π The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
fix(ruflo-migrations): v0.2.0 β namespace-routing fix + adopt plugin contract (ADR-0001)
Reuven894a199ccbd9
diff --git a/plugins/ruflo-migrations/.claude-plugin/plugin.json b/plugins/ruflo-migrations/.claude-plugin/plugin.jsonindex 682e920d62..c6d4bdfe08 100644--- a/plugins/ruflo-migrations/.claude-plugin/plugin.json+++ b/plugins/ruflo-migrations/.claude-plugin/plugin.json@@ -1,7 +1,7 @@{"name": "ruflo-migrations","description": "Schema migration management β generate, validate, dry-run, and rollback database migrations",- "version": "0.1.0",+ "version": "0.2.0","author": {"name": "ruvnet","url": "https://github.com/ruvnet"@@ -13,6 +13,9 @@"migrations","database","schema",- "rollback"+ "rollback",+ "mcp",+ "dry-run",+ "up-down-pairs"]}diff --git a/plugins/ruflo-migrations/README.md b/plugins/ruflo-migrations/README.mdindex f0b8150deb..0e92f95244 100644--- a/plugins/ruflo-migrations/README.md+++ b/plugins/ruflo-migrations/README.md@@ -59,8 +59,33 @@ migrations/002_add_email_index.down.sql```+## Compatibility++- **CLI:** pinned to `@claude-flow/cli` v3.6 major+minor.+- **Verification:** `bash plugins/ruflo-migrations/scripts/smoke.sh` is the contract.++## Namespace coordination++This plugin owns the `migrations` AgentDB namespace (kebab-case is implicit when the plugin name is the intent β same documented exception as `federation`). Follows the convention from [ruflo-agentdb ADR-0001 Β§"Namespace convention"](../ruflo-agentdb/docs/adrs/0001-agentdb-optimization.md). Reserved namespaces (`pattern`, `claude-memories`, `default`) MUST NOT be shadowed.++`migrations` is accessed via `memory_*` tools (namespace-routed). Tracks migration metadata, applied/pending status, and validation results.++> **Routing note:** Earlier versions of these skills used `agentdb_hierarchical-*` and `agentdb_pattern-store` with namespace arguments β those tool families route by tier/ReasoningBank and ignore namespace strings. ADR-0001 fixed the skills to use `memory_*` for namespaced reads/writes.++## Verification++```bash+bash plugins/ruflo-migrations/scripts/smoke.sh+# Expected: "10 passed, 0 failed"+```++## Architecture Decisions++- [`ADR-0001` β ruflo-migrations plugin contract (namespace-routing fix, smoke as contract)](./docs/adrs/0001-migrations-contract.md)+## Related Plugins+- `ruflo-agentdb` β namespace convention owner; defines the routing rules ADR-0001 fixes a violation of- `ruflo-adr` -- Document schema change decisions as ADRs- `ruflo-ddd` -- Align migration boundaries with aggregate roots- `ruflo-observability` -- Track migration execution duration and failure ratesdiff --git a/plugins/ruflo-migrations/docs/adrs/0001-migrations-contract.md b/plugins/ruflo-migrations/docs/adrs/0001-migrations-contract.mdnew file mode 100644index 0000000000..c3c5c0ff10--- /dev/null+++ b/plugins/ruflo-migrations/docs/adrs/0001-migrations-contract.md@@ -0,0 +1,42 @@+---+id: ADR-0001+title: ruflo-migrations plugin contract β pinning, namespace-routing fix, namespace coordination, smoke as contract+status: Proposed+date: 2026-05-04+authors:+ - reviewer (Claude Code)+tags: [plugin, migrations, schema, namespace, smoke-test]+---++## Context++`ruflo-migrations` (v0.1.0) β schema migration generator + validator. 1 agent + 2 skills + 1 command.++Same namespace-routing bug class as ruflo-cost-tracker / ruflo-market-data: both skills called `agentdb_hierarchical-*` and `agentdb_pattern-store` with namespace arguments, but those tool families route by tier / ReasoningBank and ignore namespace strings.++## Decision++1. **Functional fix:** switch namespaced reads/writes from `agentdb_hierarchical-*` to `memory_*` (namespace-routed) in both skills. Document the dual pattern-store path (typed via ReasoningBank vs namespace-routable via `memory_store`).+2. Add this ADR (Proposed).+3. README augment: Compatibility (pin v3.6); Namespace coordination (claims `migrations`); Verification + Architecture Decisions sections.+4. Bump `0.1.0 β 0.2.0`. Keywords add `mcp`, `dry-run`, `up-down-pairs`.+5. `scripts/smoke.sh` β 10 structural checks: version + keywords; both skills + agent + command; skills use `memory_*` not `hierarchical-*` with namespace; v3.6 pin; namespace coordination; `migrations` namespace claimed; ADR Proposed; no wildcard tools.++## Consequences++**Positive:** real bugs fixed (silent ignored-namespace writes/reads). Plugin joins the cadence.++**Negative:** none β anyone scripting against the broken tool calls was already silently failing.++## Verification++```bash+bash plugins/ruflo-migrations/scripts/smoke.sh+# Expected: "10 passed, 0 failed"+```++## Related++- `plugins/ruflo-cost-tracker/docs/adrs/0001-cost-tracker-contract.md` β same bug class+- `plugins/ruflo-market-data/docs/adrs/0001-market-data-contract.md` β same bug class+- `plugins/ruflo-agentdb/docs/adrs/0001-agentdb-optimization.md` β namespace convention this fix observesdiff --git a/plugins/ruflo-migrations/scripts/smoke.sh b/plugins/ruflo-migrations/scripts/smoke.shnew file mode 100755index 0000000000..37f8443040--- /dev/null+++ b/plugins/ruflo-migrations/scripts/smoke.sh@@ -0,0 +1,86 @@+#!/usr/bin/env bash+set -u+ROOT="$(cd "$(dirname "$0")/.." && pwd)"+PASS=0+FAIL=0+step() { printf "β %s ... " "$1"; }+ok() { printf "PASS\n"; PASS=$((PASS+1)); }+bad() { printf "FAIL: %s\n" "$1"; FAIL=$((FAIL+1)); }++step "1. plugin.json declares 0.2.0 with new keywords"+v=$(grep -E '"version"' "$ROOT/.claude-plugin/plugin.json" | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' | head -1)+if [[ "$v" != "0.2.0" ]]; then bad "expected 0.2.0, got '$v'"; else+ miss=""+ for k in mcp dry-run up-down-pairs; do+ grep -q "\"$k\"" "$ROOT/.claude-plugin/plugin.json" || miss="$miss $k"+ done+ [[ -z "$miss" ]] && ok || bad "missing keywords:$miss"+fi++step "2. both skills + agent + command present with valid frontmatter"+miss=""+for s in migrate-create migrate-validate; do+ f="$ROOT/skills/$s/SKILL.md"+ [[ -f "$f" ]] || { miss="$miss missing-$s"; continue; }+ for k in 'name:' 'description:' 'allowed-tools:'; do+ grep -q "^$k" "$f" || miss="$miss $s-no-$k"+ done+done+[[ -f "$ROOT/agents/migration-engineer.md" ]] || miss="$miss missing-agent"+[[ -f "$ROOT/commands/migrate.md" ]] || miss="$miss missing-command"+[[ -z "$miss" ]] && ok || bad "$miss"++step "3. /migrate command covers 6 subcommands"+F="$ROOT/commands/migrate.md"+miss=""+for sub in create up down status validate history; do+ grep -q "$sub" "$F" || miss="$miss $sub"+done+[[ -z "$miss" ]] && ok || bad "missing subcommands:$miss"++step "4. migrate-create uses memory_* (namespace-routed) for store path"+F="$ROOT/skills/migrate-create/SKILL.md"+miss=""+grep -q "memory_store" "$F" || miss="$miss no-memory_store"+grep -qE 'agentdb_hierarchical-store.+migrations|migrations.+agentdb_hierarchical-store' "$F" && miss="$miss still-uses-hierarchical-store"+[[ -z "$miss" ]] && ok || bad "$miss"++step "5. migrate-validate uses memory_* for namespaced reads"+F="$ROOT/skills/migrate-validate/SKILL.md"+miss=""+grep -q "memory_search\|memory_list" "$F" || miss="$miss no-memory-load"+grep -qE 'agentdb_hierarchical-recall.+migrations|migrations.+agentdb_hierarchical-recall' "$F" && miss="$miss still-uses-hierarchical-recall"+[[ -z "$miss" ]] && ok || bad "$miss"++step "6. migrate-validate documents dual pattern-store path"+F="$ROOT/skills/migrate-validate/SKILL.md"+if grep -q "ReasoningBank" "$F" \+ && grep -q "memory_store --namespace migrations" "$F"; then+ ok+else+ bad "missing dual-path documentation"+fi++step "7. README pins @claude-flow/cli to v3.6"+grep -qE "@claude-flow/cli.*v3\.6|v3\.6.*claude-flow/cli" "$ROOT/README.md" \+ && ok || bad "v3.6 pin missing"++step "8. README defers to ruflo-agentdb namespace convention"+grep -q "ruflo-agentdb" "$ROOT/README.md" \+ && grep -q "Namespace convention" "$ROOT/README.md" \+ && ok || bad "namespace coordination block incomplete"++step "9. ADR-0001 exists with status Proposed"+ADR="$ROOT/docs/adrs/0001-migrations-contract.md"+[[ -f "$ADR" ]] && grep -qE "^status:[[:space:]]*Proposed" "$ADR" \+ && ok || bad "ADR missing or status != Proposed"++step "10. no wildcard tool grants in skills"+bad_skills=""+for f in "$ROOT"/skills/*/SKILL.md; do+ grep -q '^allowed-tools:[[:space:]]*\*' "$f" && bad_skills="$bad_skills $(basename $(dirname "$f"))"+done+[[ -z "$bad_skills" ]] && ok || bad "wildcard:$bad_skills"++printf "\n%s passed, %s failed\n" "$PASS" "$FAIL"+[[ $FAIL -eq 0 ]] || exit 1diff --git a/plugins/ruflo-migrations/skills/migrate-create/SKILL.md b/plugins/ruflo-migrations/skills/migrate-create/SKILL.mdindex 090bcda9f6..adf74a3bbf 100644--- a/plugins/ruflo-migrations/skills/migrate-create/SKILL.md+++ b/plugins/ruflo-migrations/skills/migrate-create/SKILL.md@@ -2,7 +2,7 @@name: migrate-createdescription: Create a new sequentially numbered database migration with up/down SQL filesargument-hint: "<name>"-allowed-tools: Read Write Glob Bash mcp__claude-flow__agentdb_hierarchical-store mcp__claude-flow__agentdb_hierarchical-recall mcp__claude-flow__agentdb_pattern-search+allowed-tools: Read Write Glob Bash mcp__claude-flow__memory_store mcp__claude-flow__memory_search mcp__claude-flow__agentdb_pattern-search---# Migrate Create@@ -24,8 +24,8 @@ When you need to create a new database migration for schema changes such as crea- Other -> generic migration template with placeholder comments3. **Generate up migration** -- write `NNN_<name>.up.sql` with the appropriate SQL using IF NOT EXISTS for idempotency4. **Generate down migration** -- write `NNN_<name>.down.sql` with the reverse operation using IF EXISTS-5. **Search patterns** -- call `mcp__claude-flow__agentdb_pattern-search` to find similar past migrations for reference-6. **Store metadata** -- call `mcp__claude-flow__agentdb_hierarchical-store` to record the migration in `migrations` namespace with number, name, status (pending), and file paths+5. **Search past patterns** -- call `mcp__claude-flow__agentdb_pattern-search` (ReasoningBank-routed; **don't** pass a `namespace` argument β pattern-* tools ignore it).+6. **Store metadata** -- call `mcp__claude-flow__memory_store --namespace migrations` to record the migration with number, name, status (pending), and file paths. The `memory_*` tool family routes by namespace; `agentdb_hierarchical-*` does NOT (it routes by tier `working|episodic|semantic`), so use `memory_*` here. See [ruflo-agentdb ADR-0001 Β§"Namespace convention"](../../../ruflo-agentdb/docs/adrs/0001-agentdb-optimization.md).7. **Report** -- display: migration number, file paths created, template used, any similar past migrations found## CLI alternativediff --git a/plugins/ruflo-migrations/skills/migrate-validate/SKILL.md b/plugins/ruflo-migrations/skills/migrate-validate/SKILL.mdindex 3ce737a7fa..a8b52bc3ff 100644--- a/plugins/ruflo-migrations/skills/migrate-validate/SKILL.md+++ b/plugins/ruflo-migrations/skills/migrate-validate/SKILL.md@@ -2,7 +2,7 @@name: migrate-validatedescription: Validate pending migrations for foreign key consistency, rollback safety, and best practicesargument-hint: ""-allowed-tools: Read Glob Grep Bash mcp__claude-flow__agentdb_hierarchical-recall mcp__claude-flow__agentdb_pattern-store mcp__claude-flow__agentdb_semantic-route+allowed-tools: Read Glob Grep Bash mcp__claude-flow__memory_search mcp__claude-flow__memory_list mcp__claude-flow__memory_store mcp__claude-flow__agentdb_pattern-store mcp__claude-flow__agentdb_semantic-route---# Migrate Validate@@ -15,7 +15,7 @@ Before applying migrations to catch issues early -- foreign key references to no## Steps-1. **Find pending migrations** -- use `Glob` to list all migration files, cross-reference with applied history via `mcp__claude-flow__agentdb_hierarchical-recall` to identify pending ones+1. **Find pending migrations** -- use `Glob` to list all migration files, cross-reference with applied history via `mcp__claude-flow__memory_search --namespace migrations` (or `memory_list`) to identify pending ones. The `memory_*` tool family routes by namespace; `agentdb_hierarchical-*` does NOT (it routes by tier), so use `memory_*` here.2. **Parse SQL** -- use `Read` to load each pending `.up.sql` and `.down.sql` file and parse the SQL statements3. **Check foreign keys** -- verify that all REFERENCES targets exist in the current schema or in prior migrations (both applied and pending)4. **Check NOT NULL defaults** -- verify that any ADD COLUMN with NOT NULL has a DEFAULT value@@ -23,7 +23,9 @@ Before applying migrations to catch issues early -- foreign key references to no6. **Flag destructive ops** -- warn on DROP TABLE, DROP COLUMN, TRUNCATE without explicit confirmation7. **Check idempotency** -- verify IF EXISTS / IF NOT EXISTS is used for safety8. **Check naming** -- verify table names are plural, column names are snake_case, index names follow `idx_table_column` convention-9. **Store results** -- call `mcp__claude-flow__agentdb_pattern-store` to record validation patterns for future reference+9. **Store validation patterns** -- two paths (per ruflo-cost-tracker ADR-0001 dual-path pattern):+ - **Pattern store (typed, recommended)**: `mcp__claude-flow__agentdb_pattern-store` with `type: 'migration-validation'`. No namespace arg β ReasoningBank routes it.+ - **Plain store (namespace-routable)**: `mcp__claude-flow__memory_store --namespace migrations` for validation results tied to a specific migration number.10. **Report** -- display: errors (must fix), warnings (should fix), info (suggestions), with file path and line number for each issue## CLI alternative