Proposed specificationSource-located exemplarH1

Cache-dialect fanout

Adapt caching to provider-specific interfaces.

JOIN POINTprovider_request_constructionRECORD STATUSCandidate · v0.1.0

UML class view

The proposed contract drawn as participant roles, received calls, and numbered dependencies.

Object interactions

The same roles and calls as a class collaboration and a numbered message sequence.

Object interaction diagram for Cache-dialect fanout, showing role collaboration and a numbered message sequence — FIG. P07 / OBJECT INTERACTIONS
Open full SVG Download PDF

Pointcut

Where the mechanism applies. All four dimensions belong to the proposed match, not just its vocabulary.

Context: A request is built for a provider with cacheable context.
Trigger: A cache key, hint, or control record is attached.
Structure: Provider dialect adapter, cache identity, and response association.
Effect: Compatible cache controls are encoded and unsupported controls are rejected or omitted.

Protected contract

The obligation that clients, operators, and auditors should be able to rely on.

Requires: Provider capability and cache identity are known before dispatch.
Ensures: Cache control maps to the request without changing semantic content.
Invariant: Cache identity never crosses user, tenant, or incompatible provider boundaries.
Violation: Unsupported or invalid hints degrade explicitly without silent semantic drift.

Negative control

A generic response cache is not provider-dialect cache control.

Variation & lifecycle

The hot spot is admitted only where the protected semantics survive.

Permitted variation

Prompt cache keys, cache-control blocks, TTLs, and dialect adapters.

Test obligation

Test identity collisions, invalidation, unsupported providers, and privacy boundaries.

Evolution question

Did cache hints become provider-capability-driven adapters?

Prompt + code design

An illustrative prompt and a small design sketch for the proposed contract. Names and APIs are invented; this is not a repository excerpt.

PROMPT SKETCH

Resolve the provider's cache dialect before dispatch. Attach cache keys and cache-control blocks without changing the semantic request content; if the dialect is unknown, send an uncached request and say so.

CODE DESIGN / PYTHON

def prepare(request, registry):
    dialect = registry.resolve(request.provider)
    if dialect is None:
        return request.without_cache(), "cache dialect unsupported"
    hint = dialect.cache_hint(request.prompt, ttl=request.ttl)
    return request.with_cache(hint), "cache hint attached"

Illustrative design sketch. Caching is an optimization layered on the request, not a semantic rewrite. This example is a teaching aid, not implementation evidence or a conformance claim.

Detection & matching

The frozen rule that retrieves this record, the canonical source exemplar, and the control that should stay unmatched.

Join point: provider_request_construction
Source locator: Barbaste et al., Table 12, p. 53 (OpenCode, “Cache-Dialect Fanout”); source label
Lexical cue: (?i)\b(?:prompt[_-]?cache|cache[_-]?control|cache[_-]?key|cache[_-]?hint|dialect)\bFrozen expression, v0.1.0. A match is a retrieval cue, not a confirmed implementation.
Aliases: None
Canonical exemplar: openai/openai-agents-pythonsrc/agents/run_internal/prompt_cache_key.py:17Support: tests/test_prompt_cache_key.py:1
Negative control: A generic response cache is not provider-dialect cache control.

Scope-anchored review. pohe-agent analyze <repo> --pattern P07 anchors the cue to its enclosing declaration and checks a separate operational signature for all four pointcut dimensions. Missing roles and negative-control risks remain visible; a structural match is not E2/E3. Calibration report ↗

Repository files

Up to five public files retrieved by the frozen cue and pinned to the audited commit. A match is a place to inspect, not a confirmed implementation.

01openai/openai-agents-pythonsrc/agents/run_internal/prompt_cache_key.py:17CANONICAL SOURCE 02aaif-goose/goosecrates/goose-local-inference/src/lib.rs:814RETRIEVAL CUE 03affaan-m/ECCskills/ito-baskets/scripts/ito-baskets.js:158RETRIEVAL CUE 04agno-agi/agnolibs/agno/agno/db/singlestore/singlestore.py:258RETRIEVAL CUE 05Aider-AI/aideraider/coders/base_coder.py:426RETRIEVAL CUE

Evidence & provenance

Each layer answers a different question. Do not substitute retrieval for review.

Source-located exemplar

A concrete source anchor is available for this proposed record. It is one exemplar, not evidence that all repositories—or every contract field—conform.

Review boundary: this candidate and its specification come from an AI-assisted study. Independent human validation remains open.

ANY-EVIDENCE FAMILY COVERAGE34/36

94.4% of repository families in the frozen panel have at least one current cue, historical cue, or canonical source layer. This is not confirmed prevalence.

Current lexical-cue repositories: 38 / 41

Canonical source anchoropenai/openai-agents-python 86bd29878b30src/agents/run_internal/prompt_cache_key.py:17

Supporting surfacetests/test_prompt_cache_key.py:1

Provider-aware prompt-cache key resolution.

Exploratory retrieval cue Regex / v0.1.0

(?i)\b(?:prompt[_-]?cache|cache[_-]?control|cache[_-]?key|cache[_-]?hint|dialect)\b

This expression is a discovery instrument only. A match is a retrieval cue—not a confirmed implementation, pointcut match, or contract proof.