@tea-agent/loop-agent 0.13.0-beta.0 → 0.13.0

package/docs/templates/backend-test-analysis.schema.json

@@ -1,44 +1,44 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "https://tea-agent.dev/schemas/backend-test-analysis-v1.json",
-  "title": "Backend Test Analysis v1",
-  "type": "object",
-  "additionalProperties": false,
-  "required": ["schemaVersion", "sourceBinding", "acceptanceCriteria", "endpoints", "dataModels", "businessRules", "stateTransitions", "boundaryConstraints", "externalDependencies", "risks", "evidenceGaps"],
-  "properties": {
-    "schemaVersion": { "const": 1 },
-    "sourceBinding": {
-      "type": "object", "additionalProperties": false,
-      "required": ["taskId", "requirementPath", "requirementSha256", "referencePaths", "requirementIds"],
-      "properties": {
-        "taskId": { "type": "string", "minLength": 1 },
-        "requirementPath": { "type": "string", "minLength": 1 },
-        "requirementSha256": { "type": "string", "pattern": "^[a-f0-9]{64}$" },
-        "referencePaths": { "type": "array", "items": { "type": "string", "minLength": 1 } },
-        "requirementIds": { "type": "array", "items": { "type": "string", "pattern": "^(REQ|BR|AC)-[A-Z0-9]+(-[A-Z0-9]+)*$" } }
-      }
-    },
-    "acceptanceCriteria": { "type": "array", "items": { "$ref": "#/$defs/acceptanceCriterion" } },
-    "endpoints": { "type": "array", "items": { "$ref": "#/$defs/endpoint" } },
-    "dataModels": { "type": "array", "items": { "$ref": "#/$defs/evidencedDescription" } },
-    "businessRules": { "type": "array", "items": { "$ref": "#/$defs/businessRule" } },
-    "stateTransitions": { "type": "array", "items": { "$ref": "#/$defs/stateTransition" } },
-    "boundaryConstraints": { "type": "array", "items": { "$ref": "#/$defs/boundaryConstraint" } },
-    "externalDependencies": { "type": "array", "items": { "$ref": "#/$defs/optionalEvidenceDescription" } },
-    "risks": { "type": "array", "items": { "$ref": "#/$defs/optionalEvidenceDescription" } },
-    "evidenceGaps": { "type": "array", "items": { "$ref": "#/$defs/evidenceGap" } }
-  },
-  "$defs": {
-    "sourceRef": { "type": "string", "minLength": 1 },
-    "field": { "type": "object", "additionalProperties": false, "required": ["name"], "properties": { "name": { "type": "string", "minLength": 1 }, "type": { "type": "string", "minLength": 1 }, "required": { "type": "boolean" }, "description": { "type": "string" } } },
-    "errorCase": { "type": "object", "additionalProperties": false, "required": ["description"], "properties": { "status": { "type": "integer", "minimum": 400, "maximum": 599 }, "code": { "type": "string", "minLength": 1 }, "messageField": { "type": "string", "minLength": 1 }, "description": { "type": "string", "minLength": 1 } } },
-    "acceptanceCriterion": { "type": "object", "additionalProperties": false, "required": ["id", "text", "sourceRef"], "properties": { "id": { "type": "string", "pattern": "^AC-[A-Z0-9]+(-[A-Z0-9]+)*$" }, "text": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
-    "endpoint": { "type": "object", "additionalProperties": false, "required": ["id", "method", "path", "requestFields", "responseFields", "successStatuses", "errorCases"], "properties": { "id": { "type": "string", "minLength": 1 }, "method": { "enum": ["GET", "POST", "PUT", "PATCH", "DELETE", "HEAD", "OPTIONS"] }, "path": { "type": "string", "pattern": "^/" }, "requestFields": { "type": "array", "items": { "$ref": "#/$defs/field" } }, "responseFields": { "type": "array", "items": { "$ref": "#/$defs/field" } }, "successStatuses": { "type": "array", "items": { "type": "integer", "minimum": 100, "maximum": 399 } }, "errorCases": { "type": "array", "items": { "$ref": "#/$defs/errorCase" } } } },
-    "evidencedDescription": { "type": "object", "additionalProperties": false, "required": ["id", "description", "sourceRef"], "properties": { "id": { "type": "string", "minLength": 1 }, "description": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
-    "businessRule": { "type": "object", "additionalProperties": false, "required": ["id", "text", "sourceRef"], "properties": { "id": { "type": "string", "minLength": 1 }, "text": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
-    "stateTransition": { "type": "object", "additionalProperties": false, "required": ["from", "to", "trigger", "sourceRef"], "properties": { "from": { "type": "string", "minLength": 1 }, "to": { "type": "string", "minLength": 1 }, "trigger": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
-    "boundaryConstraint": { "type": "object", "additionalProperties": false, "required": ["field", "constraint", "sourceRef"], "properties": { "field": { "type": "string", "minLength": 1 }, "constraint": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
-    "optionalEvidenceDescription": { "type": "object", "additionalProperties": false, "required": ["description"], "properties": { "name": { "type": "string", "minLength": 1 }, "description": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
-    "evidenceGap": { "type": "object", "additionalProperties": false, "required": ["description"], "properties": { "description": { "type": "string", "minLength": 1 }, "requirementId": { "type": "string" }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } }
-  }
-}
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://tea-agent.dev/schemas/backend-test-analysis-v1.json",
+  "title": "Backend Test Analysis v1",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["schemaVersion", "sourceBinding", "acceptanceCriteria", "endpoints", "dataModels", "businessRules", "stateTransitions", "boundaryConstraints", "externalDependencies", "risks", "evidenceGaps"],
+  "properties": {
+    "schemaVersion": { "const": 1 },
+    "sourceBinding": {
+      "type": "object", "additionalProperties": false,
+      "required": ["taskId", "requirementPath", "requirementSha256", "referencePaths", "requirementIds"],
+      "properties": {
+        "taskId": { "type": "string", "minLength": 1 },
+        "requirementPath": { "type": "string", "minLength": 1 },
+        "requirementSha256": { "type": "string", "pattern": "^[a-f0-9]{64}$" },
+        "referencePaths": { "type": "array", "items": { "type": "string", "minLength": 1 } },
+        "requirementIds": { "type": "array", "items": { "type": "string", "pattern": "^(REQ|BR|AC)-[A-Z0-9]+(-[A-Z0-9]+)*$" } }
+      }
+    },
+    "acceptanceCriteria": { "type": "array", "items": { "$ref": "#/$defs/acceptanceCriterion" } },
+    "endpoints": { "type": "array", "items": { "$ref": "#/$defs/endpoint" } },
+    "dataModels": { "type": "array", "items": { "$ref": "#/$defs/evidencedDescription" } },
+    "businessRules": { "type": "array", "items": { "$ref": "#/$defs/businessRule" } },
+    "stateTransitions": { "type": "array", "items": { "$ref": "#/$defs/stateTransition" } },
+    "boundaryConstraints": { "type": "array", "items": { "$ref": "#/$defs/boundaryConstraint" } },
+    "externalDependencies": { "type": "array", "items": { "$ref": "#/$defs/optionalEvidenceDescription" } },
+    "risks": { "type": "array", "items": { "$ref": "#/$defs/optionalEvidenceDescription" } },
+    "evidenceGaps": { "type": "array", "items": { "$ref": "#/$defs/evidenceGap" } }
+  },
+  "$defs": {
+    "sourceRef": { "type": "string", "minLength": 1 },
+    "field": { "type": "object", "additionalProperties": false, "required": ["name"], "properties": { "name": { "type": "string", "minLength": 1 }, "type": { "type": "string", "minLength": 1 }, "required": { "type": "boolean" }, "description": { "type": "string" } } },
+    "errorCase": { "type": "object", "additionalProperties": false, "required": ["description"], "properties": { "status": { "type": "integer", "minimum": 400, "maximum": 599 }, "code": { "type": "string", "minLength": 1 }, "messageField": { "type": "string", "minLength": 1 }, "description": { "type": "string", "minLength": 1 } } },
+    "acceptanceCriterion": { "type": "object", "additionalProperties": false, "required": ["id", "text", "sourceRef"], "properties": { "id": { "type": "string", "pattern": "^AC-[A-Z0-9]+(-[A-Z0-9]+)*$" }, "text": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
+    "endpoint": { "type": "object", "additionalProperties": false, "required": ["id", "method", "path", "requestFields", "responseFields", "successStatuses", "errorCases"], "properties": { "id": { "type": "string", "minLength": 1 }, "method": { "enum": ["GET", "POST", "PUT", "PATCH", "DELETE", "HEAD", "OPTIONS"] }, "path": { "type": "string", "pattern": "^/" }, "requestFields": { "type": "array", "items": { "$ref": "#/$defs/field" } }, "responseFields": { "type": "array", "items": { "$ref": "#/$defs/field" } }, "successStatuses": { "type": "array", "items": { "type": "integer", "minimum": 100, "maximum": 399 } }, "errorCases": { "type": "array", "items": { "$ref": "#/$defs/errorCase" } } } },
+    "evidencedDescription": { "type": "object", "additionalProperties": false, "required": ["id", "description", "sourceRef"], "properties": { "id": { "type": "string", "minLength": 1 }, "description": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
+    "businessRule": { "type": "object", "additionalProperties": false, "required": ["id", "text", "sourceRef"], "properties": { "id": { "type": "string", "minLength": 1 }, "text": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
+    "stateTransition": { "type": "object", "additionalProperties": false, "required": ["from", "to", "trigger", "sourceRef"], "properties": { "from": { "type": "string", "minLength": 1 }, "to": { "type": "string", "minLength": 1 }, "trigger": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
+    "boundaryConstraint": { "type": "object", "additionalProperties": false, "required": ["field", "constraint", "sourceRef"], "properties": { "field": { "type": "string", "minLength": 1 }, "constraint": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
+    "optionalEvidenceDescription": { "type": "object", "additionalProperties": false, "required": ["description"], "properties": { "name": { "type": "string", "minLength": 1 }, "description": { "type": "string", "minLength": 1 }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } },
+    "evidenceGap": { "type": "object", "additionalProperties": false, "required": ["description"], "properties": { "description": { "type": "string", "minLength": 1 }, "requirementId": { "type": "string" }, "sourceRef": { "$ref": "#/$defs/sourceRef" } } }
+  }
+}

package/docs/templates/backend-test-case-manifest.schema.json

@@ -0,0 +1,190 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://tea-agent.dev/schemas/backend-test-case-manifest-v1.json",
+  "title": "Backend Test Case Manifest v1",
+  "description": "Run-owned AC → BE-* case → automation mapping. Coverage ratios are deterministic gate outputs; models must not invent percentages. Conditional required fields mirror Zod: generated requires file+symbol; skipped|unsupported requires gapReason; each evidence gap requires acId and/or caseId.",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["schemaVersion", "sourceBinding", "cases", "evidenceGaps"],
+  "properties": {
+    "schemaVersion": { "const": 1 },
+    "sourceBinding": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": [
+        "taskId",
+        "requirementPath",
+        "requirementSha256",
+        "referencePaths",
+        "requirementIds"
+      ],
+      "properties": {
+        "taskId": { "type": "string", "minLength": 1 },
+        "requirementPath": { "type": "string", "minLength": 1 },
+        "requirementSha256": {
+          "type": "string",
+          "pattern": "^[a-f0-9]{64}$"
+        },
+        "referencePaths": {
+          "type": "array",
+          "items": { "type": "string", "minLength": 1 }
+        },
+        "requirementIds": {
+          "type": "array",
+          "items": {
+            "type": "string",
+            "pattern": "^(?:REQ|BR|AC)-[A-Z0-9]+(?:-[A-Z0-9]+)*$"
+          }
+        }
+      }
+    },
+    "cases": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": [
+          "caseId",
+          "acIds",
+          "title",
+          "category",
+          "automationStatus"
+        ],
+        "properties": {
+          "caseId": {
+            "type": "string",
+            "pattern": "^BE-[A-Z0-9]+(?:-[A-Z0-9]+)*-\\d{3}$"
+          },
+          "acIds": {
+            "type": "array",
+            "minItems": 1,
+            "items": {
+              "type": "string",
+              "pattern": "^AC-[A-Z0-9]+(?:-[A-Z0-9]+)*$"
+            }
+          },
+          "title": { "type": "string", "minLength": 1 },
+          "category": {
+            "type": "string",
+            "enum": [
+              "positive",
+              "negative",
+              "boundary",
+              "state-transition",
+              "auth",
+              "timeout",
+              "concurrency",
+              "other"
+            ]
+          },
+          "automationStatus": {
+            "type": "string",
+            "enum": ["planned", "generated", "skipped", "unsupported"]
+          },
+          "endpointRef": { "type": "string", "minLength": 1 },
+          "ruleRefs": {
+            "type": "array",
+            "items": { "type": "string", "minLength": 1 }
+          },
+          "file": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Repo-relative posix path required when automationStatus=generated"
+          },
+          "symbol": {
+            "type": "string",
+            "minLength": 1,
+            "description": "pytest function name required when automationStatus=generated; must bind to caseId"
+          },
+          "gapReason": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Required when automationStatus is skipped or unsupported"
+          },
+          "evidenceRef": { "type": "string", "minLength": 1 }
+        },
+        "allOf": [
+          {
+            "if": {
+              "properties": {
+                "automationStatus": { "const": "generated" }
+              },
+              "required": ["automationStatus"]
+            },
+            "then": {
+              "required": ["file", "symbol"]
+            }
+          },
+          {
+            "if": {
+              "properties": {
+                "automationStatus": {
+                  "enum": ["skipped", "unsupported"]
+                }
+              },
+              "required": ["automationStatus"]
+            },
+            "then": {
+              "required": ["gapReason"]
+            }
+          }
+        ]
+      }
+    },
+    "evidenceGaps": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["description"],
+        "properties": {
+          "acId": {
+            "type": "string",
+            "pattern": "^AC-[A-Z0-9]+(?:-[A-Z0-9]+)*$"
+          },
+          "caseId": {
+            "type": "string",
+            "pattern": "^BE-[A-Z0-9]+(?:-[A-Z0-9]+)*-\\d{3}$"
+          },
+          "description": { "type": "string", "minLength": 1 },
+          "evidenceRef": { "type": "string", "minLength": 1 }
+        },
+        "anyOf": [
+          { "required": ["acId"] },
+          { "required": ["caseId"] }
+        ]
+      }
+    },
+    "coverageSummary": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": [
+        "explicitAcCount",
+        "coveredAcCount",
+        "gappedAcCount",
+        "caseCount",
+        "generatedCount",
+        "plannedCount",
+        "skippedCount",
+        "unsupportedCount",
+        "acCoverageRatio"
+      ],
+      "properties": {
+        "explicitAcCount": { "type": "integer", "minimum": 0 },
+        "coveredAcCount": { "type": "integer", "minimum": 0 },
+        "gappedAcCount": { "type": "integer", "minimum": 0 },
+        "caseCount": { "type": "integer", "minimum": 0 },
+        "generatedCount": { "type": "integer", "minimum": 0 },
+        "plannedCount": { "type": "integer", "minimum": 0 },
+        "skippedCount": { "type": "integer", "minimum": 0 },
+        "unsupportedCount": { "type": "integer", "minimum": 0 },
+        "acCoverageRatio": {
+          "type": "number",
+          "minimum": 0,
+          "maximum": 1,
+          "description": "Deterministic coveredAcCount/explicitAcCount (or 1 when no explicit AC)"
+        }
+      }
+    }
+  }
+}

package/docs/templates/backend-test-dag.classify.prompt.md

@@ -0,0 +1,75 @@
+# Backend Test DAG Classify Prompt Template
+
+## Purpose
+
+Use this prompt for a **read-only classification** node: `executor: "pi"`, `role: "reviewer"`, `writePolicy: "read-only"`. The agent reads the run-owned Backend Test Result v1 artifact and returns structured failure classification JSON.
+
+Do **not** create a new executor type. Do **not** write repository files.
+
+## Recommended DAG Node Shape
+
+```json
+{
+  "id": "classify-backend-test-result-pi",
+  "depends_on": ["parse-backend-test-result-shell"],
+  "complexity": "MED",
+  "executor": "pi",
+  "role": "reviewer",
+  "writePolicy": "read-only",
+  "allowedPaths": ["**"],
+  "forbiddenPaths": [".harness/**", "artifacts/**"],
+  "outputContract": "Pure JSON classification: category in {ProductBug,TestBug,EnvFailure,ContractMismatch,FlakyTest,Unknown}, evidence[], confidence (capped), notes. No file writes.",
+  "subtask_prompt_markdown": "./backend-test-dag.classify.prompt.md"
+}
+```
+
+## Prompt Body
+
+You are the Backend Test DAG **result classifier** agent.
+
+Your job is to classify the structured Backend Test Result v1 produced by `parse-backend-test-result-shell`. Return **exactly one JSON object**. Prefer pure JSON; a single fenced `json` block is tolerated; no trailing prose. Read-only: do not modify code, docs, artifacts, or repository files.
+
+### Inputs (authoritative)
+
+1. **Result v1** — `$HARNESS_DAG_RUN_DIR/contracts/backend-test-result.json` (schemaId `backend-test-result-v1`).
+2. Optional: execute-node stdout markers (`pytestExitCode=…`, `JUnit report: …`) as secondary evidence only.
+
+Do **not** invent pass rates or failure lists from raw logs when Result v1 is present. Counts and `failures[]` come from the result artifact only.
+
+### Output JSON shape
+
+```json
+{
+  "schemaVersion": 1,
+  "category": "ProductBug",
+  "confidence": 0.0,
+  "evidence": ["result.outcome=completed-with-failures", "failures[0].name=…"],
+  "notes": "short rationale",
+  "forbiddenCategoriesHonored": ["FlakyTest"]
+}
+```
+
+### Categories
+
+| Category | When |
+|----------|------|
+| **ProductBug** | Assertion failures that indicate implementation/API behavior mismatch (only when collection/command/report are healthy). |
+| **TestBug** | Broken test code, wrong expectations, bad fixtures, or collection/import errors clearly in tests. |
+| **EnvFailure** | Missing env, service down, tooling/runtime failure, command-error. |
+| **ContractMismatch** | Execution/analysis contract assumptions violated (wrong testRoot/mode, missing readiness). |
+| **FlakyTest** | **Only** with multi-run historical evidence of intermittent pass/fail. |
+| **Unknown** | Insufficient evidence. |
+
+### Hard constraints (MUST)
+
+1. **Single-run failure MUST NOT use `FlakyTest`.** Prefer `Unknown`, `TestBug`, or `ProductBug`.
+2. If `executionStatus` or `outcome` is `collection-error`, `command-error`, or `report-error`, **MUST NOT** use `ProductBug`. Prefer `EnvFailure`, `TestBug`, or `Unknown`.
+3. If `outcome=passed` with `failed=0` and `error=0`, set `category` to `Unknown` (or omit product diagnosis) and note all-pass; do not invent bugs.
+4. `confidence` caps: ≤ `0.75` for assertion failures; ≤ `0.6` for env/collection/command/report errors; `1.0` only for all-pass with no issues.
+5. `evidence[]` must cite concrete result fields (`outcome`, `executionStatus`, `failed`, `failures[].name`, `pytestExitCode`).
+
+### Non-goals
+
+- Do not rewrite Result v1.
+- Do not decide final DAG success/failure (that is `backend-test-outcome-gate-shell`).
+- Do not implement M3 case manifest / Task Pool auto follow-up.