weavatrix 1.9.0 → 1.9.2

package/skill/references/tools/read_source.md

@@ -0,0 +1,31 @@
+# `read_source`
+
+Bounded source context by node or repository path.
+
+## When to use
+
+Read an exact verified line range after a file and location are known.
+
+## Inputs
+
+- `after` (integer, min 0).
+- `before` (integer, min 0).
+- `label` (string).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `path` (string).
+- `start_line` (integer, min 0).
+- `token_budget` (integer, min 1) — Approximate output ceiling in tokens (serialized bytes / 4); result arrays are trimmed from the tail to fit and the report states what was dropped.
+
+## Minimal call
+
+```json
+{
+  "name": "read_source",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/rebuild_graph.md

@@ -0,0 +1,30 @@
+# `rebuild_graph`
+
+Rebuild the derived in-memory graph without source writes.
+
+## When to use
+
+Force an explicit graph rebuild only when automatic refresh is stale or a deliberate mode change is required.
+
+Do not rebuild on every call; the server normally refreshes derived state automatically.
+
+## Inputs
+
+- `mode` ("full" | "no-tests" | "tests-only").
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `precision` (string).
+- `scope` (string).
+
+## Minimal call
+
+```json
+{
+  "name": "rebuild_graph",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/run_audit.md

@@ -0,0 +1,33 @@
+# `run_audit`
+
+Repository structure and evidence completeness audit.
+
+## When to use
+
+Run a broad repository health and evidence-completeness pass before targeted investigation.
+
+## Inputs
+
+- `base_ref` (string).
+- `category` ("all" | "diagnostics" | "structure" | "dependencies" | "runtime").
+- `changed_files` (array<string>).
+- `debt` ("new" | "existing" | "all").
+- `include_capabilities` (boolean).
+- `include_classified` (boolean).
+- `max_findings` (integer, min 0).
+- `min_severity` ("low" | "medium" | "high" | "critical").
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+
+## Minimal call
+
+```json
+{
+  "name": "run_audit",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/search_code.md

@@ -0,0 +1,33 @@
+# `search_code`
+
+Literal or Rust-regex repository search without ripgrep.
+
+## When to use
+
+Find bounded literal or regular-expression matches when the source text is known but its location is not.
+
+## Inputs
+
+- `query` (string, required).
+- `after` (integer, min 0).
+- `before` (integer, min 0).
+- `glob` (string).
+- `is_regex` (boolean).
+- `max_results` (integer, min 0).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `token_budget` (integer, min 1) — Approximate output ceiling in tokens (serialized bytes / 4); result arrays are trimmed from the tail to fit and the report states what was dropped.
+
+## Minimal call
+
+```json
+{
+  "name": "search_code",
+  "arguments": {
+    "query": "<value>",
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/select_tests.md

@@ -0,0 +1,34 @@
+# `select_tests`
+
+Select the test suites a change most plausibly needs to run.
+
+## When to use
+
+Rank the test suites most plausibly affected by a change; it selects tests but does not run them.
+
+## Inputs
+
+- `base` (string).
+- `base_ref` (string).
+- `depth` (integer, min 0).
+- `diff` (string).
+- `files` (array<string>).
+- `head_ref` (string).
+- `max_nodes` (integer, min 0).
+- `max_tests` (integer, min 0).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `precision` ("graph").
+
+## Minimal call
+
+```json
+{
+  "name": "select_tests",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/semantic_link.md

@@ -0,0 +1,31 @@
+# `semantic_link`
+
+Build inferred semantic graph evidence from supplied vectors.
+
+## When to use
+
+Build inferred semantic graph edges from vectors supplied by the caller; Weavatrix does not create embeddings.
+
+## Inputs
+
+- `vectors` (array<object>, required).
+- `min_similarity` (number, min 0, max 100) — 0..1 is a fraction; values above 1 through 100 are percentages.
+- `model` (string).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `selection` ("union" | "mutual" | "directed").
+- `top_k` (string).
+
+## Minimal call
+
+```json
+{
+  "name": "semantic_link",
+  "arguments": {
+    "vectors": [{}],
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/seo_link_suggestions.md

@@ -0,0 +1,34 @@
+# `seo_link_suggestions`
+
+Directional SEO internal-link evidence from supplied page profiles.
+
+## When to use
+
+Generate directional internal-link evidence from caller-supplied page profiles and vectors.
+
+## Inputs
+
+- `pages` (array<object>, required).
+- `vectors` (array<object>, required).
+- `allow_cross_language` (boolean).
+- `min_similarity` (number, min 0, max 100) — 0..1 is a fraction; values above 1 through 100 are percentages.
+- `model` (string).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `selection` ("union" | "mutual" | "directed").
+- `top_k` (string).
+
+## Minimal call
+
+```json
+{
+  "name": "seo_link_suggestions",
+  "arguments": {
+    "pages": [{}],
+    "vectors": [{}],
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/shortest_path.md

@@ -0,0 +1,30 @@
+# `shortest_path`
+
+Shortest typed dependency path between two nodes.
+
+## When to use
+
+Prove the shortest typed dependency path between two exact nodes.
+
+## Inputs
+
+- `source` (string, required).
+- `target` (string, required).
+- `max_hops` (integer, min 0).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+
+## Minimal call
+
+```json
+{
+  "name": "shortest_path",
+  "arguments": {
+    "source": "<source node>",
+    "target": "<target node>",
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/trace_api_contract.md

@@ -0,0 +1,54 @@
+# `trace_api_contract`
+
+Cross-repository HTTP, GraphQL, gRPC and event-transport contract evidence.
+
+## When to use
+
+Trace cross-repository HTTP, GraphQL, gRPC, or concrete event-transport contract evidence.
+
+Keep Kafka, AMQP/RabbitMQ, NATS, SNS/SQS, JMS, GraphQL, and gRPC identities distinct.
+
+## Inputs
+
+- `backend` (string, required).
+- `clients` (array<string>, required).
+- `auto_discover_wrappers` (boolean).
+- `changed_files` (array<string>).
+- `client_names` (array<string>).
+- `client_wrappers` (object).
+- `cursor` (string).
+- `include_classified` (boolean).
+- `include_tests` (boolean).
+- `max_affected_files` (integer, min 0).
+- `max_endpoints` (integer, min 0).
+- `max_impact_depth` (integer, min 0).
+- `max_matches` (integer, min 0).
+- `max_source_file_bytes` (integer, min 0).
+- `max_source_files` (integer, min 0).
+- `method` (string).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `page_size` (integer, min 0).
+- `path` (string).
+- `per_item_limit` (integer, min 0).
+- `response_detail` ("compact" | "full").
+- `runtime_config` (object).
+- `runtime_evidence_files` (object).
+- `runtime_evidence_max_age_hours` (integer, min 0).
+- `top_n` (integer, min 0).
+- `transport` ("all" | "http" | "graphql" | "grpc" | "event").
+
+## Minimal call
+
+```json
+{
+  "name": "trace_api_contract",
+  "arguments": {
+    "backend": "<value>",
+    "clients": ["<value>"],
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/trace_endpoint.md

@@ -0,0 +1,34 @@
+# `trace_endpoint`
+
+Resolve an endpoint and its bounded call neighborhood.
+
+## When to use
+
+Resolve one HTTP route and inspect its bounded handler and call neighborhood.
+
+## Inputs
+
+- `path` (string, required).
+- `context_lines` (integer, min 0).
+- `handler_file` (string).
+- `include_classified` (boolean).
+- `max_depth` (integer, min 0).
+- `max_excerpts` (integer, min 0).
+- `max_nodes` (integer, min 0).
+- `method` (string).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+
+## Minimal call
+
+```json
+{
+  "name": "trace_endpoint",
+  "arguments": {
+    "path": "<path>",
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/vector_search.md

@@ -0,0 +1,31 @@
+# `vector_search`
+
+Exact or bounded approximate nearest-neighbor search.
+
+## When to use
+
+Run exact or bounded approximate nearest-neighbor search over vectors supplied by the caller.
+
+## Inputs
+
+- `query` (array<number>, required).
+- `vectors` (array<object>, required).
+- `exact` (boolean).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `top_k` (string).
+
+## Minimal call
+
+```json
+{
+  "name": "vector_search",
+  "arguments": {
+    "query": ["<value>"],
+    "vectors": [{}],
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/verified_change.md

@@ -0,0 +1,45 @@
+# `verified_change`
+
+Composite pre-commit evidence and conservative verdict.
+
+## When to use
+
+Produce one conservative plan or verify envelope combining impact, architecture, duplicate, API, and optional test evidence.
+
+Use the same `task` and base revision in `phase:"plan"` and `phase:"verify"`.
+
+## Inputs
+
+- `task` (string, required).
+- `api_contract` (object).
+- `base_ref` (string).
+- `data_flow_depth` (integer, min 0).
+- `diff` (string).
+- `duplicate_ratchet` (boolean).
+- `files` (array<string>).
+- `head_ref` (string).
+- `impact_depth` (integer, min 0).
+- `max_data_flow_edges` (integer, min 0).
+- `max_impact_nodes` (integer, min 0).
+- `max_symbols` (integer, min 0).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `phase` ("plan" | "verify").
+- `precision` (string).
+- `run_tests` (boolean).
+- `test_timeout_ms` (integer, min 0).
+- `tests` (array<string>).
+
+## Minimal call
+
+```json
+{
+  "name": "verified_change",
+  "arguments": {
+    "task": "<task>",
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/verify_architecture.md

@@ -0,0 +1,25 @@
+# `verify_architecture`
+
+Verify graph dependencies against the active contract.
+
+## When to use
+
+Check current graph dependencies, cycles, and budgets against the active architecture contract.
+
+## Inputs
+
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+
+## Minimal call
+
+```json
+{
+  "name": "verify_architecture",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/verify_capabilities.md

@@ -0,0 +1,28 @@
+# `verify_capabilities`
+
+Resolve declared capabilities against exposed endpoint evidence.
+
+## When to use
+
+Resolve declared capabilities against statically exposed endpoint evidence.
+
+## Inputs
+
+- `include_classified` (boolean).
+- `include_tests` (boolean).
+- `max_results` (integer, min 0).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+
+## Minimal call
+
+```json
+{
+  "name": "verify_capabilities",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.