purecontext-mcp 1.5.2 → 1.11.0

package/WORKFLOW-PR-REVIEW.md

@@ -1,199 +1,245 @@
-# Workflow: Reviewing a Pull Request
-
-**Scenario:** It's Tuesday morning. You open GitHub and find a pull request sitting in your queue: "Migrate user authentication to OAuth2 — 40 files changed." You're the designated reviewer. The author is a colleague you trust, but this is a large, cross-cutting change affecting the core authentication flow. You have about 45 minutes before your next meeting.
-
-Without context, you'd start reading diffs top to bottom, hoping to understand the intent as you go. With PureContext, you start by understanding the impact, then read strategically.
-
----
-
-## Step 1: Understand the scope before reading anything
-
-**You:** "I have a PR to review — 40 files changed in the authentication migration. Before I read any diffs, give me a symbol-level analysis of what actually changed."
-
-**Claude** calls `analyze_diff(base: "main", head: "feature/oauth2-migration")`:
-
-```
-Symbols modified (signature changed — potential breaking changes):
-  authenticateUser()         apps/auth/validator.py    signature changed
-  require_auth               apps/auth/decorators.py   implementation changed
-  UserPermissions            apps/core/types.py         fields added
-
-Symbols modified (implementation only — no signature change):
-  JWTMiddleware              apps/auth/middleware.py    replaced internally
-  createSession()            apps/auth/session.py       updated token format
-  ... (12 more)
-
-Symbols added (new in this PR):
-  OAuthClient                apps/auth/oauth2.py        new class
-  exchangeOAuthCode()        apps/auth/oauth2.py        new
-  refreshOAuthToken()        apps/auth/oauth2.py        new
-  OAuthCallbackView          apps/auth/views.py          new
-  ... (8 more)
-
-Symbols deleted:
-  generateLegacyToken()      apps/auth/legacy.py        removed
-  OldSessionManager          apps/auth/sessions.py      removed
-  validateBasicAuth()        apps/auth/basic.py         removed
-
-Blast radius of modified symbols: 47 files
-Review priority: HIGH (signature changes to authenticateUser and require_auth)
-```
-
-In 30 seconds you know:
-- The signature of `authenticateUser` changed — everything that calls it may need to be checked
-- `require_auth` was modified — it wraps 134 view functions, so behavior changes here affect the entire application
-- Three symbols were deleted — are they truly dead, or are there call sites the PR missed?
-- The real blast radius is 47 files, not 40 (some impact is indirect)
-
-This frames your entire review before you've read a diff.
-
----
-
-## Step 2: Verify the deleted symbols were actually unused
-
-The deleted symbols are the first concern. Deleting code that's still called causes a runtime error.
-
-**You:** "Three symbols were deleted. Verify that they had no importers in main — confirm they were actually dead code before this PR."
-
-**Claude** calls `get_blast_radius` on each deleted symbol against the main branch index:
-
-```
-generateLegacyToken()  — 0 importers in main (confirmed dead)
-OldSessionManager      — 0 importers in main (confirmed dead)
-validateBasicAuth()    — 0 importers in main (confirmed dead)
-```
-
-All three confirmed dead. The author cleaned up dead code correctly. This concern is closed.
-
----
-
-## Step 3: Check the signature change for `authenticateUser`
-
-A signature change to a function is the highest-risk change in any PR. It means every call site needs to handle the new interface.
-
-**You:** "authenticateUser changed its signature. Show me the old signature, the new one, and all the places that call it."
-
-**Claude** retrieves the symbol history for `authenticateUser` and the current source:
-
-```
-Old signature (main):
-  def authenticate_user(username: str, password: str) -> Optional[User]
-
-New signature (this PR):
-  def authenticate_user(credentials: OAuthCredentials | PasswordCredentials) -> AuthResult
-```
-
-The parameter type changed from two positional strings to a union type, and the return type changed from `Optional[User]` to `AuthResult`. This is a significant interface change.
-
-**Claude** calls `find_references(symbolId: "authenticateUser")` on the current branch:
-
-```
-authenticate_user() is called in 6 places:
-
-  apps/auth/views.py:45      LoginView.post()         ← using new signature ✓
-  apps/users/tests/test_auth.py:23   test_login()    ← updated ✓
-  apps/users/tests/test_auth.py:67   test_lockout()  ← updated ✓
-  apps/api/auth.py:89        api_login()              ← using new signature ✓
-  apps/admin/views.py:134    admin_login()            ← still using old signature ✗
-  apps/integrations/sso.py:67  sso_authenticate()    ← still using old signature ✗
-```
-
-Two call sites weren't updated. `admin_login` and `sso_authenticate` are still passing two positional string arguments. This is a bug in the PR — it would pass type checking if the types weren't enforced strictly, but would fail at runtime.
-
-You've found the blocking issue in the PR. Two minutes into the review.
-
----
-
-## Step 4: Verify the critical path
-
-`require_auth` is the decorator used by 134 views. It was modified. You need to know the modification is backward compatible.
-
-**You:** "require_auth was modified. Show me what changed and verify that all 134 views that use it still work with the new implementation."
-
-**Claude** retrieves the new source for `require_auth`:
-
-```python
-def require_auth(view_func):
-    @wraps(view_func)
-    def wrapper(request, *args, **kwargs):
-        # NEW: Accept both JWT (legacy) and OAuth2 Bearer tokens
-        auth_header = request.META.get('HTTP_AUTHORIZATION', '')
-        if auth_header.startswith('Bearer '):
-            user = authenticate_oauth_token(auth_header[7:])
-        else:
-            user = authenticate_jwt_token(request)  # legacy path preserved
-        if user is None:
-            return HttpResponse(status=401)
-        request.user = user
-        return view_func(request, *args, **kwargs)
-    return wrapper
-```
-
-The implementation accepts both token formats — OAuth2 Bearer tokens and the legacy JWT. The 134 decorated views don't need to be updated because the decorator handles the transition transparently. This is a good implementation decision, and it's verifiable from the code.
-
-**You:** "This looks correct — it's a compatible shim. But check: is there any test that specifically covers the JWT fallback path in the new implementation?"
-
-**Claude** calls `search_symbols(query: "authenticate_jwt_token", filePath: "tests/**")`:
-
-```
-authenticate_jwt_token referenced in tests:
-  tests/auth/test_middleware.py    test_jwt_fallback()   ← exists ✓
-  tests/auth/test_decorators.py    test_require_auth()   ← exists ✓
-```
-
-The fallback path is tested. The implementation is sound.
-
----
-
-## Step 5: Check for any missed text-level dependencies
-
-Symbol analysis catches structured dependencies. But JWT-specific string patterns — cache keys, token format strings, configuration keys — might be missed.
-
-**You:** "Search for any remaining references to the old JWT configuration key or the old session format that might have been missed."
-
-**Claude** calls `search_text(query: "JWT_SECRET", filePath: "**/*.py")`:
-
-```
-Remaining JWT_SECRET references:
-  apps/auth/oauth2.py:156    settings.JWT_SECRET   ← why does the new OAuth module reference this?
-```
-
-Unexpected. The new OAuth2 module references `JWT_SECRET`. You open the source:
-
-```python
-# Temporary: use JWT_SECRET as the OAuth state parameter signing key
-# TODO: Replace with dedicated OAUTH_STATE_SECRET before merge
-state_sig = hmac.new(settings.JWT_SECRET.encode(), ...)
-```
-
-The author left a TODO comment but didn't create a separate configuration key. This is a code smell — the OAuth implementation is reusing the JWT secret for a different purpose, which violates key isolation. Flag it in the review.
-
----
-
-## The review summary
-
-45 minutes, structured review. Findings:
-
-| Finding | Severity | Location |
-|---------|----------|----------|
-| `authenticate_user` called with old signature | **Blocking** | `admin/views.py:134`, `integrations/sso.py:67` |
-| JWT secret reused as OAuth state signing key | **Major** — flag before merge | `auth/oauth2.py:156` |
-| Deleted symbols confirmed dead | **Pass** | legacy.py, sessions.py, basic.py |
-| `require_auth` shim correctly backward compatible | **Pass** | auth/decorators.py |
-| Legacy fallback path covered by tests | **Pass** | tests/auth/ |
-
-You found two real issues — one blocking, one major — before reading most of the diff. The blocking issue (two call sites using the wrong signature) would have been a runtime error in production. The major issue (key reuse) is a security design problem.
-
----
-
-## What made this review effective
-
-**Start with impact, not diffs.** `analyze_diff` gave you the symbol-level map before you read anything. You knew where to focus.
-
-**Verify deletions first.** Deleted code that's still called is the most dangerous class of PR error. Checking blast radius for deleted symbols takes 30 seconds and catches the worst case.
-
-**Find all call sites for signature changes.** `find_references` across the branch revealed the two missed call sites that static analysis alone might have missed in a dynamically typed codebase.
-
-**Use text search for string-level dependencies.** Symbol analysis doesn't catch JWT_SECRET usage in string context. Text search does.
-
-**Know when to stop.** With the two blocking issues identified and the critical path verified, you have what you need to write a meaningful review. You don't need to read all 40 diffs to give a quality review — you need to read the right ones.
+# Workflow: Reviewing a Pull Request
+
+**Scenario:** It's Tuesday morning. You open GitHub and find a pull request sitting in your queue: "Migrate user authentication to OAuth2 — 40 files changed." You're the designated reviewer. The author is a colleague you trust, but this is a large, cross-cutting change affecting the core authentication flow. You have about 45 minutes before your next meeting.
+
+Without context, you'd start reading diffs top to bottom, hoping to understand the intent as you go. With PureContext, you start by understanding the impact, then read strategically.
+
+---
+
+## Step 1: Understand the scope before reading anything
+
+**You:** "I have a PR to review — 40 files changed in the authentication migration. Before I read any diffs, give me a symbol-level analysis of what actually changed."
+
+**Claude** calls `analyze_diff(base: "main", head: "feature/oauth2-migration")`:
+
+```
+Symbols modified (signature changed — potential breaking changes):
+  authenticateUser()         apps/auth/validator.py    signature changed
+  require_auth               apps/auth/decorators.py   implementation changed
+  UserPermissions            apps/core/types.py         fields added
+
+Symbols modified (implementation only — no signature change):
+  JWTMiddleware              apps/auth/middleware.py    replaced internally
+  createSession()            apps/auth/session.py       updated token format
+  ... (12 more)
+
+Symbols added (new in this PR):
+  OAuthClient                apps/auth/oauth2.py        new class
+  exchangeOAuthCode()        apps/auth/oauth2.py        new
+  refreshOAuthToken()        apps/auth/oauth2.py        new
+  OAuthCallbackView          apps/auth/views.py          new
+  ... (8 more)
+
+Symbols deleted:
+  generateLegacyToken()      apps/auth/legacy.py        removed
+  OldSessionManager          apps/auth/sessions.py      removed
+  validateBasicAuth()        apps/auth/basic.py         removed
+
+Blast radius of modified symbols: 47 files
+
+Aggregate risk: HIGH
+  authenticate_user   high (78/100) — 6 dependents · churn 9/90d · signature changed
+  require_auth        high (71/100) — wraps 134 views · co-changes with middleware tests
+
+missingCoChange (historically move with the edited files, but NOT in this PR):
+  apps/auth/sso_config.py     (confidence 0.62)   ← SSO config usually changes with the auth flow
+  tests/auth/test_sso.py      (confidence 0.55)
+
+coverageGaps (changed symbols with no detected test):
+  OAuthCallbackView    apps/auth/views.py
+
+recommendedTests:
+  tests/auth/test_middleware.py · tests/auth/test_decorators.py
+
+architecturalFlags:
+  (none — changed files don't currently sit on a cycle or cross a layer boundary)
+
+Review priority: CRITICAL (signature breaks + high aggregate risk)
+```
+
+In 30 seconds you know — without reading a diff:
+- The signature of `authenticateUser` changed and it scores **high** composite risk — everything that calls it must be checked
+- `require_auth` was modified — it wraps 134 view functions, so behavior changes here affect the entire application
+- Three symbols were deleted — are they truly dead, or are there call sites the PR missed?
+- The real blast radius is 47 files, not 40 (some impact is indirect)
+- **`missingCoChange` is the senior-reviewer instinct made explicit:** `sso_config.py` and `test_sso.py` historically move with the auth flow but aren't in this PR — likely an omission to ask the author about
+- `OAuthCallbackView` ships with no test
+
+`analyze_diff` returns all of this in one call (the risk / co-change / test / flag sections default on; switch any off for cheap runs). This frames your entire review before you've read a diff.
+
+---
+
+## Step 2: Verify the deleted symbols were actually unused
+
+The deleted symbols are the first concern. Deleting code that's still called causes a runtime error.
+
+**You:** "Three symbols were deleted. Verify that they had no importers in main — confirm they were actually dead code before this PR."
+
+**Claude** calls `get_blast_radius` on each deleted symbol against the main branch index:
+
+```
+generateLegacyToken()  — 0 importers in main (confirmed dead)
+OldSessionManager      — 0 importers in main (confirmed dead)
+validateBasicAuth()    — 0 importers in main (confirmed dead)
+```
+
+All three confirmed dead. The author cleaned up dead code correctly. This concern is closed.
+
+---
+
+## Step 3: Check the signature change for `authenticateUser`
+
+A signature change to a function is the highest-risk change in any PR. It means every call site needs to handle the new interface.
+
+**You:** "authenticateUser changed its signature. Show me the old signature, the new one, and all the places that call it."
+
+**Claude** retrieves the symbol history for `authenticateUser` and the current source:
+
+```
+Old signature (main):
+  def authenticate_user(username: str, password: str) -> Optional[User]
+
+New signature (this PR):
+  def authenticate_user(credentials: OAuthCredentials | PasswordCredentials) -> AuthResult
+```
+
+The parameter type changed from two positional strings to a union type, and the return type changed from `Optional[User]` to `AuthResult`. This is a significant interface change.
+
+**Claude** calls `find_references(symbolId: "authenticateUser")` on the current branch:
+
+```
+authenticate_user() is called in 6 places:
+
+  apps/auth/views.py:45      LoginView.post()         ← using new signature ✓
+  apps/users/tests/test_auth.py:23   test_login()    ← updated ✓
+  apps/users/tests/test_auth.py:67   test_lockout()  ← updated ✓
+  apps/api/auth.py:89        api_login()              ← using new signature ✓
+  apps/admin/views.py:134    admin_login()            ← still using old signature ✗
+  apps/integrations/sso.py:67  sso_authenticate()    ← still using old signature ✗
+```
+
+Two call sites weren't updated. `admin_login` and `sso_authenticate` are still passing two positional string arguments. This is a bug in the PR — it would pass type checking if the types weren't enforced strictly, but would fail at runtime.
+
+You've found the blocking issue in the PR. Two minutes into the review.
+
+---
+
+## Step 4: Verify the critical path
+
+`require_auth` is the decorator used by 134 views. It was modified. You need to know the modification is backward compatible.
+
+**You:** "require_auth was modified. Show me what changed and verify that all 134 views that use it still work with the new implementation."
+
+**Claude** retrieves the new source for `require_auth`:
+
+```python
+def require_auth(view_func):
+    @wraps(view_func)
+    def wrapper(request, *args, **kwargs):
+        # NEW: Accept both JWT (legacy) and OAuth2 Bearer tokens
+        auth_header = request.META.get('HTTP_AUTHORIZATION', '')
+        if auth_header.startswith('Bearer '):
+            user = authenticate_oauth_token(auth_header[7:])
+        else:
+            user = authenticate_jwt_token(request)  # legacy path preserved
+        if user is None:
+            return HttpResponse(status=401)
+        request.user = user
+        return view_func(request, *args, **kwargs)
+    return wrapper
+```
+
+The implementation accepts both token formats — OAuth2 Bearer tokens and the legacy JWT. The 134 decorated views don't need to be updated because the decorator handles the transition transparently. This is a good implementation decision, and it's verifiable from the code.
+
+**You:** "This looks correct — it's a compatible shim. But check: is there any test that specifically covers the JWT fallback path in the new implementation?"
+
+**Claude** calls `search_symbols(query: "authenticate_jwt_token", filePath: "tests/**")`:
+
+```
+authenticate_jwt_token referenced in tests:
+  tests/auth/test_middleware.py    test_jwt_fallback()   ← exists ✓
+  tests/auth/test_decorators.py    test_require_auth()   ← exists ✓
+```
+
+The fallback path is tested. The implementation is sound.
+
+---
+
+## Step 5: Check for any missed text-level dependencies
+
+Symbol analysis catches structured dependencies. But JWT-specific string patterns — cache keys, token format strings, configuration keys — might be missed.
+
+**You:** "Search for any remaining references to the old JWT configuration key or the old session format that might have been missed."
+
+**Claude** calls `search_text(query: "JWT_SECRET", filePath: "**/*.py")`:
+
+```
+Remaining JWT_SECRET references:
+  apps/auth/oauth2.py:156    settings.JWT_SECRET   ← why does the new OAuth module reference this?
+```
+
+Unexpected. The new OAuth2 module references `JWT_SECRET`. You open the source:
+
+```python
+# Temporary: use JWT_SECRET as the OAuth state parameter signing key
+# TODO: Replace with dedicated OAUTH_STATE_SECRET before merge
+state_sig = hmac.new(settings.JWT_SECRET.encode(), ...)
+```
+
+The author left a TODO comment but didn't create a separate configuration key. This is a code smell — the OAuth implementation is reusing the JWT secret for a different purpose, which violates key isolation. Flag it in the review.
+
+---
+
+## Step 6: Did the migration make the architecture worse?
+
+A 40-file migration is exactly the kind of change that quietly introduces a new import cycle or layer violation. If a baseline architecture snapshot was taken on `main` (e.g. in CI before the branch diverged), `compare_change_impact` reports only what *this* change introduced.
+
+**You:** "Did this PR introduce any new import cycles or layer violations versus main?"
+
+```
+compare_change_impact(repoId, baselineSnapshotId: "main-baseline") →
+
+  verdict: "regressed"
+  newCycles: [ [ "apps/auth/oauth2.py", "apps/auth/views.py", "apps/auth/oauth2.py" ] ]
+  newLayerViolations: [ ]
+  resolvedCycles: [ ]
+```
+
+A new cycle between `oauth2.py` and `views.py` that did not exist on `main` — introduced by this PR. Unlike `analyze_diff`'s `architecturalFlags` (which flag *pre-existing* structure), this is a genuine regression to raise. (The PR author can run the same check locally before pushing — and `verify_change` to confirm they covered the `missingCoChange` files surfaced in Step 1.)
+
+---
+
+## The review summary
+
+45 minutes, structured review. Findings:
+
+| Finding | Severity | Location |
+|---------|----------|----------|
+| `authenticate_user` called with old signature | **Blocking** | `admin/views.py:134`, `integrations/sso.py:67` |
+| New import cycle introduced (oauth2 ⇄ views) | **Blocking** | `auth/oauth2.py` ⇄ `auth/views.py` |
+| JWT secret reused as OAuth state signing key | **Major** — flag before merge | `auth/oauth2.py:156` |
+| SSO config historically co-changes but absent from PR | **Question for author** | `auth/sso_config.py` |
+| `OAuthCallbackView` ships with no test | **Minor** | `auth/views.py` |
+| Deleted symbols confirmed dead | **Pass** | legacy.py, sessions.py, basic.py |
+| `require_auth` shim correctly backward compatible | **Pass** | auth/decorators.py |
+| Legacy fallback path covered by tests | **Pass** | tests/auth/ |
+
+You found two real issues — one blocking, one major — before reading most of the diff. The blocking issue (two call sites using the wrong signature) would have been a runtime error in production. The major issue (key reuse) is a security design problem.
+
+---
+
+## What made this review effective
+
+**Start with impact, not diffs.** `analyze_diff` gave you the symbol-level map before you read anything. You knew where to focus.
+
+**Verify deletions first.** Deleted code that's still called is the most dangerous class of PR error. Checking blast radius for deleted symbols takes 30 seconds and catches the worst case.
+
+**Find all call sites for signature changes.** `find_references` across the branch revealed the two missed call sites that static analysis alone might have missed in a dynamically typed codebase.
+
+**Use text search for string-level dependencies.** Symbol analysis doesn't catch JWT_SECRET usage in string context. Text search does.
+
+**Know when to stop.** With the two blocking issues identified and the critical path verified, you have what you need to write a meaningful review. You don't need to read all 40 diffs to give a quality review — you need to read the right ones.
+
+---
+
+→ Reference: [MCP Tools Reference](docs/06-tools-reference.md) — `analyze_diff`, `compare_change_impact`, `verify_change`, `prepare_change`, `find_references`, `get_blast_radius`, `get_symbol_history`, `search_text`

package/dist/adapters/astro-preprocessor.d.ts

@@ -0,0 +1,25 @@
+/**
+ * Astro component pre-processor.
+ *
+ * An .astro file begins with an optional "frontmatter" block fenced by `---`
+ * lines at the very top of the file; its contents are TypeScript. The remainder
+ * is HTML-like template with JSX-style expressions and component usage, which we
+ * do not index for symbols.
+ *
+ * This extracts the leading frontmatter as a single TypeScript ProcessedBlock.
+ *
+ * Byte-offset correctness:
+ *   offsetInOriginal is computed from Buffer.byteLength() of the prefix up to and
+ *   including the opening fence, never from string character indices.
+ */
+import type { ProcessedBlock } from '../core/types.js';
+/**
+ * Extract the leading `---`-fenced frontmatter of an Astro component as a single
+ * TypeScript block. The fence must be the first non-whitespace content in the
+ * file (`---` appearing later in markup is ignored).
+ *
+ * Returns [] when there is no leading frontmatter.
+ * Throws ParseError when a leading fence is opened but never closed.
+ */
+export declare function splitAstroSFC(source: Buffer, filePath: string): ProcessedBlock[];
+//# sourceMappingURL=astro-preprocessor.d.ts.map

package/dist/adapters/astro-preprocessor.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"astro-preprocessor.d.ts","sourceRoot":"","sources":["../../src/adapters/astro-preprocessor.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;GAaG;AAEH,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,kBAAkB,CAAC;AAKvD;;;;;;;GAOG;AACH,wBAAgB,aAAa,CAAC,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,MAAM,GAAG,cAAc,EAAE,CA6BhF"}

package/dist/adapters/astro-preprocessor.js

@@ -0,0 +1,50 @@
+/**
+ * Astro component pre-processor.
+ *
+ * An .astro file begins with an optional "frontmatter" block fenced by `---`
+ * lines at the very top of the file; its contents are TypeScript. The remainder
+ * is HTML-like template with JSX-style expressions and component usage, which we
+ * do not index for symbols.
+ *
+ * This extracts the leading frontmatter as a single TypeScript ProcessedBlock.
+ *
+ * Byte-offset correctness:
+ *   offsetInOriginal is computed from Buffer.byteLength() of the prefix up to and
+ *   including the opening fence, never from string character indices.
+ */
+import { ParseError } from '../core/errors.js';
+// ─── Public API ───────────────────────────────────────────────────────────────
+/**
+ * Extract the leading `---`-fenced frontmatter of an Astro component as a single
+ * TypeScript block. The fence must be the first non-whitespace content in the
+ * file (`---` appearing later in markup is ignored).
+ *
+ * Returns [] when there is no leading frontmatter.
+ * Throws ParseError when a leading fence is opened but never closed.
+ */
+export function splitAstroSFC(source, filePath) {
+    const str = source.toString('utf8');
+    // The opening fence must be the first non-whitespace content. A line of
+    // exactly `---` (optionally with trailing spaces) starting the file.
+    const openMatch = str.match(/^\s*---[ \t]*\r?\n/);
+    if (!openMatch) {
+        return []; // no frontmatter
+    }
+    const openLen = openMatch[0].length; // chars consumed by leading ws + `---` + newline
+    const rest = str.slice(openLen);
+    // Closing fence: a line that is exactly `---` (optionally trailing spaces).
+    const closeMatch = rest.match(/\r?\n[ \t]*---[ \t]*(?:\r?\n|$)/);
+    if (!closeMatch) {
+        throw new ParseError(`Malformed Astro component: unterminated frontmatter fence`, filePath);
+    }
+    const innerContent = rest.slice(0, closeMatch.index);
+    const offsetInOriginal = Buffer.byteLength(str.slice(0, openLen), 'utf8');
+    return [
+        {
+            content: Buffer.from(innerContent, 'utf8'),
+            language: 'typescript',
+            offsetInOriginal,
+        },
+    ];
+}
+//# sourceMappingURL=astro-preprocessor.js.map

package/dist/adapters/astro-preprocessor.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"astro-preprocessor.js","sourceRoot":"","sources":["../../src/adapters/astro-preprocessor.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;GAaG;AAGH,OAAO,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAE/C,iFAAiF;AAEjF;;;;;;;GAOG;AACH,MAAM,UAAU,aAAa,CAAC,MAAc,EAAE,QAAgB;IAC5D,MAAM,GAAG,GAAG,MAAM,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC;IAEpC,wEAAwE;IACxE,qEAAqE;IACrE,MAAM,SAAS,GAAG,GAAG,CAAC,KAAK,CAAC,oBAAoB,CAAC,CAAC;IAClD,IAAI,CAAC,SAAS,EAAE,CAAC;QACf,OAAO,EAAE,CAAC,CAAC,iBAAiB;IAC9B,CAAC;IAED,MAAM,OAAO,GAAG,SAAS,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,iDAAiD;IACtF,MAAM,IAAI,GAAG,GAAG,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;IAEhC,4EAA4E;IAC5E,MAAM,UAAU,GAAG,IAAI,CAAC,KAAK,CAAC,iCAAiC,CAAC,CAAC;IACjE,IAAI,CAAC,UAAU,EAAE,CAAC;QAChB,MAAM,IAAI,UAAU,CAAC,2DAA2D,EAAE,QAAQ,CAAC,CAAC;IAC9F,CAAC;IAED,MAAM,YAAY,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,UAAU,CAAC,KAAK,CAAC,CAAC;IACrD,MAAM,gBAAgB,GAAG,MAAM,CAAC,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,EAAE,OAAO,CAAC,EAAE,MAAM,CAAC,CAAC;IAE1E,OAAO;QACL;YACE,OAAO,EAAE,MAAM,CAAC,IAAI,CAAC,YAAY,EAAE,MAAM,CAAC;YAC1C,QAAQ,EAAE,YAAY;YACtB,gBAAgB;SACjB;KACF,CAAC;AACJ,CAAC"}

package/dist/adapters/astro.d.ts

@@ -0,0 +1,13 @@
+/**
+ * Astro framework adapter.
+ *
+ * Responsibilities:
+ *  1. Detect Astro projects (package.json declares `astro`/`@astrojs/*`,
+ *     an astro.config.* file, or `.astro` files present — incl. monorepo sub-apps).
+ *  2. Pre-process .astro components: extract the leading `---` frontmatter as a
+ *     TypeScript block via astro-preprocessor.
+ *  3. Emit one `component` symbol per .astro file (name derived from filename).
+ */
+import type { FrameworkAdapter } from '../core/types.js';
+export declare const astroAdapter: FrameworkAdapter;
+//# sourceMappingURL=astro.d.ts.map

package/dist/adapters/astro.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"astro.d.ts","sourceRoot":"","sources":["../../src/adapters/astro.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAKH,OAAO,KAAK,EAAE,gBAAgB,EAAsB,MAAM,kBAAkB,CAAC;AAyB7E,eAAO,MAAM,YAAY,EAAE,gBA0D1B,CAAC"}