UAAU,GAAG,IAAI,GAAG,CAAC,OAAmB,CAAC,CAAC;IAChD,MAAM,MAAM,GAAG,MAAM,CAAC,SAAS,CAAC,UAAU,CAAC,CAAC;IAC5C,IAAI,CAAC,MAAM,CAAC,OAAO,EAAE,CAAC;QACpB,KAAK,MAAM,KAAK,IAAI,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC;YACxC,MAAM,CAAC,SAAS,CAAC,GAAG,KAAK,CAAC,IAAI,CAAC;YAC/B,MAAM,KAAK,GAAG,OAAO,SAAS,KAAK,QAAQ,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC;YACpE,IAAI,KAAK,KAAK,SAAS,IAAI,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC;gBACjD,SAAS;YACX,CAAC;YACD,UAAU,CAAC,IAAI,CAAC;gBACd,KAAK;gBACL,IAAI,EAAE,QAAQ;gBACd,OAAO,EAAE,KAAK,CAAC,OAAO;gBACtB,QAAQ,EAAE,OAAO;aAClB,CAAC,CAAC;QACL,CAAC;IACH,CAAC;IACD,KAAK,MAAM,SAAS,IAAI,UAAU,IAAI,EAAE,EAAE,CAAC;QACzC,UAAU,CAAC,IAAI,CAAC,GAAG,SAAS,CAAC,UAAU,CAAC,CAAC,CAAC;IAC5C,CAAC;IACD,OAAO,UAAU,CAAC;AACpB,CAAC;AAED;;;;;GAKG;AACH,MAAM,CAAC,MAAM,KAAK,GAAG;IACnB;;;;;;OAMG;IACH,kBAAkB,EAAE;QAClB,6CAA6C;QAC7C,QAAQ,EAAE,MAAM;QAChB,yDAAyD;QACzD,oBAAoB,EAAE,GAAG;QACzB,sDAAsD;QACtD,iBAAiB,EAAE,GAAG;QACtB,wDAAwD;QACxD,mBAAmB,EAAE,GAAG;QACxB,qGAAqG;QACrG,OAAO,EAAE,CAAC,CAAU,EAAE,CAAU,EAAW,EAAE;YAC3C,IAAI,OAAO,CAAC,KAAK,QAAQ,IAAI,OAAO,CAAC,KAAK,QAAQ,EAAE,CAAC;gBACnD,OAAO,CAAC,CAAC,WAAW,EAAE,KAAK,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7C,CAAC;YACD,OAAO,CAAC,KAAK,CAAC,CAAC;QACjB,CAAC;KACyB;IAE5B;;;;;;;;;;;;;;;;;;;;OAoBG;IACH,KAAK,CACH,KAAa,EACb,SAA8B,EAC9B,QAAiB,EACjB,MAAkC,EAClC,MAAe;QAEf,MAAM,UAAU,GAAqB,EAAE,GAAG,KAAK,CAAC,kBAAkB,EAAE,GAAG,MAAM,EAAE,CAAC;QAChF,MAAM,aAAa,GAAG,QAAQ,IAAI,IAAI,CAAC;QAEvC,IAAI,SAAS,KAAK,IAAI,IAAI,aAAa,KAAK,IAAI,EAAE,CAAC;YACjD,OAAO;gBACL,KAAK,EAAE,SAAS,CAAC,KAAK;gBACtB,UAAU,EAAE,SAAS,CAAC,UAAU;gBAChC,QAAQ,EAAE,SAAS;aACpB,CAAC;QACJ,CAAC;QAED,IAAI,SAAS,KAAK,IAAI,IAAI,aAAa,KAAK,IAAI,EAAE,CAAC;YACjD,OAAO;gBACL,KAAK,EAAE,aAAkB;gBACzB,UAAU,EAAE,UAAU,CAAC,oBAAoB;gBAC3C,QAAQ,EAAE,SAAS;aACpB,CAAC;QACJ,CAAC;QAED,IAAI,SAAS,KAAK,IAAI,IAAI,aAAa,KAAK,IAAI,EAAE,CAAC;YACjD,OAAO,EAAE,KAAK,EAAE,IAAI,EAAE,UAAU,EAAE,IAAI,EAAE,QAAQ,EAAE,SAAS,EAAE,CAAC;QAChE,CAAC;QAED,IAAI,UAAU,CAAC,OAAO,CAAC,SAAS,CAAC,KAAK,EAAE,aAAa,CAAC,EAAE,CAAC;YACvD,OAAO;gBACL,KAAK,EAAE,SAAS,CAAC,KAAK;gBACtB,UAAU,EAAE,UAAU,CAAC,mBAAmB;gBAC1C,QAAQ,EAAE,SAAS;aACpB,CAAC;QACJ,CAAC;QAED,IAAI,UAAU,CAAC,QAAQ,KAAK,aAAa,EAAE,CAAC;YAC1C,OAAO;gBACL,KAAK,EAAE,SAAS,CAAC,KAAK;gBACtB,UAAU,EAAE,SAAS,CAAC,UAAU;gBAChC,QAAQ,EAAE,SAAS;aACpB,CAAC;QACJ,CAAC;QACD,IAAI,UAAU,CAAC,QAAQ,KAAK,YAAY,EAAE,CAAC;YACzC,OAAO;gBACL,KAAK,EAAE,aAAkB;gBACzB,UAAU,EAAE,UAAU,CAAC,oBAAoB;gBAC3C,QAAQ,EAAE,SAAS;aACpB,CAAC;QACJ,CAAC;QACD,IAAI,UAAU,CAAC,QAAQ,KAAK,MAAM,EAAE,CAAC;YACnC,MAAM,EAAE,IAAI,CAAC,iDAAiD,EAAE;gBAC9D,QAAQ,EAAE,UAAU,CAAC,QAAQ;gBAC7B,KAAK;aACN,CAAC,CAAC;QACL,CAAC;QACD,OAAO;YACL,KAAK,EAAE,SAAS,CAAC,KAAK;YACtB,UAAU,EAAE,UAAU,CAAC,iBAAiB;YACxC,QAAQ,EAAE;gBACR,KAAK;gBACL,SAAS,EAAE,SAAS,CAAC,KAAK;gBAC1B,cAAc,EAAE,SAAS,CAAC,UAAU;gBACpC,QAAQ,EAAE,aAAa;aACxB;SACF,CAAC;IACJ,CAAC;IAED;;;;;;;;;;;;;;;;;;;;;;;OAuBG;IACH,KAAK,CACH,MAAS,EACT,WAAoC,EACpC,SAA2B,EAC3B,OAAe,EACf,OAAiD,EACjD,OAAkB;QAGlB,MAAM,UAAU,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,KAAK,CAAmB,CAAC;QAE/D,MAAM,MAAM,GAAG,aAAa,CAC1B,UAAU,EACV,WAAW,EACX,SAAS,EACT,OAAO,EAAE,MAAM,EACf,OAAO,EAAE,aAAa,EACtB,OAAO,EAAE,MAAM,CAChB,CAAC;QAEF,MAAM,UAAU,GAAG,cAAc,CAAC,MAAM,CAAC,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,OAAO,EAAE,OAAO,CAAC,CAAC;QAEvF,MAAM,UAAU,GAAG,iBAAiB,CAClC,MAAM,EACN,UAAU,EACV,MAAM,CAAC,OAAO,EACd,OAAO,EAAE,UAAU,CACpB,CAAC;QACF,MAAM,KAAK,GAAG,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,OAAO,CAAC,CAAC;QAE9D,OAAO;YACL,IAAI,EAAE,UAAU;YAChB,UAAU,EAAE,MAAM,CAAC,UAAU;YAC7B,OAAO,EAAE,MAAM,CAAC,OAAO;YACvB,SAAS,EAAE,MAAM,CAAC,SAAS;YAC3B,OAAO,EAAE,MAAM,CAAC,OAAO;YACvB,UAAU,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE;YACjC,IAAI,EAAE;gBACJ,YAAY,EAAE,MAAM,CAAC,YAAY;gBACjC,SAAS,EAAE,SAAS,KAAK,IAAI;gBAC7B,UAAU,EAAE,CAAC;aACd;SACF,CAAC;IACJ,CAAC;CACF,CAAC"}
package/dist/prompt.d.ts CHANGED
@@ -39,7 +39,7 @@ export declare const prompt: {
39
39
  /**
40
40
  * Parse a raw LLM response permissively. Accepts either an already-decoded
41
41
  * object or a JSON-encoded string. Each field listed in `missing` is
42
- * validated individually against its Zod schema valid fields flow into
42
+ * validated individually against its Zod schema - valid fields flow into
43
43
  * `values`, invalid ones are dropped and surfaced as warnings. Keys outside
44
44
  * `missing` are dropped as well, with a single aggregated warning so the
45
45
  * caller can spot a prompt/provider mismatch.
@@ -50,7 +50,7 @@ export declare const prompt: {
50
50
  * @param schema - Zod object schema whose fields back the validation.
51
51
  * @param missing - Fields the LLM was expected to produce (typically
52
52
  * {@link ExtractionResult.missing}).
53
- * @param raw - The provider response object or JSON string.
53
+ * @param raw - The provider response - object or JSON string.
54
54
  */
55
55
  parse<S extends z.ZodObject<z.ZodRawShape>>(schema: S, missing: readonly (keyof z.infer<S>)[], raw: unknown): LlmResult;
56
56
  };
package/dist/prompt.js CHANGED
@@ -89,7 +89,7 @@ function buildResponseSchema(schema, missing) {
89
89
  return { type: 'object', properties, required, additionalProperties: false };
90
90
  }
91
91
  /**
92
- * Pick the non-null, non-missing entries of the partial result the values
92
+ * Pick the non-null, non-missing entries of the partial result - the values
93
93
  * the deterministic pass has already resolved.
94
94
  */
95
95
  function collectKnownValues(data, missing) {
@@ -233,7 +233,7 @@ export const prompt = {
233
233
  /**
234
234
  * Parse a raw LLM response permissively. Accepts either an already-decoded
235
235
  * object or a JSON-encoded string. Each field listed in `missing` is
236
- * validated individually against its Zod schema valid fields flow into
236
+ * validated individually against its Zod schema - valid fields flow into
237
237
  * `values`, invalid ones are dropped and surfaced as warnings. Keys outside
238
238
  * `missing` are dropped as well, with a single aggregated warning so the
239
239
  * caller can spot a prompt/provider mismatch.
@@ -244,7 +244,7 @@ export const prompt = {
244
244
  * @param schema - Zod object schema whose fields back the validation.
245
245
  * @param missing - Fields the LLM was expected to produce (typically
246
246
  * {@link ExtractionResult.missing}).
247
- * @param raw - The provider response object or JSON string.
247
+ * @param raw - The provider response - object or JSON string.
248
248
  */
249
249
  parse(schema, missing, raw) {
250
250
  const missingKeys = missing;
package/dist/rules.d.ts CHANGED
@@ -10,18 +10,23 @@ export declare const rule: {
10
10
  * Declare a deterministic extraction rule targeting a single schema field.
11
11
  *
12
12
  * The `extract` callback receives the raw content and must return either a
13
- * {@link RuleMatch} or `null` when the rule does not apply.
13
+ * {@link RuleMatch} or `null` when the rule does not apply. It may also
14
+ * accept an optional caller-defined `context` forwarded verbatim by
15
+ * {@link rule.apply} / {@link Extractor.extract}.
14
16
  *
17
+ * @typeParam TContext - Shape of the optional context forwarded to
18
+ * `extract`. Defaults to `unknown`.
15
19
  * @param field - Name of the schema field the rule writes to.
16
- * @param extract - Callback that inspects the content and proposes a value.
20
+ * @param extract - Callback that inspects the content (and optional context)
21
+ * and proposes a value.
17
22
  * @param options - Optional rule metadata. `id` is surfaced in
18
23
  * `ExtractionResult.sources` when this rule produces the kept value;
19
24
  * defaults to `${field}#${declarationIndex}`.
20
25
  * @returns An {@link ExtractionRule} ready to be passed to {@link rule.apply}.
21
26
  */
22
- create(field: string, extract: (content: string) => RuleMatch<unknown> | null, options?: {
27
+ create<TContext = unknown>(field: string, extract: (content: string, context?: TContext) => RuleMatch<unknown> | null, options?: {
23
28
  id?: string;
24
- }): ExtractionRule;
29
+ }): ExtractionRule<TContext>;
25
30
  /**
26
31
  * Shortcut to build a regex-based {@link ExtractionRule}. On match, the
27
32
  * value is taken from capture group 1 (or the full match if none), then
@@ -68,13 +73,21 @@ export declare const rule: {
68
73
  * - Values failing the per-field Zod `safeParse` are discarded and the
69
74
  * field falls back to `missing`. An optional logger receives a warning.
70
75
  *
76
+ * The optional `context` is forwarded verbatim to every rule's `extract`
77
+ * callback. Rules that declare a narrower `ExtractionRule<TContext>` than
78
+ * the one passed here still compile thanks to contextual parameter
79
+ * contravariance; rules that ignore `context` keep working unchanged.
80
+ *
71
81
  * @typeParam S - A Zod object schema.
82
+ * @typeParam TContext - Shape of the optional context forwarded to rules.
72
83
  * @param content - Raw content to extract from (typically markdown or text).
73
84
  * @param rules - Deterministic rules to evaluate.
74
85
  * @param schema - Zod object schema describing the target data shape.
75
86
  * @param logger - Optional logger notified when a value is rejected.
87
+ * @param context - Optional caller-defined value forwarded to every rule's
88
+ * `extract` callback. Left `undefined` when omitted.
76
89
  * @returns The deterministic extraction result (values, confidence, missing).
77
90
  */
78
- apply<S extends z.ZodObject<z.ZodRawShape>>(content: string, rules: ExtractionRule[], schema: S, logger?: Logger): RulesResult<z.infer<S>>;
91
+ apply<S extends z.ZodObject<z.ZodRawShape>, TContext = unknown>(content: string, rules: ExtractionRule<TContext>[], schema: S, logger?: Logger, context?: TContext): RulesResult<z.infer<S>>;
79
92
  };
80
93
  //# sourceMappingURL=rules.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"rules.d.ts","sourceRoot":"","sources":["../src/rules.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAC7B,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,yBAAyB,CAAC;AACtD,OAAO,KAAK,EAAE,cAAc,EAAE,SAAS,EAAE,WAAW,EAAE,MAAM,uBAAuB,CAAC;AAEpF;;;GAGG;AACH,eAAO,MAAM,IAAI;IACf;;;;;;;;;;;;OAYG;kBAEM,MAAM,WACJ,CAAC,OAAO,EAAE,MAAM,KAAK,SAAS,CAAC,OAAO,CAAC,GAAG,IAAI,YAC7C;QAAE,EAAE,CAAC,EAAE,MAAM,CAAA;KAAE,GACxB,cAAc;IAIjB;;;;;;;;;;;OAWG;UACG,CAAC,kBACE,MAAM,WACJ,MAAM,mBACE,MAAM,cACX,CAAC,KAAK,EAAE,gBAAgB,KAAK,CAAC,YAChC;QAAE,EAAE,CAAC,EAAE,MAAM,CAAA;KAAE,GACxB,cAAc;IAYjB;;;;;;;;;;;;;;;;;OAiBG;eACQ,CAAC,SAAS,CAAC,SAAS,MAAM,GAAG,SAAS,CAAC,CAAC,CAAC;IAIpD;;;;;;;;;;;;;;;;;;OAkBG;UACG,CAAC,SAAS,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC,WAC/B,MAAM,SACR,cAAc,EAAE,UACf,CAAC,WACA,MAAM,GACd,WAAW,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;CAwC3B,CAAC"}
1
+ {"version":3,"file":"rules.d.ts","sourceRoot":"","sources":["../src/rules.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAC7B,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,yBAAyB,CAAC;AACtD,OAAO,KAAK,EAAE,cAAc,EAAE,SAAS,EAAE,WAAW,EAAE,MAAM,uBAAuB,CAAC;AAEpF;;;GAGG;AACH,eAAO,MAAM,IAAI;IACf;;;;;;;;;;;;;;;;;OAiBG;WACI,QAAQ,mBACN,MAAM,WACJ,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,QAAQ,KAAK,SAAS,CAAC,OAAO,CAAC,GAAG,IAAI,YACjE;QAAE,EAAE,CAAC,EAAE,MAAM,CAAA;KAAE,GACxB,cAAc,CAAC,QAAQ,CAAC;IAI3B;;;;;;;;;;;OAWG;UACG,CAAC,kBACE,MAAM,WACJ,MAAM,mBACE,MAAM,cACX,CAAC,KAAK,EAAE,gBAAgB,KAAK,CAAC,YAChC;QAAE,EAAE,CAAC,EAAE,MAAM,CAAA;KAAE,GACxB,cAAc;IAYjB;;;;;;;;;;;;;;;;;OAiBG;eACQ,CAAC,SAAS,CAAC,SAAS,MAAM,GAAG,SAAS,CAAC,CAAC,CAAC;IAIpD;;;;;;;;;;;;;;;;;;;;;;;;;;OA0BG;UACG,CAAC,SAAS,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC,EAAE,QAAQ,qBACzC,MAAM,SACR,cAAc,CAAC,QAAQ,CAAC,EAAE,UACzB,CAAC,WACA,MAAM,YACL,QAAQ,GACjB,WAAW,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;CAwC3B,CAAC"}
package/dist/rules.js CHANGED
@@ -7,10 +7,15 @@ export const rule = {
7
7
  * Declare a deterministic extraction rule targeting a single schema field.
8
8
  *
9
9
  * The `extract` callback receives the raw content and must return either a
10
- * {@link RuleMatch} or `null` when the rule does not apply.
10
+ * {@link RuleMatch} or `null` when the rule does not apply. It may also
11
+ * accept an optional caller-defined `context` forwarded verbatim by
12
+ * {@link rule.apply} / {@link Extractor.extract}.
11
13
  *
14
+ * @typeParam TContext - Shape of the optional context forwarded to
15
+ * `extract`. Defaults to `unknown`.
12
16
  * @param field - Name of the schema field the rule writes to.
13
- * @param extract - Callback that inspects the content and proposes a value.
17
+ * @param extract - Callback that inspects the content (and optional context)
18
+ * and proposes a value.
14
19
  * @param options - Optional rule metadata. `id` is surfaced in
15
20
  * `ExtractionResult.sources` when this rule produces the kept value;
16
21
  * defaults to `${field}#${declarationIndex}`.
@@ -75,14 +80,22 @@ export const rule = {
75
80
  * - Values failing the per-field Zod `safeParse` are discarded and the
76
81
  * field falls back to `missing`. An optional logger receives a warning.
77
82
  *
83
+ * The optional `context` is forwarded verbatim to every rule's `extract`
84
+ * callback. Rules that declare a narrower `ExtractionRule<TContext>` than
85
+ * the one passed here still compile thanks to contextual parameter
86
+ * contravariance; rules that ignore `context` keep working unchanged.
87
+ *
78
88
  * @typeParam S - A Zod object schema.
89
+ * @typeParam TContext - Shape of the optional context forwarded to rules.
79
90
  * @param content - Raw content to extract from (typically markdown or text).
80
91
  * @param rules - Deterministic rules to evaluate.
81
92
  * @param schema - Zod object schema describing the target data shape.
82
93
  * @param logger - Optional logger notified when a value is rejected.
94
+ * @param context - Optional caller-defined value forwarded to every rule's
95
+ * `extract` callback. Left `undefined` when omitted.
83
96
  * @returns The deterministic extraction result (values, confidence, missing).
84
97
  */
85
- apply(content, rules, schema, logger) {
98
+ apply(content, rules, schema, logger, context) {
86
99
  const schemaKeys = Object.keys(schema.shape);
87
100
  const values = {};
88
101
  const confidenceMap = {};
@@ -93,7 +106,7 @@ export const rule = {
93
106
  if (!schemaKeys.includes(field)) {
94
107
  continue;
95
108
  }
96
- const match = candidate.extract(content);
109
+ const match = candidate.extract(content, context);
97
110
  if (match === null) {
98
111
  continue;
99
112
  }
package/dist/rules.js.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"rules.js","sourceRoot":"","sources":["../src/rules.ts"],"names":[],"mappings":"AAIA;;;GAGG;AACH,MAAM,CAAC,MAAM,IAAI,GAAG;IAClB;;;;;;;;;;;;OAYG;IACH,MAAM,CACJ,KAAa,EACb,OAAuD,EACvD,OAAyB;QAEzB,OAAO,OAAO,EAAE,EAAE,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,OAAO,CAAC,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC;IAC7F,CAAC;IAED;;;;;;;;;;;OAWG;IACH,KAAK,CACH,KAAa,EACb,OAAe,EACf,eAAuB,EACvB,SAA0C,EAC1C,OAAyB;QAEzB,MAAM,OAAO,GAAG,CAAC,OAAe,EAA6B,EAAE;YAC7D,MAAM,KAAK,GAAG,OAAO,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;YACrC,IAAI,CAAC,KAAK,EAAE,CAAC;gBACX,OAAO,IAAI,CAAC;YACd,CAAC;YACD,MAAM,KAAK,GAAG,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;YACpE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE,eAAe,EAAE,CAAC;QAChD,CAAC,CAAC;QACF,OAAO,OAAO,EAAE,EAAE,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,OAAO,CAAC,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC;IAC7F,CAAC;IAED;;;;;;;;;;;;;;;;;OAiBG;IACH,UAAU,CAAI,KAAQ,EAAE,KAAa;QACnC,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE,KAAK,EAAE,CAAC;IACtC,CAAC;IAED;;;;;;;;;;;;;;;;;;OAkBG;IACH,KAAK,CACH,OAAe,EACf,KAAuB,EACvB,MAAS,EACT,MAAe;QAGf,MAAM,UAAU,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,KAAK,CAAmB,CAAC;QAC/D,MAAM,MAAM,GAAkB,EAAE,CAAC;QACjC,MAAM,aAAa,GAAwC,EAAE,CAAC;QAC9D,MAAM,SAAS,GAAwC,EAAE,CAAC;QAE1D,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,KAAK,CAAC,MAAM,EAAE,KAAK,IAAI,CAAC,EAAE,CAAC;YACrD,MAAM,SAAS,GAAG,KAAK,CAAC,KAAK,CAAE,CAAC;YAChC,MAAM,KAAK,GAAG,SAAS,CAAC,KAAmB,CAAC;YAC5C,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;gBAChC,SAAS;YACX,CAAC;YACD,MAAM,KAAK,GAAG,SAAS,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC;YACzC,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;gBACnB,SAAS;YACX,CAAC;YACD,MAAM,WAAW,GAAG,MAAM,CAAC,KAAK,CAAC,SAAS,CAAC,KAAK,CAAiB,CAAC;YAClE,MAAM,MAAM,GAAG,WAAW,CAAC,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;YAClD,IAAI,CAAC,MAAM,CAAC,OAAO,EAAE,CAAC;gBACpB,MAAM,EAAE,IAAI,CAAC,+BAA+B,EAAE;oBAC5C,KAAK,EAAE,SAAS,CAAC,KAAK;oBACtB,KAAK,EAAE,KAAK,CAAC,KAAK;oBAClB,KAAK,EAAE,MAAM,CAAC,KAAK,CAAC,MAAM;iBAC3B,CAAC,CAAC;gBACH,SAAS;YACX,CAAC;YACD,MAAM,kBAAkB,GAAG,aAAa,CAAC,KAAK,CAAC,CAAC;YAChD,IAAI,kBAAkB,KAAK,SAAS,IAAI,KAAK,CAAC,UAAU,IAAI,kBAAkB,EAAE,CAAC;gBAC/E,SAAS;YACX,CAAC;YACD,MAAM,CAAC,KAAK,CAAC,GAAG,MAAM,CAAC,IAAwB,CAAC;YAChD,aAAa,CAAC,KAAK,CAAC,GAAG,KAAK,CAAC,UAAU,CAAC;YACxC,SAAS,CAAC,KAAK,CAAC,GAAG,SAAS,CAAC,EAAE,IAAI,GAAG,SAAS,CAAC,KAAK,IAAI,KAAK,EAAE,CAAC;QACnE,CAAC;QAED,MAAM,OAAO,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC,CAAC,GAAG,IAAI,MAAM,CAAC,CAAC,CAAC;QAE7D,OAAO,EAAE,MAAM,EAAE,UAAU,EAAE,aAAa,EAAE,SAAS,EAAE,OAAO,EAAE,CAAC;IACnE,CAAC;CACF,CAAC"}
1
+ {"version":3,"file":"rules.js","sourceRoot":"","sources":["../src/rules.ts"],"names":[],"mappings":"AAIA;;;GAGG;AACH,MAAM,CAAC,MAAM,IAAI,GAAG;IAClB;;;;;;;;;;;;;;;;;OAiBG;IACH,MAAM,CACJ,KAAa,EACb,OAA2E,EAC3E,OAAyB;QAEzB,OAAO,OAAO,EAAE,EAAE,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,OAAO,CAAC,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC;IAC7F,CAAC;IAED;;;;;;;;;;;OAWG;IACH,KAAK,CACH,KAAa,EACb,OAAe,EACf,eAAuB,EACvB,SAA0C,EAC1C,OAAyB;QAEzB,MAAM,OAAO,GAAG,CAAC,OAAe,EAA6B,EAAE;YAC7D,MAAM,KAAK,GAAG,OAAO,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;YACrC,IAAI,CAAC,KAAK,EAAE,CAAC;gBACX,OAAO,IAAI,CAAC;YACd,CAAC;YACD,MAAM,KAAK,GAAG,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;YACpE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE,eAAe,EAAE,CAAC;QAChD,CAAC,CAAC;QACF,OAAO,OAAO,EAAE,EAAE,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,OAAO,CAAC,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC;IAC7F,CAAC;IAED;;;;;;;;;;;;;;;;;OAiBG;IACH,UAAU,CAAI,KAAQ,EAAE,KAAa;QACnC,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE,KAAK,EAAE,CAAC;IACtC,CAAC;IAED;;;;;;;;;;;;;;;;;;;;;;;;;;OA0BG;IACH,KAAK,CACH,OAAe,EACf,KAAiC,EACjC,MAAS,EACT,MAAe,EACf,OAAkB;QAGlB,MAAM,UAAU,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,KAAK,CAAmB,CAAC;QAC/D,MAAM,MAAM,GAAkB,EAAE,CAAC;QACjC,MAAM,aAAa,GAAwC,EAAE,CAAC;QAC9D,MAAM,SAAS,GAAwC,EAAE,CAAC;QAE1D,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,KAAK,CAAC,MAAM,EAAE,KAAK,IAAI,CAAC,EAAE,CAAC;YACrD,MAAM,SAAS,GAAG,KAAK,CAAC,KAAK,CAAE,CAAC;YAChC,MAAM,KAAK,GAAG,SAAS,CAAC,KAAmB,CAAC;YAC5C,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;gBAChC,SAAS;YACX,CAAC;YACD,MAAM,KAAK,GAAG,SAAS,CAAC,OAAO,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC;YAClD,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;gBACnB,SAAS;YACX,CAAC;YACD,MAAM,WAAW,GAAG,MAAM,CAAC,KAAK,CAAC,SAAS,CAAC,KAAK,CAAiB,CAAC;YAClE,MAAM,MAAM,GAAG,WAAW,CAAC,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;YAClD,IAAI,CAAC,MAAM,CAAC,OAAO,EAAE,CAAC;gBACpB,MAAM,EAAE,IAAI,CAAC,+BAA+B,EAAE;oBAC5C,KAAK,EAAE,SAAS,CAAC,KAAK;oBACtB,KAAK,EAAE,KAAK,CAAC,KAAK;oBAClB,KAAK,EAAE,MAAM,CAAC,KAAK,CAAC,MAAM;iBAC3B,CAAC,CAAC;gBACH,SAAS;YACX,CAAC;YACD,MAAM,kBAAkB,GAAG,aAAa,CAAC,KAAK,CAAC,CAAC;YAChD,IAAI,kBAAkB,KAAK,SAAS,IAAI,KAAK,CAAC,UAAU,IAAI,kBAAkB,EAAE,CAAC;gBAC/E,SAAS;YACX,CAAC;YACD,MAAM,CAAC,KAAK,CAAC,GAAG,MAAM,CAAC,IAAwB,CAAC;YAChD,aAAa,CAAC,KAAK,CAAC,GAAG,KAAK,CAAC,UAAU,CAAC;YACxC,SAAS,CAAC,KAAK,CAAC,GAAG,SAAS,CAAC,EAAE,IAAI,GAAG,SAAS,CAAC,KAAK,IAAI,KAAK,EAAE,CAAC;QACnE,CAAC;QAED,MAAM,OAAO,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC,CAAC,GAAG,IAAI,MAAM,CAAC,CAAC,CAAC;QAE7D,OAAO,EAAE,MAAM,EAAE,UAAU,EAAE,aAAa,EAAE,SAAS,EAAE,OAAO,EAAE,CAAC;IACnE,CAAC;CACF,CAAC"}
@@ -51,16 +51,24 @@ export type ExtractorLlmConfig = {
51
51
  * produce values for each field before any LLM fallback kicks in.
52
52
  *
53
53
  * @typeParam S - A Zod object schema describing the target data shape.
54
+ * @typeParam TContext - Shape of the optional per-call context forwarded to
55
+ * every rule's `extract` callback. Defaults to `unknown`, which keeps
56
+ * context-unaware rules assignable with zero boilerplate.
54
57
  */
55
- export type ExtractorConfig<S extends z.ZodObject<z.ZodRawShape>> = {
58
+ export type ExtractorConfig<S extends z.ZodObject<z.ZodRawShape>, TContext = unknown> = {
56
59
  /** Zod object schema the extractor targets. Drives field enumeration and re-validation. */
57
60
  schema: S;
58
61
  /** Deterministic rules evaluated against the raw content before any LLM fallback. */
59
- rules: ExtractionRule[];
62
+ rules: ExtractionRule<TContext>[];
60
63
  /** Optional LLM fallback invoked for fields the rules could not produce. */
61
64
  llm?: ExtractorLlmConfig;
62
- /** Post-merge transformations, forwarded to every `merge.apply` call. */
63
- normalizers?: Normalizer<z.infer<S>>[];
65
+ /**
66
+ * Post-merge transformations, forwarded to every `merge.apply` call.
67
+ * Normalizers share the extractor's `TContext`, so they can read the same
68
+ * per-call context as the rules (see
69
+ * {@link Extractor.extract} / {@link Extractor.extractSync} / {@link Extractor.merge}).
70
+ */
71
+ normalizers?: Normalizer<z.infer<S>, TContext>[];
64
72
  /** Invariants checked on the normalized data; populate `result.validation`. */
65
73
  validators?: Validator<ExtractedData<z.infer<S>>>[];
66
74
  /** Overrides for the per-field merge policy (conflict strategy, confidences, compare). */
@@ -81,21 +89,25 @@ export type ExtractorConfig<S extends z.ZodObject<z.ZodRawShape>> = {
81
89
  * this interface as the matching slice introduces them.
82
90
  *
83
91
  * @typeParam T - Shape of the target data object inferred from a Zod schema.
92
+ * @typeParam TContext - Shape of the optional per-call context forwarded to
93
+ * every rule's `extract` callback. Defaults to `unknown`.
84
94
  */
85
- export type Extractor<T> = {
95
+ export type Extractor<T, TContext = unknown> = {
86
96
  /**
87
97
  * Run the full extraction pipeline against `content`: deterministic rules,
88
98
  * optionally followed by an LLM fallback for missing fields, then the merge
89
- * + validation step.
99
+ * + validation step. An optional `context` is forwarded verbatim to every
100
+ * rule's `extract` callback.
90
101
  */
91
- extract(content: string): Promise<ExtractionResult<T>>;
102
+ extract(content: string, context?: TContext): Promise<ExtractionResult<T>>;
92
103
  /**
93
104
  * Run the deterministic rules and merge them against a `null` LLM result.
94
105
  * Synchronous counterpart to {@link Extractor.extract} for batch workflows
95
106
  * where the LLM call is managed by the caller (queues, scheduled jobs,
96
- * external batch APIs).
107
+ * external batch APIs). An optional `context` is forwarded verbatim to
108
+ * every rule's `extract` callback.
97
109
  */
98
- extractSync(content: string): ExtractionResult<T>;
110
+ extractSync(content: string, context?: TContext): ExtractionResult<T>;
99
111
  /**
100
112
  * Build the LLM request for `partial`. The target field set depends on the
101
113
  * configured `llm.mode`: `'fill-gaps'` (default) covers only
@@ -112,11 +124,12 @@ export type Extractor<T> = {
112
124
  */
113
125
  parse(raw: unknown): LlmResult;
114
126
  /**
115
- * Merge a previously-obtained `partial` with an LLM result and re-run the
116
- * deterministic rules to produce the final {@link ExtractionResult}.
117
- * Rules are pure, so re-running them is cheaper than carrying private
118
- * state on the extractor.
127
+ * Merge a previously-obtained `partial` with an LLM result to produce the
128
+ * final {@link ExtractionResult}. Reuses the per-field values, confidence
129
+ * and provenance already carried by `partial` - the deterministic rules are
130
+ * not re-evaluated. Normalizers still run here, so an optional `context` is
131
+ * accepted and forwarded verbatim to every normalizer that declares one.
119
132
  */
120
- merge(partial: ExtractionResult<T>, llmResult: LlmResult, content: string): ExtractionResult<T>;
133
+ merge(partial: ExtractionResult<T>, llmResult: LlmResult, content: string, context?: TContext): ExtractionResult<T>;
121
134
  };
122
135
  //# sourceMappingURL=extractor.types.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"extractor.types.d.ts","sourceRoot":"","sources":["../../src/types/extractor.types.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAC7B,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAC;AACtD,OAAO,KAAK,EACV,aAAa,EACb,gBAAgB,EAChB,gBAAgB,EAChB,SAAS,EACT,UAAU,EACX,MAAM,kBAAkB,CAAC;AAC1B,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AACvD,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,mBAAmB,CAAC;AAChD,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,qBAAqB,CAAC;AACrD,OAAO,KAAK,EAAE,eAAe,EAAE,UAAU,EAAE,eAAe,EAAE,MAAM,mBAAmB,CAAC;AAEtF;;;;GAIG;AACH,MAAM,MAAM,kBAAkB,GAAG;IAC/B,+DAA+D;IAC/D,QAAQ,EAAE,WAAW,CAAC;IACtB,4GAA4G;IAC5G,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB;;;;;OAKG;IACH,IAAI,CAAC,EAAE,eAAe,CAAC;IACvB;;;OAGG;IACH,eAAe,CAAC,EAAE,eAAe,CAAC;IAClC;;;;;;;OAOG;IACH,gBAAgB,CAAC,EAAE,CACjB,OAAO,EAAE,UAAU,EACnB,OAAO,EAAE,MAAM,KACZ,UAAU,GAAG,OAAO,CAAC,UAAU,CAAC,CAAC;IACtC;;;;;;OAMG;IACH,iBAAiB,CAAC,EAAE,CAClB,MAAM,EAAE,SAAS,EACjB,OAAO,EAAE,UAAU,KAChB,SAAS,GAAG,OAAO,CAAC,SAAS,CAAC,CAAC;CACrC,CAAC;AAEF;;;;;;GAMG;AACH,MAAM,MAAM,eAAe,CAAC,CAAC,SAAS,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC,IAAI;IAClE,2FAA2F;IAC3F,MAAM,EAAE,CAAC,CAAC;IACV,qFAAqF;IACrF,KAAK,EAAE,cAAc,EAAE,CAAC;IACxB,4EAA4E;IAC5E,GAAG,CAAC,EAAE,kBAAkB,CAAC;IACzB,yEAAyE;IACzE,WAAW,CAAC,EAAE,UAAU,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;IACvC,+EAA+E;IAC/E,UAAU,CAAC,EAAE,SAAS,CAAC,aAAa,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;IACpD,0FAA0F;IAC1F,MAAM,CAAC,EAAE,OAAO,CAAC,gBAAgB,CAAC,CAAC;IACnC;;;;OAIG;IACH,aAAa,CAAC,EAAE;SAAG,CAAC,IAAI,MAAM,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,OAAO,CAAC,gBAAgB,CAAC;KAAE,CAAC;IACxE,+EAA+E;IAC/E,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB,CAAC;AAEF;;;;;GAKG;AACH,MAAM,MAAM,SAAS,CAAC,CAAC,IAAI;IACzB;;;;OAIG;IACH,OAAO,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,gBAAgB,CAAC,CAAC,CAAC,CAAC,CAAC;IACvD;;;;;OAKG;IACH,WAAW,CAAC,OAAO,EAAE,MAAM,GAAG,gBAAgB,CAAC,CAAC,CAAC,CAAC;IAClD;;;;;;OAMG;IACH,MAAM,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,gBAAgB,CAAC,CAAC,CAAC,GAAG,UAAU,CAAC;IAClE;;;;;OAKG;IACH,KAAK,CAAC,GAAG,EAAE,OAAO,GAAG,SAAS,CAAC;IAC/B;;;;;OAKG;IACH,KAAK,CACH,OAAO,EAAE,gBAAgB,CAAC,CAAC,CAAC,EAC5B,SAAS,EAAE,SAAS,EACpB,OAAO,EAAE,MAAM,GACd,gBAAgB,CAAC,CAAC,CAAC,CAAC;CACxB,CAAC"}
1
+ {"version":3,"file":"extractor.types.d.ts","sourceRoot":"","sources":["../../src/types/extractor.types.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAC7B,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAC;AACtD,OAAO,KAAK,EACV,aAAa,EACb,gBAAgB,EAChB,gBAAgB,EAChB,SAAS,EACT,UAAU,EACX,MAAM,kBAAkB,CAAC;AAC1B,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AACvD,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,mBAAmB,CAAC;AAChD,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,qBAAqB,CAAC;AACrD,OAAO,KAAK,EAAE,eAAe,EAAE,UAAU,EAAE,eAAe,EAAE,MAAM,mBAAmB,CAAC;AAEtF;;;;GAIG;AACH,MAAM,MAAM,kBAAkB,GAAG;IAC/B,+DAA+D;IAC/D,QAAQ,EAAE,WAAW,CAAC;IACtB,4GAA4G;IAC5G,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB;;;;;OAKG;IACH,IAAI,CAAC,EAAE,eAAe,CAAC;IACvB;;;OAGG;IACH,eAAe,CAAC,EAAE,eAAe,CAAC;IAClC;;;;;;;OAOG;IACH,gBAAgB,CAAC,EAAE,CACjB,OAAO,EAAE,UAAU,EACnB,OAAO,EAAE,MAAM,KACZ,UAAU,GAAG,OAAO,CAAC,UAAU,CAAC,CAAC;IACtC;;;;;;OAMG;IACH,iBAAiB,CAAC,EAAE,CAClB,MAAM,EAAE,SAAS,EACjB,OAAO,EAAE,UAAU,KAChB,SAAS,GAAG,OAAO,CAAC,SAAS,CAAC,CAAC;CACrC,CAAC;AAEF;;;;;;;;;GASG;AACH,MAAM,MAAM,eAAe,CACzB,CAAC,SAAS,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC,EACpC,QAAQ,GAAG,OAAO,IAChB;IACF,2FAA2F;IAC3F,MAAM,EAAE,CAAC,CAAC;IACV,qFAAqF;IACrF,KAAK,EAAE,cAAc,CAAC,QAAQ,CAAC,EAAE,CAAC;IAClC,4EAA4E;IAC5E,GAAG,CAAC,EAAE,kBAAkB,CAAC;IACzB;;;;;OAKG;IACH,WAAW,CAAC,EAAE,UAAU,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,QAAQ,CAAC,EAAE,CAAC;IACjD,+EAA+E;IAC/E,UAAU,CAAC,EAAE,SAAS,CAAC,aAAa,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;IACpD,0FAA0F;IAC1F,MAAM,CAAC,EAAE,OAAO,CAAC,gBAAgB,CAAC,CAAC;IACnC;;;;OAIG;IACH,aAAa,CAAC,EAAE;SAAG,CAAC,IAAI,MAAM,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,OAAO,CAAC,gBAAgB,CAAC;KAAE,CAAC;IACxE,+EAA+E;IAC/E,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB,CAAC;AAEF;;;;;;;GAOG;AACH,MAAM,MAAM,SAAS,CAAC,CAAC,EAAE,QAAQ,GAAG,OAAO,IAAI;IAC7C;;;;;OAKG;IACH,OAAO,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,QAAQ,GAAG,OAAO,CAAC,gBAAgB,CAAC,CAAC,CAAC,CAAC,CAAC;IAC3E;;;;;;OAMG;IACH,WAAW,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,QAAQ,GAAG,gBAAgB,CAAC,CAAC,CAAC,CAAC;IACtE;;;;;;OAMG;IACH,MAAM,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,gBAAgB,CAAC,CAAC,CAAC,GAAG,UAAU,CAAC;IAClE;;;;;OAKG;IACH,KAAK,CAAC,GAAG,EAAE,OAAO,GAAG,SAAS,CAAC;IAC/B;;;;;;OAMG;IACH,KAAK,CACH,OAAO,EAAE,gBAAgB,CAAC,CAAC,CAAC,EAC5B,SAAS,EAAE,SAAS,EACpB,OAAO,EAAE,MAAM,EACf,OAAO,CAAC,EAAE,QAAQ,GACjB,gBAAgB,CAAC,CAAC,CAAC,CAAC;CACxB,CAAC"}
@@ -1,6 +1,6 @@
1
1
  /**
2
2
  * Minimal logger interface consumed by llmbic internals. Any logger that
3
- * exposes a `warn` method (and optionally `info`) can be plugged in
3
+ * exposes a `warn` method (and optionally `info`) can be plugged in -
4
4
  * pino, winston, `console`, or a test double.
5
5
  */
6
6
  export type Logger = {
@@ -17,17 +17,29 @@ export type ExtractedData<T> = {
17
17
  * and return the updated data. They are allowed to mutate their input; the
18
18
  * merge pipeline shallow-copies once before invoking them.
19
19
  *
20
+ * Normalizers can optionally accept a `context` argument: an opaque,
21
+ * caller-defined value forwarded verbatim by `merge.apply` /
22
+ * `Extractor.extract` - the same per-call context the extractor's rules
23
+ * receive. Typical use is to gate cross-field fix-ups on tenant-specific
24
+ * configuration (e.g. a source URL, a feature flag). `TContext` defaults to
25
+ * `unknown` so context-unaware normalizers stay assignable to arrays typed
26
+ * with any context.
27
+ *
20
28
  * @typeParam T - Non-null target shape the extraction is aiming for.
29
+ * @typeParam TContext - Shape of the optional per-call context forwarded to
30
+ * the normalizer. Defaults to `unknown`.
21
31
  */
22
- export type Normalizer<T> = (data: ExtractedData<T>, content: string) => ExtractedData<T>;
32
+ export type Normalizer<T, TContext = unknown> = (data: ExtractedData<T>, content: string, context?: TContext) => ExtractedData<T>;
23
33
  /**
24
34
  * Behavior overrides accepted by the top-level merge. Every field is
25
35
  * optional; defaults match rules-only mode with no normalization and no
26
36
  * validators.
27
37
  *
28
38
  * @typeParam T - Non-null target shape (`z.infer<Schema>`).
39
+ * @typeParam TContext - Shape of the optional per-call context forwarded to
40
+ * every normalizer. Defaults to `unknown`.
29
41
  */
30
- export type MergeApplyOptions<T> = {
42
+ export type MergeApplyOptions<T, TContext = unknown> = {
31
43
  /** Overrides forwarded to every field-level fusion call. */
32
44
  policy?: Partial<FieldMergePolicy>;
33
45
  /**
@@ -39,7 +51,7 @@ export type MergeApplyOptions<T> = {
39
51
  [K in keyof T]?: Partial<FieldMergePolicy>;
40
52
  };
41
53
  /** Transformations run in declared order after the per-field fusion. */
42
- normalizers?: Normalizer<T>[];
54
+ normalizers?: Normalizer<T, TContext>[];
43
55
  /** Invariants run on the normalized data; their violations populate `validation`. */
44
56
  validators?: Validator<ExtractedData<T>>[];
45
57
  /** Logger propagated through the pipeline for warnings and fallbacks. */
@@ -48,10 +60,10 @@ export type MergeApplyOptions<T> = {
48
60
  /**
49
61
  * Strategy applied when the rule and the LLM disagree on a field value.
50
62
  *
51
- * - `'flag'` keep the rule value, lower its confidence, and record a
63
+ * - `'flag'` - keep the rule value, lower its confidence, and record a
52
64
  * {@link Conflict} so the caller can review the disagreement.
53
- * - `'prefer-rule'` silently keep the rule value and its confidence.
54
- * - `'prefer-llm'` silently keep the LLM value and the default LLM
65
+ * - `'prefer-rule'` - silently keep the rule value and its confidence.
66
+ * - `'prefer-llm'` - silently keep the LLM value and the default LLM
55
67
  * confidence.
56
68
  */
57
69
  export type ConflictStrategy = 'flag' | 'prefer-rule' | 'prefer-llm';
@@ -1 +1 @@
1
- {"version":3,"file":"merge.types.d.ts","sourceRoot":"","sources":["../../src/types/merge.types.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AACjD,OAAO,KAAK,EAAE,SAAS,EAAE,SAAS,EAAE,MAAM,qBAAqB,CAAC;AAChE,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,mBAAmB,CAAC;AAEhD;;;;;;GAMG;AACH,MAAM,MAAM,aAAa,CAAC,CAAC,IAAI;KAAG,CAAC,IAAI,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,IAAI;CAAE,CAAC;AAE/D;;;;;;;GAOG;AACH,MAAM,MAAM,UAAU,CAAC,CAAC,IAAI,CAC1B,IAAI,EAAE,aAAa,CAAC,CAAC,CAAC,EACtB,OAAO,EAAE,MAAM,KACZ,aAAa,CAAC,CAAC,CAAC,CAAC;AAEtB;;;;;;GAMG;AACH,MAAM,MAAM,iBAAiB,CAAC,CAAC,IAAI;IACjC,4DAA4D;IAC5D,MAAM,CAAC,EAAE,OAAO,CAAC,gBAAgB,CAAC,CAAC;IACnC;;;;OAIG;IACH,aAAa,CAAC,EAAE;SAAG,CAAC,IAAI,MAAM,CAAC,CAAC,CAAC,EAAE,OAAO,CAAC,gBAAgB,CAAC;KAAE,CAAC;IAC/D,wEAAwE;IACxE,WAAW,CAAC,EAAE,UAAU,CAAC,CAAC,CAAC,EAAE,CAAC;IAC9B,qFAAqF;IACrF,UAAU,CAAC,EAAE,SAAS,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;IAC3C,yEAAyE;IACzE,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB,CAAC;AAEF;;;;;;;;GAQG;AACH,MAAM,MAAM,gBAAgB,GAAG,MAAM,GAAG,aAAa,GAAG,YAAY,CAAC;AAErE;;;;;;;;;;;;;GAaG;AACH,MAAM,MAAM,WAAW,GACnB;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,GAChC;IAAE,IAAI,EAAE,KAAK,CAAA;CAAE,GACf;IAAE,IAAI,EAAE,WAAW,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,GACrC;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,CAAC;AAErC;;;GAGG;AACH,MAAM,MAAM,QAAQ,GAAG;IACrB,gEAAgE;IAChE,KAAK,EAAE,MAAM,CAAC;IACd,kCAAkC;IAClC,SAAS,EAAE,OAAO,CAAC;IACnB,kEAAkE;IAClE,cAAc,EAAE,MAAM,CAAC;IACvB,iCAAiC;IACjC,QAAQ,EAAE,OAAO,CAAC;CACnB,CAAC;AAEF;;;;GAIG;AACH,MAAM,MAAM,gBAAgB,CAAC,CAAC,IAAI;IAChC,8EAA8E;IAC9E,KAAK,EAAE,CAAC,GAAG,IAAI,CAAC;IAChB,4EAA4E;IAC5E,UAAU,EAAE,MAAM,GAAG,IAAI,CAAC;IAC1B,uFAAuF;IACvF,QAAQ,EAAE,QAAQ,GAAG,SAAS,CAAC;CAChC,CAAC;AAEF;;;;GAIG;AACH,MAAM,MAAM,YAAY,GAAG,CAAC,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,KAAK,OAAO,CAAC;AAE/D;;;GAGG;AACH,MAAM,MAAM,gBAAgB,GAAG;IAC7B,kEAAkE;IAClE,QAAQ,EAAE,gBAAgB,CAAC;IAC3B,gEAAgE;IAChE,oBAAoB,EAAE,MAAM,CAAC;IAC7B,+EAA+E;IAC/E,iBAAiB,EAAE,MAAM,CAAC;IAC1B,qFAAqF;IACrF,mBAAmB,EAAE,MAAM,CAAC;IAC5B,4EAA4E;IAC5E,OAAO,EAAE,YAAY,CAAC;CACvB,CAAC;AAEF;;;;GAIG;AACH,YAAY,EAAE,SAAS,EAAE,CAAC;AAE1B;;;;GAIG;AACH,MAAM,MAAM,SAAS,GAAG;IACtB,4GAA4G;IAC5G,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IAChC,qGAAqG;IACrG,QAAQ,CAAC,EAAE,MAAM,EAAE,CAAC;CACrB,CAAC;AAEF;;GAEG;AACH,MAAM,MAAM,gBAAgB,GAAG;IAC7B,+DAA+D;IAC/D,KAAK,EAAE,OAAO,CAAC;IACf,6EAA6E;IAC7E,UAAU,EAAE,SAAS,EAAE,CAAC;CACzB,CAAC;AAEF;;GAEG;AACH,MAAM,MAAM,cAAc,GAAG;IAC3B,gFAAgF;IAChF,YAAY,EAAE,MAAM,CAAC;IACrB,6DAA6D;IAC7D,SAAS,EAAE,OAAO,CAAC;IACnB,8DAA8D;IAC9D,UAAU,EAAE,MAAM,CAAC;CACpB,CAAC;AAEF;;;;;;GAMG;AACH,MAAM,MAAM,gBAAgB,CAAC,CAAC,IAAI;IAChC,2FAA2F;IAC3F,IAAI,EAAE,aAAa,CAAC,CAAC,CAAC,CAAC;IACvB,6EAA6E;IAC7E,UAAU,EAAE;SAAG,CAAC,IAAI,MAAM,CAAC,GAAG,MAAM,GAAG,IAAI;KAAE,CAAC;IAC9C;;;;OAIG;IACH,OAAO,EAAE;SAAG,CAAC,IAAI,MAAM,CAAC,GAAG,WAAW,GAAG,IAAI;KAAE,CAAC;IAChD,+EAA+E;IAC/E,SAAS,EAAE,QAAQ,EAAE,CAAC;IACtB,mDAAmD;IACnD,OAAO,EAAE,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC;IACrB,0CAA0C;IAC1C,UAAU,EAAE,gBAAgB,CAAC;IAC7B,8CAA8C;IAC9C,IAAI,EAAE,cAAc,CAAC;CACtB,CAAC"}
1
+ {"version":3,"file":"merge.types.d.ts","sourceRoot":"","sources":["../../src/types/merge.types.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AACjD,OAAO,KAAK,EAAE,SAAS,EAAE,SAAS,EAAE,MAAM,qBAAqB,CAAC;AAChE,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,mBAAmB,CAAC;AAEhD;;;;;;GAMG;AACH,MAAM,MAAM,aAAa,CAAC,CAAC,IAAI;KAAG,CAAC,IAAI,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,IAAI;CAAE,CAAC;AAE/D;;;;;;;;;;;;;;;;;GAiBG;AACH,MAAM,MAAM,UAAU,CAAC,CAAC,EAAE,QAAQ,GAAG,OAAO,IAAI,CAC9C,IAAI,EAAE,aAAa,CAAC,CAAC,CAAC,EACtB,OAAO,EAAE,MAAM,EACf,OAAO,CAAC,EAAE,QAAQ,KACf,aAAa,CAAC,CAAC,CAAC,CAAC;AAEtB;;;;;;;;GAQG;AACH,MAAM,MAAM,iBAAiB,CAAC,CAAC,EAAE,QAAQ,GAAG,OAAO,IAAI;IACrD,4DAA4D;IAC5D,MAAM,CAAC,EAAE,OAAO,CAAC,gBAAgB,CAAC,CAAC;IACnC;;;;OAIG;IACH,aAAa,CAAC,EAAE;SAAG,CAAC,IAAI,MAAM,CAAC,CAAC,CAAC,EAAE,OAAO,CAAC,gBAAgB,CAAC;KAAE,CAAC;IAC/D,wEAAwE;IACxE,WAAW,CAAC,EAAE,UAAU,CAAC,CAAC,EAAE,QAAQ,CAAC,EAAE,CAAC;IACxC,qFAAqF;IACrF,UAAU,CAAC,EAAE,SAAS,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;IAC3C,yEAAyE;IACzE,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB,CAAC;AAEF;;;;;;;;GAQG;AACH,MAAM,MAAM,gBAAgB,GAAG,MAAM,GAAG,aAAa,GAAG,YAAY,CAAC;AAErE;;;;;;;;;;;;;GAaG;AACH,MAAM,MAAM,WAAW,GACnB;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,GAChC;IAAE,IAAI,EAAE,KAAK,CAAA;CAAE,GACf;IAAE,IAAI,EAAE,WAAW,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,GACrC;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,CAAC;AAErC;;;GAGG;AACH,MAAM,MAAM,QAAQ,GAAG;IACrB,gEAAgE;IAChE,KAAK,EAAE,MAAM,CAAC;IACd,kCAAkC;IAClC,SAAS,EAAE,OAAO,CAAC;IACnB,kEAAkE;IAClE,cAAc,EAAE,MAAM,CAAC;IACvB,iCAAiC;IACjC,QAAQ,EAAE,OAAO,CAAC;CACnB,CAAC;AAEF;;;;GAIG;AACH,MAAM,MAAM,gBAAgB,CAAC,CAAC,IAAI;IAChC,8EAA8E;IAC9E,KAAK,EAAE,CAAC,GAAG,IAAI,CAAC;IAChB,4EAA4E;IAC5E,UAAU,EAAE,MAAM,GAAG,IAAI,CAAC;IAC1B,uFAAuF;IACvF,QAAQ,EAAE,QAAQ,GAAG,SAAS,CAAC;CAChC,CAAC;AAEF;;;;GAIG;AACH,MAAM,MAAM,YAAY,GAAG,CAAC,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,KAAK,OAAO,CAAC;AAE/D;;;GAGG;AACH,MAAM,MAAM,gBAAgB,GAAG;IAC7B,kEAAkE;IAClE,QAAQ,EAAE,gBAAgB,CAAC;IAC3B,gEAAgE;IAChE,oBAAoB,EAAE,MAAM,CAAC;IAC7B,+EAA+E;IAC/E,iBAAiB,EAAE,MAAM,CAAC;IAC1B,qFAAqF;IACrF,mBAAmB,EAAE,MAAM,CAAC;IAC5B,4EAA4E;IAC5E,OAAO,EAAE,YAAY,CAAC;CACvB,CAAC;AAEF;;;;GAIG;AACH,YAAY,EAAE,SAAS,EAAE,CAAC;AAE1B;;;;GAIG;AACH,MAAM,MAAM,SAAS,GAAG;IACtB,4GAA4G;IAC5G,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IAChC,qGAAqG;IACrG,QAAQ,CAAC,EAAE,MAAM,EAAE,CAAC;CACrB,CAAC;AAEF;;GAEG;AACH,MAAM,MAAM,gBAAgB,GAAG;IAC7B,+DAA+D;IAC/D,KAAK,EAAE,OAAO,CAAC;IACf,6EAA6E;IAC7E,UAAU,EAAE,SAAS,EAAE,CAAC;CACzB,CAAC;AAEF;;GAEG;AACH,MAAM,MAAM,cAAc,GAAG;IAC3B,gFAAgF;IAChF,YAAY,EAAE,MAAM,CAAC;IACrB,6DAA6D;IAC7D,SAAS,EAAE,OAAO,CAAC;IACnB,8DAA8D;IAC9D,UAAU,EAAE,MAAM,CAAC;CACpB,CAAC;AAEF;;;;;;GAMG;AACH,MAAM,MAAM,gBAAgB,CAAC,CAAC,IAAI;IAChC,2FAA2F;IAC3F,IAAI,EAAE,aAAa,CAAC,CAAC,CAAC,CAAC;IACvB,6EAA6E;IAC7E,UAAU,EAAE;SAAG,CAAC,IAAI,MAAM,CAAC,GAAG,MAAM,GAAG,IAAI;KAAE,CAAC;IAC9C;;;;OAIG;IACH,OAAO,EAAE;SAAG,CAAC,IAAI,MAAM,CAAC,GAAG,WAAW,GAAG,IAAI;KAAE,CAAC;IAChD,+EAA+E;IAC/E,SAAS,EAAE,QAAQ,EAAE,CAAC;IACtB,mDAAmD;IACnD,OAAO,EAAE,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC;IACrB,0CAA0C;IAC1C,UAAU,EAAE,gBAAgB,CAAC;IAC7B,8CAA8C;IAC9C,IAAI,EAAE,cAAc,CAAC;CACtB,CAAC"}
@@ -8,7 +8,7 @@ export type LlmProvider = {
8
8
  /**
9
9
  * Send `request` to the underlying model and return the structured values
10
10
  * it produced. Observability concerns (token counters, latency, cost) are
11
- * the caller's responsibility they live outside the llmbic contract so
11
+ * the caller's responsibility - they live outside the llmbic contract so
12
12
  * the library stays free of vendor-specific metering.
13
13
  *
14
14
  * @param request - Prompt, user content, and JSON Schema built by {@link prompt.build}.
@@ -13,8 +13,18 @@ export type RuleMatch<T> = {
13
13
  /**
14
14
  * A deterministic rule that tries to extract a single schema field from raw
15
15
  * content. `extract` returns `null` when the rule does not apply.
16
+ *
17
+ * Rules can optionally accept a `context` argument: an opaque, caller-defined
18
+ * value forwarded verbatim by `rule.apply` / `Extractor.extract`. Typical use
19
+ * is to expose per-call metadata (locale, tenant-specific configuration,
20
+ * feature flags) rules need to decide whether they apply. `TContext`
21
+ * defaults to `unknown` so context-unaware rules stay assignable to arrays
22
+ * typed with any context.
23
+ *
24
+ * @typeParam TContext - Shape of the optional per-call context forwarded to
25
+ * `extract`. Defaults to `unknown`.
16
26
  */
17
- export type ExtractionRule = {
27
+ export type ExtractionRule<TContext = unknown> = {
18
28
  /**
19
29
  * Stable identifier surfaced in `ExtractionResult.sources` when this rule
20
30
  * produces the kept value. Optional: when omitted, `rule.apply` assigns
@@ -24,8 +34,13 @@ export type ExtractionRule = {
24
34
  id?: string;
25
35
  /** Name of the schema field this rule targets. */
26
36
  field: string;
27
- /** Inspects `content` and returns a match, or `null` if nothing was found. */
28
- extract: (content: string) => RuleMatch<unknown> | null;
37
+ /**
38
+ * Inspects `content` - and optionally a caller-provided `context` -
39
+ * and returns a match, or `null` if nothing was found. `context` is
40
+ * forwarded verbatim by `rule.apply` / `Extractor.extract` and left
41
+ * `undefined` when the caller passes no context.
42
+ */
43
+ extract: (content: string, context?: TContext) => RuleMatch<unknown> | null;
29
44
  };
30
45
  /**
31
46
  * The output of the rules pass. Contains the values that deterministic rules
@@ -1 +1 @@
1
- {"version":3,"file":"rule.types.d.ts","sourceRoot":"","sources":["../../src/types/rule.types.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AACH,MAAM,MAAM,SAAS,CAAC,CAAC,IAAI;IACzB,gDAAgD;IAChD,KAAK,EAAE,CAAC,CAAC;IACT,4EAA4E;IAC5E,UAAU,EAAE,MAAM,CAAC;CACpB,CAAC;AAEF;;;GAGG;AACH,MAAM,MAAM,cAAc,GAAG;IAC3B;;;;;OAKG;IACH,EAAE,CAAC,EAAE,MAAM,CAAC;IACZ,kDAAkD;IAClD,KAAK,EAAE,MAAM,CAAC;IACd,8EAA8E;IAC9E,OAAO,EAAE,CAAC,OAAO,EAAE,MAAM,KAAK,SAAS,CAAC,OAAO,CAAC,GAAG,IAAI,CAAC;CACzD,CAAC;AAEF;;;;;;GAMG;AACH,MAAM,MAAM,WAAW,CAAC,CAAC,IAAI;IAC3B,mEAAmE;IACnE,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC,CAAC;IACnB,yDAAyD;IACzD,UAAU,EAAE,OAAO,CAAC,MAAM,CAAC,MAAM,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC;IAC7C;;;;;;;OAOG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC,MAAM,CAAC,MAAM,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC;IAC7C,8DAA8D;IAC9D,OAAO,EAAE,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC;CACtB,CAAC"}
1
+ {"version":3,"file":"rule.types.d.ts","sourceRoot":"","sources":["../../src/types/rule.types.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AACH,MAAM,MAAM,SAAS,CAAC,CAAC,IAAI;IACzB,gDAAgD;IAChD,KAAK,EAAE,CAAC,CAAC;IACT,4EAA4E;IAC5E,UAAU,EAAE,MAAM,CAAC;CACpB,CAAC;AAEF;;;;;;;;;;;;;GAaG;AACH,MAAM,MAAM,cAAc,CAAC,QAAQ,GAAG,OAAO,IAAI;IAC/C;;;;;OAKG;IACH,EAAE,CAAC,EAAE,MAAM,CAAC;IACZ,kDAAkD;IAClD,KAAK,EAAE,MAAM,CAAC;IACd;;;;;OAKG;IACH,OAAO,EAAE,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,QAAQ,KAAK,SAAS,CAAC,OAAO,CAAC,GAAG,IAAI,CAAC;CAC7E,CAAC;AAEF;;;;;;GAMG;AACH,MAAM,MAAM,WAAW,CAAC,CAAC,IAAI;IAC3B,mEAAmE;IACnE,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC,CAAC;IACnB,yDAAyD;IACzD,UAAU,EAAE,OAAO,CAAC,MAAM,CAAC,MAAM,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC;IAC7C;;;;;;;OAOG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC,MAAM,CAAC,MAAM,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC;IAC7C,8DAA8D;IAC9D,OAAO,EAAE,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC;CACtB,CAAC"}
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "llmbic",
3
- "version": "1.2.0",
3
+ "version": "1.4.0",
4
4
  "description": "Hybrid data extraction — deterministic rules + LLM fallback, with per-field confidence scoring.",
5
5
  "type": "module",
6
6
  "license": "MIT",