carto-md 2.0.9 → 2.1.0

package/docs/api/get_hotspot_files.md

@@ -0,0 +1,37 @@
+# `get_hotspot_files`
+
+Top files by churn × blast_radius score over a window. The CodeHealth heuristic: high-churn files in high-blast-radius positions are where bugs cluster.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "time_range": {
+      "type": "string",
+      "description": "Window like \"30d\", \"90d\" (default \"90d\")."
+    },
+    "limit": {
+      "type": "number",
+      "description": "Max rows (default 20)."
+    }
+  },
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `time_range` | string | Window like "30d", "90d" (default "90d"). |
+| `limit` | number | Max rows (default 20). |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_iac_resources.md

@@ -0,0 +1,25 @@
+# `get_iac_resources`
+
+Surface Terraform / Helm / Pulumi / AWS CDK resources discovered in the repo. Returns kind, name, file, dependencies.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {},
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+_None._
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_interface_contract.md

@@ -0,0 +1,33 @@
+# `get_interface_contract`
+
+Exported symbols + models + routes the file exposes. Use to understand a module's public API before consuming it.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "file": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "file"
+  ]
+}
+```
+
+## Required arguments
+
+- `file`
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `file` | string |  |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_intervention_history.md

@@ -0,0 +1,32 @@
+# `get_intervention_history`
+
+List interventions (Carto-issued violations and suggestions) optionally filtered by file. Use to see prior warnings on a file before editing it.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "file": {
+      "type": "string",
+      "description": "Optional file filter (relative path from project root)."
+    }
+  },
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `file` | string | Optional file filter (relative path from project root). |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_invariants.md

@@ -0,0 +1,37 @@
+# `get_invariants`
+
+Architectural invariants mined from the import graph: "Domain X never imports from Y", "Files in Z always export N symbols", etc. Confidence-scored.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "domain": {
+      "type": "string",
+      "description": "Optional domain filter."
+    },
+    "threshold": {
+      "type": "number",
+      "description": "Confidence threshold 0-1 (default 0.85)."
+    }
+  },
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `domain` | string | Optional domain filter. |
+| `threshold` | number | Confidence threshold 0-1 (default 0.85). |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_llm_enrichment.md

@@ -0,0 +1,33 @@
+# `get_llm_enrichment`
+
+Per-node summary via a local LLM. Opt-in only; returns disabled stub until `ai.llm` is wired in carto.config.json.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "file": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "file"
+  ]
+}
+```
+
+## Required arguments
+
+- `file`
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `file` | string |  |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_microservice_cut_points.md

@@ -0,0 +1,32 @@
+# `get_microservice_cut_points`
+
+Natural microservice cut-points: domains with high cohesion (intra-edges) AND low external coupling. Use to plan extraction-style refactors.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "threshold": {
+      "type": "number",
+      "description": "Cohesion threshold 0-1 (default 0.7)."
+    }
+  },
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `threshold` | number | Cohesion threshold 0-1 (default 0.7). |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_microservices_migration_cut_points.md

@@ -0,0 +1,25 @@
+# `get_microservices_migration_cut_points`
+
+Suggested microservices extraction order. Repos with high stability (more incoming than outgoing edges) extract first.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {},
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+_None._
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_minimal_context_for_intent.md

@@ -0,0 +1,39 @@
+# `get_minimal_context_for_intent`
+
+Token-budgeted context picker. Given a natural-language intent + a budget (default 4000 tokens), returns the minimum file set needed via hybrid retrieval (structural + lexical + semantic) with RRF fusion and high-blast / same-domain / recent-changes boosts. Reports per-file token cost.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "intent": {
+      "type": "string",
+      "description": "Natural-language description of the change."
+    },
+    "budget_tokens": {
+      "type": "number",
+      "description": "Token budget (default 4000)."
+    }
+  },
+  "required": [
+    "intent"
+  ]
+}
+```
+
+## Required arguments
+
+- `intent`
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `intent` | string | Natural-language description of the change. |
+| `budget_tokens` | number | Token budget (default 4000). |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_models.md

@@ -0,0 +1,32 @@
+# `get_models`
+
+Get all data models (Prisma, Pydantic, TypeScript interfaces, Zod schemas) across the project, optionally filtered by domain.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "domain": {
+      "type": "string",
+      "description": "Optional domain filter e.g. AUTH, DATABASE"
+    }
+  },
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `domain` | string | Optional domain filter e.g. AUTH, DATABASE |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_neighbors.md

@@ -0,0 +1,39 @@
+# `get_neighbors`
+
+Get import graph neighbors of a file — files it imports and files that import it. Returns nodes and edges for visualization.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "file": {
+      "type": "string",
+      "description": "Relative file path from project root"
+    },
+    "hops": {
+      "type": "number",
+      "description": "How many hops to traverse (default 1, max 3)"
+    }
+  },
+  "required": [
+    "file"
+  ]
+}
+```
+
+## Required arguments
+
+- `file`
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `file` | string | Relative file path from project root |
+| `hops` | number | How many hops to traverse (default 1, max 3) |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_org_architecture.md

@@ -0,0 +1,25 @@
+# `get_org_architecture`
+
+Org-wide summary: registered repos + total cross-repo edge count + edges by kind. Requires `carto org init` + `carto org sync`.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {},
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+_None._
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_org_domain_mapping.md

@@ -0,0 +1,25 @@
+# `get_org_domain_mapping`
+
+Per-repo domain list across all org repos (reads each repo's carto.db if registered).
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {},
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+_None._
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_pending_decisions.md

@@ -0,0 +1,32 @@
+# `get_pending_decisions`
+
+Recent decisions with pending/unresolved/HIGH-risk flags in their payload. Surfaces unfinished AI work from the episodic log.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "hours": {
+      "type": "number",
+      "description": "Lookback window in hours (default 6)."
+    }
+  },
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `hours` | number | Lookback window in hours (default 6). |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_predictive_risk.md

@@ -0,0 +1,32 @@
+# `get_predictive_risk`
+
+Predictive risk score per file: P(this file causes the next incident). Combines blast radius, churn, cross-domain coupling, intervention history, test presence into a 0-1 score.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "file": {
+      "type": "string",
+      "description": "Optional single-file filter; otherwise scores all files."
+    }
+  },
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `file` | string | Optional single-file filter; otherwise scores all files. |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_progressive_disclosure_tree.md

@@ -0,0 +1,25 @@
+# `get_progressive_disclosure_tree`
+
+Pre-computed hierarchy: domain → top files per domain → per-file exports. Use as a structured table-of-contents for the codebase before drilling in.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {},
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+_None._
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_recent_decisions.md

@@ -0,0 +1,37 @@
+# `get_recent_decisions`
+
+List recent validation decisions and architectural choices the AI has made in this project. Returns time-descending rows.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "time_range": {
+      "type": "string",
+      "description": "Time window like \"7d\", \"24h\", \"1h\" (default \"7d\")."
+    },
+    "kind": {
+      "type": "string",
+      "description": "Optional filter — e.g. \"validation\"."
+    }
+  },
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `time_range` | string | Time window like "7d", "24h", "1h" (default "7d"). |
+| `kind` | string | Optional filter — e.g. "validation". |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_risk_weighted_blast_radius.md

@@ -0,0 +1,32 @@
+# `get_risk_weighted_blast_radius`
+
+Combine static dependents with runtime call counts (from ingest_otlp_traces or similar) to rank routes by real-world risk. `risk = dependents × runtime_calls + dependents`.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "otlp_path": {
+      "type": "string",
+      "description": "Optional OTLP file for runtime data."
+    }
+  },
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `otlp_path` | string | Optional OTLP file for runtime data. |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_routes.md

@@ -0,0 +1,25 @@
+# `get_routes`
+
+Get all API routes in this project including REST, tRPC, and webhooks.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {},
+  "required": []
+}
+```
+
+## Required arguments
+
+_None._
+
+## Properties
+
+_None._
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_safety_checklist.md

@@ -0,0 +1,33 @@
+# `get_safety_checklist`
+
+Per-file safety checklist: blast radius, cross-domain coupling, missing tests, temporal hotspot, unresolved interventions. Run before writing a high-impact change.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "file": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "file"
+  ]
+}
+```
+
+## Required arguments
+
+- `file`
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `file` | string |  |
+
+## See also
+
+- [Index of all MCP tools](./README.md)

package/docs/api/get_semantic_diff.md

@@ -0,0 +1,34 @@
+# `get_semantic_diff`
+
+Beyond line-by-line: detect renames, symbol relocations across files, and new-domain introductions from a unified diff.
+
+## Input schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "diff": {
+      "type": "string",
+      "description": "Unified diff text."
+    }
+  },
+  "required": [
+    "diff"
+  ]
+}
+```
+
+## Required arguments
+
+- `diff`
+
+## Properties
+
+| Name | Type | Description |
+|------|------|-------------|
+| `diff` | string | Unified diff text. |
+
+## See also
+
+- [Index of all MCP tools](./README.md)