@apifuse/provider-sdk 2.2.0-beta.3 → 2.2.0-beta.31

package/src/cli/templates/provider/AGENTS.md.tpl

@@ -4,8 +4,8 @@ You are building an APIFuse provider. APIFuse turns messy upstream APIs into
 normalized, typed, evidence-backed public APIs. A provider that merely proxies
 the upstream is a failed provider, even if every check passes.
 
-This file is the core contract. Detailed procedures live in `skills/` — load
-the matching skill BEFORE working on that area (index at the bottom).
+This file is the core contract. Detailed procedures live in `.agents/skills/` —
+load the matching skill BEFORE working on that area (index at the bottom).
 
 ## Non-negotiable principles
 
@@ -75,13 +75,22 @@ bun run submit-check # structural score; a high score does NOT prove quality
 `submit-check` is a structural gate. Every principle above can be violated
 while scoring 95/100 — reviewers and CI audit for exactly these classes.
 
+## Managed prompt assets
+
+`AGENTS.md` and `.agents/skills/**` are generated by the SDK; `CLAUDE.md`,
+`.claude`, and `.codex` are symlinks onto them so every agent CLI reads the
+same contract. Do not hand-edit these files — regenerate them with
+`bun run sync-assets` (or `bunx apifuse sync-assets .`). `apifuse check` and
+`submit-check` enforce a freshness gate: stale or modified prompt assets
+(tracked in `.apifuse/prompt-assets.json`) block submission until re-synced.
+
 ## Skill index — load before working on:
 
 | Area | Load |
 | --- | --- |
-| Output schemas, mappers, field naming, timestamps, enums | `skills/normalization-standards/SKILL.md` |
-| Upstream request params, new endpoint wiring, field mapping | `skills/upstream-contract-verification/SKILL.md` |
-| Recording fixtures, writing tests against fixtures | `skills/fixtures-and-recording/SKILL.md` |
-| List operations, paging, totals, client-side filtering | `skills/pagination-and-counts/SKILL.md` |
-| healthCheck blocks, error classification, fail-closed guards | `skills/health-checks-and-fail-closed/SKILL.md` |
-| Upstream-specific known pitfalls for THIS bounty | `skills/upstream-notes/` (read every file) |
+| Output schemas, mappers, field naming, timestamps, enums | `.agents/skills/normalization-standards/SKILL.md` |
+| Upstream request params, new endpoint wiring, field mapping | `.agents/skills/upstream-contract-verification/SKILL.md` |
+| Recording fixtures, writing tests against fixtures | `.agents/skills/fixtures-and-recording/SKILL.md` |
+| List operations, paging, totals, client-side filtering | `.agents/skills/pagination-and-counts/SKILL.md` |
+| healthCheck blocks, error classification, fail-closed guards | `.agents/skills/health-checks-and-fail-closed/SKILL.md` |
+| Upstream-specific known pitfalls for THIS bounty | `.agents/skills/upstream-notes/` (read every file) |

package/src/cli/templates/provider/README.md.tpl

@@ -114,10 +114,10 @@ Structured errors return an `error` object with `code`, `message`,
 - Auth flow: call `/auth/start`, then `/auth/continue` with the same `flowId`;
   carry returned `contextPatch` values into the next request's `context`.
 - Stealth/browser runtime: keep access-sensitive operations on `ctx.stealth.fetch()` with an
-  SDK stealth `profile`; the TypeScript stealth runtime uses `impit` internally.
-  `ctx.stealth` supports Chrome/Firefox-style profiles. For TypeScript browser
-  Providers or Safari-specific behavior use `browser.engine: "playwright-stealth"`
-  (`nodriver` is Python-runtime only), then install local Chromium with
+  SDK stealth `profile`; the TypeScript stealth runtime uses `wreq-js` internally
+  and supports Chrome, Firefox, and Safari profiles. Use `ctx.browser` only when
+  the provider needs browser execution; TypeScript browser Providers use
+  `browser.engine: "playwright-stealth"` (`nodriver` is Python-runtime only). Install local Chromium with
   `bunx playwright install chromium` or set `APIFUSE__CDP_POOL__URL`.
 
 ## Next steps