@jaguilar87/gaia 5.0.8 → 5.0.9

package/dist/gaia-ops/tools/migration/migrate_04_harness_events.py

@@ -1,132 +0,0 @@
-#!/usr/bin/env python3
-"""
-migrate_04_harness_events.py
-
-Convierte events.jsonl -> archivo SQL con INSERT batched.
-
-Reglas:
-  - Solo I/O sobre filesystem.
-  - NO importa sqlite3.
-  - `id` es AUTOINCREMENT en la tabla; NO lo insertamos.
-  - `payload` = json.dumps(record) entero -- preserva todos los campos.
-  - Idempotencia: harness_events NO tiene UNIQUE constraint útil.
-    Aplicar una sola vez. Re-ejecuciones requieren DELETE WHERE project=...
-
-CLI args (parametrización cross-workspace):
-  --project   workspace name (default: 'me')
-  --src       path al events.jsonl (default: ws/me)
-  --out       path al SQL de salida (default: /tmp/migrate_04_harness_events.sql)
-  --fragment  emite solo INSERTs (sin BEGIN/COMMIT)
-"""
-from __future__ import annotations
-
-import argparse
-import json
-import sys
-from pathlib import Path
-
-DEFAULT_PROJECT = "me"
-DEFAULT_SRC = Path("/home/jorge/ws/me/.claude/events/events.jsonl")
-DEFAULT_OUT = Path("/tmp/migrate_04_harness_events.sql")
-BATCH_SIZE = 200
-
-COLUMNS = ["project", "ts", "type", "source", "agent", "result", "severity", "payload"]
-
-
-def sql_quote(value) -> str:
-    if value is None:
-        return "NULL"
-    if isinstance(value, bool):
-        return "1" if value else "0"
-    if isinstance(value, (int, float)):
-        if isinstance(value, float) and (value != value or value in (float("inf"), float("-inf"))):
-            return "NULL"
-        return str(value)
-    s = str(value)
-    return "'" + s.replace("'", "''") + "'"
-
-
-def extract_row(record: dict, project: str) -> dict:
-    return {
-        "project": project,
-        "ts": record.get("ts"),
-        "type": record.get("type"),
-        "source": record.get("source"),
-        "agent": record.get("agent"),
-        "result": record.get("result"),
-        "severity": record.get("severity"),
-        "payload": json.dumps(record, ensure_ascii=False, separators=(",", ":")),
-    }
-
-
-def row_values_sql(row: dict) -> str:
-    return "(" + ",".join(sql_quote(row.get(col)) for col in COLUMNS) + ")"
-
-
-def main() -> int:
-    parser = argparse.ArgumentParser(description="Generate INSERT SQL for harness_events table.")
-    parser.add_argument("--project", default=DEFAULT_PROJECT)
-    parser.add_argument("--src", default=str(DEFAULT_SRC), help="path to events.jsonl")
-    parser.add_argument("--out", default=str(DEFAULT_OUT))
-    parser.add_argument("--fragment", action="store_true")
-    args = parser.parse_args()
-
-    project = args.project
-    src = Path(args.src)
-    out = Path(args.out)
-    fragment = args.fragment
-
-    if not src.exists():
-        print(f"[migrate_04:{project}] ERROR: source not found: {src}", file=sys.stderr)
-        return 1
-
-    rows = []
-    skipped = 0
-    total_lines = 0
-
-    with src.open("r", encoding="utf-8") as f:
-        for line in f:
-            total_lines += 1
-            s = line.strip()
-            if not s:
-                continue
-            try:
-                rec = json.loads(s)
-            except json.JSONDecodeError:
-                skipped += 1
-                continue
-            if not rec.get("ts") or not rec.get("type"):
-                skipped += 1
-                continue
-            rows.append(extract_row(rec, project))
-
-    cols_csv = ",".join(COLUMNS)
-    insert_prefix = f"INSERT INTO harness_events ({cols_csv}) VALUES\n"
-
-    with out.open("w", encoding="utf-8") as fh:
-        fh.write(f"-- Generated by migrate_04_harness_events.py\n")
-        fh.write(f"-- Project: {project}\n")
-        fh.write(f"-- Source: {src}\n")
-        fh.write(f"-- Total source lines: {total_lines}\n")
-        fh.write(f"-- Records to insert:  {len(rows)}\n")
-        fh.write(f"-- Skipped:            {skipped}\n")
-        fh.write("--\n")
-        fh.write("-- WARNING: harness_events sin PK natural; aplicar 2 veces duplica filas.\n")
-        if not fragment:
-            fh.write("BEGIN TRANSACTION;\n")
-
-        for i in range(0, len(rows), BATCH_SIZE):
-            batch = rows[i : i + BATCH_SIZE]
-            fh.write(insert_prefix)
-            fh.write(",\n".join(row_values_sql(r) for r in batch))
-            fh.write(";\n")
-
-        if not fragment:
-            fh.write("COMMIT;\n")
-
-    print(f"[migrate_04:{project}] wrote {out} ({len(rows)} rows, {skipped} skipped)")
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

package/dist/gaia-ops/tools/migration/migrate_04_harness_events.sh

@@ -1,23 +0,0 @@
-#!/usr/bin/env bash
-# migrate_04_harness_events.sh
-# Wrapper: regenera el .sql desde events.jsonl y lo carga en ~/.gaia/gaia.db.
-#
-# OJO: harness_events no tiene PK natural. Re-ejecutar este wrapper duplica
-# filas. Si necesitas re-ejecutar limpio, primero elimina las filas con:
-#   sqlite3 ~/.gaia/gaia.db "DELETE FROM harness_events WHERE project='me';"
-set -euo pipefail
-
-HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-PY_SCRIPT="${HERE}/migrate_04_harness_events.py"
-SQL_FILE="/tmp/migrate_04_harness_events.sql"
-DB_PATH="${HOME}/.gaia/gaia.db"
-
-# Paso 1: regenerar el .sql.
-echo "[migrate_04] regenerando ${SQL_FILE} ..."
-python3 "${PY_SCRIPT}"
-
-# Paso 2: aplicar el SQL (interceptado por el hook).
-echo "[migrate_04] aplicando ${SQL_FILE} en ${DB_PATH} ..."
-sqlite3 "${DB_PATH}" < "${SQL_FILE}"
-
-echo "[migrate_04] OK"

package/dist/gaia-ops/tools/scan/merge.py

@@ -1,213 +0,0 @@
-"""
-Section-Aware Context Combining Logic
-
-Merges scanner sections in-memory following the merge rules from
-contracts/merge-behavior.md. No file I/O -- gaia.db is the sole
-persistence layer.
-
-  Rule 1: Scanner-owned sections -> full replace
-  Rule 2: Agent-enriched sections -> never touch
-  Rule 3: Mixed sections -> selective update at sub-key level
-  Rule 4: Unknown/user-custom sections -> preserve
-  Rule 5: Metadata -> always update
-
-Note: Backward-compatible sections (project_details, application_architecture,
-development_standards) were removed in v3. Consumers read v2 scanner sections
-directly (project_identity, stack, git, environment, infrastructure).
-
-Special handling for sub-section level ownership: the `environment` section
-is jointly owned by the `tools` scanner (tools, tool_preferences) and the
-`environment` scanner (os, runtimes, env_files). Each scanner replaces only
-its owned sub-keys without clobbering the other scanner's sub-keys.
-
-Contract: specs/002-gaia-scan/contracts/merge-behavior.md
-"""
-
-import copy
-import logging
-from typing import Any, Dict, Optional, Set
-
-from tools.context.deep_merge import deep_merge
-
-logger = logging.getLogger(__name__)
-
-# Sections fully owned by scanners -- replaced entirely on each scan (Rule 1)
-# Top-level sections only; sub-key ownership handled separately
-SCANNER_OWNED_TOP_LEVEL: Dict[str, str] = {
-    "project_identity": "stack",
-    "stack": "stack",
-    "git": "git",
-    "infrastructure": "infrastructure",
-    "orchestration": "orchestration",
-    # "environment" is NOT listed here because it has sub-key ownership
-}
-
-# Sub-key ownership within the `environment` section (Rule 4 / sub-section)
-# Maps environment sub-key -> owning scanner name
-ENVIRONMENT_SUBKEY_OWNERS: Dict[str, str] = {
-    "tools": "tools",
-    "tool_preferences": "tools",
-    "os": "environment",
-    "runtimes": "environment",
-    "env_files": "environment",
-}
-
-# Agent-enriched sections -- never modified by scanners (Rule 2)
-AGENT_ENRICHED_SECTIONS: frozenset = frozenset([
-    "operational_guidelines",
-    "cluster_details",
-    "infrastructure_topology",
-    "monitoring_observability",
-    "architecture_overview",
-    "gcp_services",
-    "workload_identity",
-])
-
-# Mixed sections with partial scanner ownership (Rule 3)
-# Maps section_name -> set of scanner-owned field names
-MIXED_SECTION_SCANNER_FIELDS: Dict[str, Set[str]] = {
-    "terraform_infrastructure": {"layout"},
-    "gitops_configuration": {"repository"},
-    "application_services": {"base_path", "services"},
-}
-
-
-def merge_context(
-    existing: Dict[str, Any],
-    scan_sections: Dict[str, Any],
-    section_owners: Dict[str, str],
-) -> Dict[str, Any]:
-    """Merge scanner results with existing project-context sections.
-
-    Applies the merge rules from contracts/merge-behavior.md to produce
-    the final merged sections dict.
-
-    Args:
-        existing: Current sections from project-context.json (may be empty).
-        scan_sections: Combined sections from all scanners.
-        section_owners: Mapping of section/sub-section name to scanner name,
-                        from ScannerRegistry.get_section_owners().
-
-    Returns:
-        Merged sections dict ready to be written to project-context.json.
-        The merge is deterministic: same inputs always produce the same output.
-    """
-    result = copy.deepcopy(existing)
-
-    # --- Rule 1: Scanner-owned top-level sections -> full replace ---
-    for section_name in SCANNER_OWNED_TOP_LEVEL:
-        if section_name in scan_sections:
-            result[section_name] = copy.deepcopy(scan_sections[section_name])
-
-    # --- Sub-section level ownership for `environment` ---
-    # Both the `tools` scanner and `environment` scanner contribute sub-keys
-    # to the `environment` section. Each scanner's sub-keys replace their owned
-    # portion without clobbering the other scanner's sub-keys.
-    _merge_environment_section(result, scan_sections)
-
-    # --- Rule 2: Agent-enriched sections -> never touch ---
-    # These are already in `result` from the deepcopy of `existing`.
-    # We explicitly do NOT overwrite them, even if a scanner accidentally
-    # produced data for one of these section names.
-    # (No action needed -- they are preserved by the deepcopy.)
-
-    # --- Rule 3: Mixed sections -> selective update ---
-    for section_name, scanner_fields in MIXED_SECTION_SCANNER_FIELDS.items():
-        if section_name in scan_sections:
-            scan_data = scan_sections[section_name]
-            if section_name not in result:
-                result[section_name] = {}
-            # Only update scanner-owned fields; preserve agent fields
-            for field_name in scanner_fields:
-                if field_name in scan_data:
-                    result[section_name][field_name] = copy.deepcopy(
-                        scan_data[field_name]
-                    )
-
-    # --- Rule 5: Unknown/user-custom sections -> preserve ---
-    # Any section in `existing` that is not scanner-owned, not agent-enriched,
-    # not backward-compat, and not mixed is a user-custom section.
-    # These are already preserved by the initial deepcopy of `existing`.
-    # We do NOT add new unknown sections from scan_sections.
-
-    return result
-
-
-def _merge_environment_section(
-    result: Dict[str, Any],
-    scan_sections: Dict[str, Any],
-) -> None:
-    """Merge the `environment` section with sub-key level ownership.
-
-    Two scanners contribute to the `environment` section:
-    - `tools` scanner owns: tools, tool_preferences
-    - `environment` scanner owns: os, runtimes, env_files
-
-    Each scanner's sub-keys replace their owned portion; the other scanner's
-    sub-keys are preserved. The `_source` field gets a combined tag.
-
-    Args:
-        result: The result dict being built (mutated in place).
-        scan_sections: Combined sections from all scanners.
-    """
-    if "environment" not in scan_sections:
-        return
-
-    scan_env = scan_sections["environment"]
-
-    if "environment" not in result:
-        result["environment"] = {}
-
-    env = result["environment"]
-
-    # Replace each sub-key based on ownership
-    for subkey in ENVIRONMENT_SUBKEY_OWNERS:
-        if subkey in scan_env:
-            env[subkey] = copy.deepcopy(scan_env[subkey])
-
-    # Set combined _source tag
-    env["_source"] = "scanner:environment+tools"
-
-
-def collect_scanner_sections(
-    scanner_results: Dict[str, Any],
-) -> Dict[str, Any]:
-    """Collect and combine sections from all scanner results.
-
-    Handles the environment section specially: both `tools` and `environment`
-    scanners produce sub-keys under `environment`, so their outputs are
-    combined into a single `environment` section.
-
-    Args:
-        scanner_results: Mapping of scanner_name -> ScanResult (must have
-                         a `sections` attribute that is a dict).
-
-    Returns:
-        Combined sections dict from all scanners.
-    """
-    combined: Dict[str, Any] = {}
-    environment_parts: Dict[str, Any] = {}
-
-    for _scanner_name, scan_result in scanner_results.items():
-        sections = scan_result.sections if hasattr(scan_result, "sections") else {}
-
-        for section_name, section_data in sections.items():
-            if section_name == "environment":
-                # Merge environment sub-keys from both scanners
-                if isinstance(section_data, dict):
-                    for key, value in section_data.items():
-                        if key != "_source":
-                            environment_parts[key] = value
-            else:
-                # Non-environment sections: direct assignment (last scanner wins,
-                # but each section should have exactly one owner)
-                combined[section_name] = section_data
-
-    # Reassemble environment section if we got any parts
-    if environment_parts:
-        combined["environment"] = {
-            "_source": "scanner:environment+tools",
-            **environment_parts,
-        }
-
-    return combined

package/dist/gaia-ops/tools/scan/tests/test_merge.py

@@ -1,269 +0,0 @@
-"""
-Unit tests for context combining logic (T026).
-
-Tests scanner-owned section replacement, agent-enriched section preservation,
-mixed section sub-key merge, unknown section preservation, v1-to-v2 upgrade,
-and idempotency.
-"""
-
-import copy
-import json
-from pathlib import Path
-from typing import Any, Dict
-
-import pytest
-
-from tools.scan.merge import merge_context
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-
-def _section_owners() -> Dict[str, str]:
-    """Return a realistic section_owners map from ScannerRegistry."""
-    return {
-        "project_identity": "stack",
-        "stack": "stack",
-        "git": "git",
-        "infrastructure": "infrastructure",
-        "orchestration": "orchestration",
-        "environment.tools": "tools",
-        "environment.tool_preferences": "tools",
-        "environment.runtimes": "environment",
-        "environment.os": "environment",
-        "environment.env_files": "environment",
-    }
-
-
-# ---------------------------------------------------------------------------
-# Test data helpers
-# ---------------------------------------------------------------------------
-
-
-def _make_existing_context() -> Dict[str, Any]:
-    """Create a realistic existing project-context with scanner + agent data."""
-    return {
-        "metadata": {
-            "version": "2.0",
-            "last_updated": "2026-01-01T00:00:00Z",
-            "project_name": "test-project",
-            "scan_config": {
-                "staleness_hours": 24,
-                "last_scan": "2026-01-01T00:00:00Z",
-                "scanner_version": "0.1.0",
-            },
-        },
-        "project_identity": {
-            "_source": "scanner:stack",
-            "name": "old-name",
-            "type": "application",
-        },
-        "stack": {
-            "_source": "scanner:stack",
-            "languages": [{"name": "python", "manifest": "pyproject.toml", "primary": True}],
-            "frameworks": [],
-            "build_tools": [],
-        },
-        "git": {
-            "_source": "scanner:git",
-            "platform": "github",
-            "remotes": [],
-            "default_branch": "main",
-        },
-        "environment": {
-            "_source": "scanner:environment",
-            "os": {"platform": "linux", "architecture": "x64"},
-            "runtimes": [{"name": "python3", "version": "3.11.0"}],
-            "env_files": [],
-            "tools": [{"name": "git", "path": "/usr/bin/git"}],
-            "tool_preferences": {"file_viewer": "bat"},
-        },
-        "operational_guidelines": {
-            "_source": "agent:developer",
-            "deployment_strategy": "blue-green",
-            "rollback_procedure": "manual",
-        },
-        "my_custom_notes": {
-            "author": "user",
-            "notes": "User-maintained section",
-        },
-    }
-
-
-def _make_scan_results() -> Dict[str, Any]:
-    """Create scan results from a new scan run."""
-    return {
-        "project_identity": {
-            "_source": "scanner:stack",
-            "name": "new-name",
-            "type": "monorepo",
-            "description": "Updated description",
-        },
-        "stack": {
-            "_source": "scanner:stack",
-            "languages": [
-                {"name": "typescript", "manifest": "package.json", "primary": True},
-                {"name": "python", "manifest": "pyproject.toml", "primary": False},
-            ],
-            "frameworks": [{"name": "react", "language": "typescript"}],
-            "build_tools": [{"name": "npm", "detected_by": "lock_file"}],
-        },
-        "git": {
-            "_source": "scanner:git",
-            "platform": "github",
-            "remotes": [{"name": "origin", "url": "git@github.com:o/r.git"}],
-            "default_branch": "main",
-        },
-        "environment": {
-            "_source": "scanner:environment",
-            "os": {"platform": "linux", "architecture": "x64", "wsl": True},
-            "runtimes": [{"name": "python3", "version": "3.12.0"}],
-            "env_files": [{"name": ".env", "path": ".env"}],
-        },
-    }
-
-
-# ---------------------------------------------------------------------------
-# Rule 1: Scanner-owned section fully replaced
-# ---------------------------------------------------------------------------
-
-
-class TestScannerOwnedSectionReplacement:
-    """Test that scanner-owned sections are fully replaced with new data."""
-
-    def test_project_identity_replaced(self) -> None:
-        existing = _make_existing_context()
-        scan = _make_scan_results()
-        result = merge_context(existing, scan, _section_owners())
-        assert result["project_identity"]["name"] == "new-name"
-        assert result["project_identity"]["type"] == "monorepo"
-
-    def test_stack_section_replaced(self) -> None:
-        existing = _make_existing_context()
-        scan = _make_scan_results()
-        result = merge_context(existing, scan, _section_owners())
-        lang_names = [l["name"] for l in result["stack"]["languages"]]
-        assert "typescript" in lang_names
-        assert len(result["stack"]["frameworks"]) == 1
-
-    def test_git_section_replaced(self) -> None:
-        existing = _make_existing_context()
-        scan = _make_scan_results()
-        result = merge_context(existing, scan, _section_owners())
-        assert len(result["git"]["remotes"]) == 1
-
-
-# ---------------------------------------------------------------------------
-# Rule 2: Agent-enriched sections preserved
-# ---------------------------------------------------------------------------
-
-
-class TestAgentEnrichedPreservation:
-    """Test that agent-enriched sections are preserved byte-identical."""
-
-    def test_operational_guidelines_preserved(self) -> None:
-        existing = _make_existing_context()
-        scan = _make_scan_results()
-        result = merge_context(existing, scan, _section_owners())
-        assert result["operational_guidelines"]["deployment_strategy"] == "blue-green"
-        assert result["operational_guidelines"]["rollback_procedure"] == "manual"
-
-
-# ---------------------------------------------------------------------------
-# Rule 4: Mixed section (environment) sub-key merge
-# ---------------------------------------------------------------------------
-
-
-class TestMixedSectionMerge:
-    """Test that mixed sections merge scanner fields and keep agent fields."""
-
-    def test_environment_scanner_fields_refreshed(self) -> None:
-        existing = _make_existing_context()
-        scan = _make_scan_results()
-        result = merge_context(existing, scan, _section_owners())
-        # Scanner-owned sub-keys should be updated
-        assert result["environment"]["os"].get("wsl") is True
-        runtimes = result["environment"]["runtimes"]
-        py = [r for r in runtimes if r["name"] == "python3"][0]
-        assert py["version"] == "3.12.0"
-
-    def test_environment_agent_fields_kept(self) -> None:
-        existing = _make_existing_context()
-        scan = _make_scan_results()
-        result = merge_context(existing, scan, _section_owners())
-        # tools and tool_preferences came from tool scanner (not in this scan)
-        # They should be preserved from existing
-        assert "tools" in result["environment"] or "tool_preferences" in result["environment"]
-
-
-# ---------------------------------------------------------------------------
-# Rule 5: Unknown/user-custom sections preserved
-# ---------------------------------------------------------------------------
-
-
-class TestUserCustomPreservation:
-    """Test that user-custom sections survive combining."""
-
-    def test_custom_section_preserved(self) -> None:
-        existing = _make_existing_context()
-        scan = _make_scan_results()
-        result = merge_context(existing, scan, _section_owners())
-        assert "my_custom_notes" in result
-        assert result["my_custom_notes"]["author"] == "user"
-
-
-# ---------------------------------------------------------------------------
-# v1-to-v2 upgrade
-# ---------------------------------------------------------------------------
-
-
-class TestV1ToV2Upgrade:
-    """Test upgrading from v1 project-context (no scan_config)."""
-
-    def test_v1_context_upgraded(self, sample_project_context_v1: Dict[str, Any]) -> None:
-        scan = _make_scan_results()
-        result = merge_context(sample_project_context_v1, scan, _section_owners())
-        # Should have scan_config after upgrade
-        assert "metadata" in result
-        # Agent-enriched data from v1 should be preserved
-        if "operational_guidelines" in sample_project_context_v1:
-            assert "operational_guidelines" in result
-
-    def test_v1_agent_data_not_lost(self, sample_project_context_v1: Dict[str, Any]) -> None:
-        scan = _make_scan_results()
-        result = merge_context(sample_project_context_v1, scan, _section_owners())
-        # User-custom sections from v1 are preserved as-is (Rule 4).
-        # project_details is no longer produced by the scanner (no backward compat),
-        # but if it existed in the v1 context it is preserved as a user-custom section.
-        if "project_details" in sample_project_context_v1:
-            assert "project_details" in result
-
-
-# ---------------------------------------------------------------------------
-# Idempotency
-# ---------------------------------------------------------------------------
-
-
-class TestIdempotency:
-    """Test that running combine twice produces same result (except timestamps)."""
-
-    def test_idempotent_combine(self) -> None:
-        existing = _make_existing_context()
-        scan = _make_scan_results()
-
-        result1 = merge_context(existing, scan, _section_owners())
-        result2 = merge_context(result1, scan, _section_owners())
-
-        # Strip timestamps for comparison
-        def strip_timestamps(d: Dict) -> Dict:
-            d = copy.deepcopy(d)
-            if "metadata" in d:
-                meta = d["metadata"]
-                meta.pop("last_updated", None)
-                if "scan_config" in meta:
-                    meta["scan_config"].pop("last_scan", None)
-            return d
-
-        assert strip_timestamps(result1) == strip_timestamps(result2)