@yottameta/yotta-dev-mcp-plugin 0.0.0 → 0.2.0

package/skills/yotta-dev-mcp/references/architecture-contract.md

@@ -0,0 +1,256 @@
+# Architecture contract and system model
+
+`system_model` builds a deterministic model of a local repository and attaches
+layer data from an optional architecture contract. Everything runs offline with
+the Python standard library; no file is written.
+
+## Contract file
+
+Path: `.yotta/architecture.json`. Plain JSON, version `1`.
+
+```json
+{
+  "version": 1,
+  "project": "demo",
+  "layers": [
+    {"id": "core", "title": "Core", "paths": ["src/core/**"], "risk": "high"},
+    {"id": "api", "paths": ["src/api/**"]},
+    {"id": "ui", "paths": ["src/ui/**"]}
+  ],
+  "rules": [
+    {
+      "id": "core-no-ui",
+      "type": "forbid-dependency",
+      "from": "core",
+      "to": "ui",
+      "severity": "high",
+      "claim": "core must not import ui"
+    }
+  ],
+  "boundaries": [
+    {"id": "public-api", "layer": "api", "paths": ["src/api/public/**"], "visibility": "public"}
+  ],
+  "data_ownership": [
+    {"store": "memory-db", "owner": "core", "paths": ["var/memory/**"], "kind": "sqlite"}
+  ],
+  "invariants": [
+    {"id": "no-plaintext-secrets", "claim": "secrets are never stored in plaintext",
+     "severity": "high", "check": "static"}
+  ],
+  "risk_weights": {"core": 3, "api": 2, "ui": 1}
+}
+```
+
+### Fields
+
+| Field | Required | Notes |
+|---|---|---|
+| `version` | yes | Must be `1`. |
+| `project` | no | Free-form name. |
+| `layers` | yes | Layer id, optional title/description, `paths` globs, optional `risk`. |
+| `rules` | no | `forbid-dependency` (`to` is one layer) or `allow-dependency` (`to` is a layer list). `from`, `to`, `severity` and `claim` describe the invariant. |
+| `boundaries` | no | Layer id plus globs; `visibility` is `public`, `internal` or `private`. |
+| `data_ownership` | no | Store id, owning layer, globs and optional `kind`. |
+| `invariants` | no | id plus a non-empty `claim`; `check` is `static`, `command` or `manual`. |
+| `risk_weights` | no | Layer id to a number between 0 and 5. |
+
+Ids match `[a-z0-9][a-z0-9._-]{0,63}`. Paths are repository-relative POSIX
+globs and must not be absolute or contain `..`.
+
+### Glob rules
+
+`*` stays inside one path segment, `**` crosses segments, `?` matches one
+character, and a trailing `/` means the whole directory (`pkg/` equals
+`pkg/**`). Matching is case-sensitive. Layers are evaluated in declaration
+order and the first match wins; a module that matches several layers is
+reported as `layer-overlap`.
+
+### Validation findings
+
+Every finding carries `code`, `severity`, `message`, a JSON `pointer`, the
+contract `path` and short `evidence`. Severity `critical` or `high` makes the
+contract `FAIL`; `medium` and `low` are advisory.
+
+| Code | Meaning |
+|---|---|
+| `contract-invalid-json` | The file is not valid JSON. |
+| `contract-not-object` | The root value is not a JSON object. |
+| `contract-unsupported-version` | `version` is missing or not `1`. |
+| `contract-invalid-layer` / `contract-duplicate-layer` | Layer shape or ids are wrong. |
+| `contract-layer-without-paths` | A layer declares no globs. |
+| `contract-invalid-path` | A glob is absolute, escapes the root, or is empty. |
+| `contract-invalid-rule` / `contract-duplicate-rule` | Rule shape, type or ids are wrong. |
+| `contract-invalid-severity` / `contract-invalid-risk` | Enum values are outside the allowed set. |
+| `contract-unknown-layer-ref` | A rule, boundary, store or risk weight points at a missing layer. |
+| `contract-invalid-boundary` / `contract-invalid-store` / `contract-invalid-invariant` | Section entries are malformed. |
+| `contract-unknown-key` | Unknown top-level key; reported as a warning and ignored. |
+
+## system_model output
+
+| Key | Content |
+|---|---|
+| `status` | `PASS`, `FAIL` (contract has blocking findings) or `UNKNOWN` (something still needs evidence). |
+| `contract` | Path, presence, validity, version, layer and rule ids, findings. |
+| `model.modules` | Repository-relative module id, language, line count and resolved layer. |
+| `model.layers` | Declared layers with the modules that match them. |
+| `model.imports` | `source`, `target`, `kind`, `line` and the raw specifier. |
+| `model.entrypoints` | Files that look like executable entrypoints. |
+| `model.tests` | Test files and the internal modules they import. |
+| `model.configs` | Configuration files with a coarse kind. |
+| `model.data_stores` | Declared stores (with owner and owner modules) and detected local database files. |
+| `unknowns` | `contract-missing`, `contract-invalid`, `unassigned-module`, `layer-overlap`, `unresolved-import`. |
+| `unverified_claims` | Verification levels that were not executed, with the reason. |
+| `evidence` | Bounded, sorted evidence lines for the findings above. |
+| `truncated` | True when the file limit cut the scan short. |
+| `model_digest` | `sha256:` digest of the model, stable across runs on the same tree. |
+
+Import kinds: `internal` (another source module), `internal-file` (a
+repository file that is not source, such as `package.json`), `external`
+(outside the repository) and `unresolved` (a relative path that does not
+exist; also listed under `unknowns`).
+
+`system_model` never asserts that a change is safe. Levels `L1` and above stay
+listed in `unverified_claims` until a dedicated check runs them.
+
+## architecture_review
+
+`architecture_review` evaluates the same contract against the same system model and
+returns every finding with file, line and severity. Per-item status is `PASS`,
+`WARN` (advisory findings only), `FAIL` or `UNKNOWN`.
+
+| Code | Meaning | Severity |
+|---|---|---|
+| `rule-forbid-dependency` | a module in the rule's `from` layer imports the forbidden `to` layer | the rule's severity |
+| `rule-allow-dependency` | a module in the rule's `from` layer imports a layer outside `to` | the rule's severity |
+| `boundary-visibility` | a module imports a protected boundary it may not reach | `high` for `private`, `medium` for `internal` |
+| `data-ownership-mismatch` | a module inside the store paths is not in the owner layer | `medium` |
+| `data-store-access-outside-owner` | a module outside the owner layer references the store path | `medium` |
+
+Boundary visibility decides who may import the protected modules:
+
+- `public` - any layer may import them; the declaration is recorded and never a finding.
+- `internal` - only modules of the same layer may import them.
+- `private` - only modules inside the boundary globs may import them.
+
+Data ownership is checked in two ways: modules that live inside a store's paths but
+belong to another layer, and modules outside the owner layer that reference the
+store path literal (the part before the first wildcard).
+
+Invariants are never reported as passing. `static`, `command` and `manual` checks
+all land in `unverified_claims` with the reason, so a review can be `PASS` while
+still stating what it did not verify.
+
+The overall status is `FAIL` when the contract has blocking findings or any
+violation reaches `critical` / `high`; `UNKNOWN` when the contract is missing or
+anything stays undecided; otherwise `PASS` (advisory findings may still be listed).
+
+### Unknown kinds
+
+| Kind | Meaning |
+|---|---|
+| `contract-missing` / `contract-invalid` | no usable contract was found. |
+| `model-truncated` | the file limit cut the scan short. |
+| `unassigned-module` / `layer-overlap` | a module has no layer or matches several. |
+| `unresolved-import` | a relative import does not resolve. |
+| `rule-target-unassigned` | the rule's source layer matches, but the target module has no layer. |
+| `boundary-no-modules` | the boundary globs match no module. |
+| `boundary-importer-unassigned` | the importer has no layer, so visibility is undecided. |
+
+## impact_analysis
+
+`impact_analysis` starts from changed files, a unified diff or target symbols and
+walks reverse dependencies (internal imports and repository-file imports) into a
+bounded cone. Each node carries `depth`, `via`, `line`, `layer` and `is_test`.
+
+Alongside the cone it reports direct consumers, affected layers, boundaries, data
+stores, invariants scoped to the changed paths, tests mapped to the cone, the
+architecture violations that fall inside the cone, rollback probes and an
+explainable blast radius.
+
+| Blast radius factor | Weight | When |
+|---|---|---|
+| `layer-risk` | 0-5 | highest declared risk weight or risk level of affected layers |
+| `layer-count` | +1 / +2 | 3-4 layers / 5 or more layers are affected |
+| `cone-depth` | +1 | the consumer chain reaches depth 2 or more |
+| `public-boundary` | +1 | a public boundary is inside the cone |
+| `data-store` | +1 per store, capped at 2 | declared or detected stores are touched |
+| `architecture-violation` | +2 / +3 | a `high` / `critical` violation is inside the cone |
+
+`level` maps the capped score (10 max): 9-10 `critical`, 6-8 `high`, 3-5 `medium`,
+otherwise `low`. `score` is the raw sum of the weights and `reasons` lists every
+factor with its detail, so the number can be recomputed by hand.
+
+Rollback probes are derived, not invented: `data-store` (affected stores),
+`entrypoint` (non-test entrypoints in the cone, capped at 5), `tests` (mapped test
+files), `invariant` (declared `command` checks) and `model` (fallback when the cone
+has no anchor). Test files that only guard on `__main__` are covered by the test
+probe and are not reported as startup entrypoints.
+
+## verification policy
+
+`.yotta/verification.json` is optional. It declares the L2-L4 checks that
+`verify_change` may execute, plus manual work that must stay unverified. It never
+holds shell strings: `kind` must be one of the whitelisted runners already supported
+by `run_checks`.
+
+```json
+{
+  "version": 1,
+  "checks": [
+    {
+      "id": "unit-tests",
+      "level": "L2",
+      "kind": "python-unittest",
+      "cwd": ".",
+      "timeout": 120,
+      "required": true,
+      "claim": "the unit suite passes"
+    }
+  ],
+  "manual": [
+    {"id": "independent-review", "claim": "a second person reviews the change"}
+  ]
+}
+```
+
+| Field | Required | Notes |
+|---|---|---|
+| `version` | yes | Must be `1`. |
+| `checks` | no | Array of L2-L4 checks. |
+| `checks[].id` | yes | Unique slug matching the same id rule as the architecture contract. |
+| `checks[].level` | yes | `L2`, `L3` or `L4`. |
+| `checks[].kind` | yes | `python-unittest`, `pytest`, `python-compile`, `npm-test` or `npm-lint`. |
+| `checks[].cwd` | no | Repository-relative directory, default `.`; absolute paths and `..` are rejected. |
+| `checks[].timeout` | no | 1-600 seconds, default 120. |
+| `checks[].required` | no | Default `true`; a required check that did not run keeps the overall result `UNKNOWN`. |
+| `checks[].claim` | no | Human-readable claim recorded in the ledger. |
+| `manual[].id` / `manual[].claim` | yes | Manual claims that are always reported as unverified. |
+
+Verification findings use the same evidence shape as the architecture contract:
+`code`, `severity`, `message`, JSON `pointer`, `path` and short `evidence`.
+Blocking codes include `verification-invalid-json`,
+`verification-unsupported-version`, `verification-invalid-id`,
+`verification-duplicate-check`, `verification-invalid-level`,
+`verification-invalid-kind`, `verification-invalid-cwd`,
+`verification-invalid-timeout` and `verification-invalid-manual`.
+
+`verify_change` runs L0/L1 in-process. L2-L4 execute only when the caller passes
+`allow_execute=true`; L5 is always manual. A `PASS` means every required claim has
+evidence. Unrun or manual claims remain in `unverified_claims` and are never written
+as passing.
+
+## Command line
+
+```bash
+python scripts/dev_engine.py system-model .
+python scripts/dev_engine.py system-model . --contract config/architecture.json
+python scripts/dev_engine.py architecture-review .
+python scripts/dev_engine.py impact-analysis . --changed src/core/store.py
+python scripts/dev_engine.py impact-analysis . --diff-file change.patch --depth 2
+python scripts/dev_engine.py impact-analysis . --symbol save
+python scripts/dev_engine.py verify-change . --changed src/core/store.py
+python scripts/dev_engine.py verify-change . --changed src/core/store.py --level L2 --allow-execute
+python scripts/dev_engine.py self-test .
+python scripts/dev_engine.py adapter . --action list
+python scripts/dev_engine.py adapter . --action run --adapter import-linter --allow-execute
+```

package/skills/yotta-dev-mcp/references/tools.md

@@ -0,0 +1,257 @@
+# Tool contracts
+
+All tools are local and deterministic. Unless a section says otherwise they are
+read-only; `run_checks`, `verify_change` and `run_adapter` require
+`allow_execute=true` for their explicit execution paths, and `scaffold_skill` /
+`workflow_state` require `apply=true` before writing.
+
+## repo_map
+
+Input:
+
+- `path` (required): repository or source directory.
+- `max_files` (optional, default 2000): source file limit.
+
+Output: `root`, `modules`, `imports`, `entrypoints`, `truncated`.
+
+## system_model
+
+Input:
+
+- `path` (required): repository or source directory.
+- `max_files` (optional, default 2000): source file limit.
+- `contract_file` (optional): contract path relative to the repository root
+  (default `.yotta/architecture.json`).
+
+Output: `status` (`PASS` / `FAIL` / `UNKNOWN`), `contract`, `model` (`modules`,
+`layers`, `imports`, `entrypoints`, `tests`, `configs`, `data_stores`),
+`unknowns`, `unknowns_truncated`, `unverified_claims`, `evidence`, `truncated`
+and `model_digest`.
+
+Contract schema, glob rules, finding codes and import kinds are documented in
+`references/architecture-contract.md`.
+
+## architecture_review
+
+Input:
+
+- `path` (required): repository or source directory.
+- `max_files` (optional, default 2000): source file limit.
+- `contract_file` (optional): contract path relative to the repository root
+  (default `.yotta/architecture.json`).
+
+Output: `status` (`PASS` / `FAIL` / `UNKNOWN`), `contract`, `checked`
+(`rules` / `boundaries` / `data_stores` / `invariants`, each with a per-item
+`status` of `PASS` / `WARN` / `FAIL` / `UNKNOWN`), `violations`, `blocking_findings`,
+`advisory_findings`, `unknowns`, `unverified_claims`, `evidence`, `truncated` and
+`model_digest`.
+
+`critical` / `high` findings fail the review; `medium` / `low` stay advisory.
+Anything the model cannot decide becomes `UNKNOWN`; declared invariants that this
+tool cannot evaluate are listed in `unverified_claims` instead of being reported
+as passing. Read-only.
+
+## impact_analysis
+
+Input:
+
+- `path` (required): repository or source directory.
+- `changed_files` (optional): repository-relative changed files.
+- `diff` (optional): unified diff text; changed files and line numbers are parsed
+  from it, deleted files keep their declared layer.
+- `symbols` (optional): target symbols; their definition sites become the change.
+- `depth` (optional, default 3, 1-10): reverse-dependency depth.
+- `max_files` (optional, default 2000): source file limit.
+- `contract_file` (optional): contract path relative to the repository root.
+
+At least one of `changed_files`, `diff` or `symbols` is required.
+
+Output: `status`, `inputs`, `changed`, `direct_consumers`, `cone` (`nodes` with
+`depth` / `via` / `layer` / `is_test`, `max_depth`, `limit`, `truncated`),
+`affected_layers`, `affected_boundaries`, `affected_data_stores`,
+`affected_invariants`, `relevant_tests`, `architecture` (`status`,
+`violations_total`, `violations_in_scope`, `unknowns`), `blast_radius`
+(`level`, `score`, `capped`, `reasons`), `rollback_probes`, `unknowns`,
+`unverified_claims`, `evidence`, `truncated` and `model_digest`.
+
+`status` is `FAIL` when a blocking architecture violation sits inside the cone,
+`UNKNOWN` while anything is undecided, otherwise `PASS`. Read-only; no command is
+executed.
+
+## verify_change
+
+Input:
+
+- `path` (required): repository or source directory.
+- `changed_files` / `diff` / `symbols` (at least one): the same change inputs as
+  `impact_analysis`.
+- `depth` (optional, default 3, 1-10): reverse-dependency depth.
+- `levels` (optional): additional execution levels `L2`, `L3`, `L4` or manual `L5`.
+  L0 and L1 always run.
+- `allow_execute` (optional, default false): required before any L2-L4 check runs.
+- `timeout` (optional, default 120, 1-600): upper bound for each policy check.
+- `max_files` / `contract_file` (optional): model limit and contract override.
+- `policy_file` (optional, default `.yotta/verification.json`): policy override.
+
+Output: `status`, `inputs`, `required_levels`, `ledger`, `unverified_claims`,
+`policy`, `evidence`, `ledger_digest`, `model_digest` and `impact_status`.
+
+Every ledger entry has `id`, `level`, `claim`, `status` (`PASS` / `FAIL` / `UNKNOWN` /
+`UNVERIFIED`), `severity`, `check`, `confidence`, `evidence`, `next_step` and
+`command`. Static checks keep `command` as `null`; executed checks record the
+whitelisted kind, relative cwd, exit code, timeout flag and `output_hash`.
+
+The default ladder runs L0 (changed-file syntax, contract schema) and L1 (architecture
+rules and boundaries inside the change cone). L2-L4 are skipped unless both a policy
+check is declared and `allow_execute=true`; they never accept arbitrary commands.
+L5 is always manual and stays in `unverified_claims`. The ledger intentionally has no
+wall-clock timestamp: its digest and the command output hashes are the reproducible
+evidence anchors.
+
+## self_test
+
+Input:
+
+- `path` (required): source checkout or installed skill directory.
+- `mode` (optional, default `auto`): `auto`, `source` or `installed`.
+- `allow_execute` (optional, default false): run the target test suite.
+- `timeout` (optional, default 120, 1-600).
+
+Source mode checks required files, version alignment across `package.json` /
+`SKILL.md` / `CHANGELOG.md` / `server.json` / engine `VERSION`, protocol tool names
+and `inputSchema.additionalProperties=false`, fail-closed defaults for every write or
+execute gate, and counterexamples. Installed mode checks `SKILL.md` and the installed
+asset payload, and records source-only checks as out of scope.
+
+The counterexample suite is in-process and deterministic: a seeded forbidden
+dependency must be `FAIL`, removing the rule must stop the failure, an invalid
+contract must be `FAIL` or `UNKNOWN`, a missing contract must be `UNKNOWN`, a seeded
+credential must be found, and a seeded version mismatch must fail readiness. These
+probes prove the verifier is not a rubber stamp.
+
+## run_adapter
+
+Input:
+
+- `action` (required): `list` probes optional adapters without executing them;
+  `run` executes exactly one adapter.
+- `path` (required): repository root.
+- `adapter` (required when `action=run`): `import-linter`,
+  `dependency-cruiser` or `repomix`.
+- `allow_execute` (optional, default false): required for `action=run`.
+- `timeout` (optional, default 120, 1-600).
+- `max_chars` (optional, default 120000, 1000-1000000): Repomix output cap.
+- `token_budget` (optional): Repomix token budget; over-budget output fails.
+- `target` (optional, default `.`): repository-relative adapter target.
+
+`action=list` returns `status`, `adapters` with `available` / `ready` /
+`executable` / `executable_source` / `config` / `reason`, plus `unknowns`.
+
+`action=run` returns `status` (`PASS` / `FAIL` / `UNKNOWN`), the selected
+`adapter` metadata, a fixed `command` record with `output_hash`, normalized
+`findings`, Repomix `content` metadata when applicable, `next_step` and
+`unknowns`. Missing tools, missing configs, invalid output and timeouts are
+`UNKNOWN`, never silent passes.
+
+Adapters are optional enhancements: no package is installed or downloaded, no
+arbitrary argv is accepted, and adapter findings do not silently change the
+status of the core architecture tools. See `references/adapters.md`.
+
+## find_code
+
+Input:
+
+- `path` (required): repository, directory or file.
+- `query` (required): symbol or text.
+- `extensions` (optional): file extensions such as `.py`.
+- `max_results` (optional, default 100).
+- `context_lines` (optional, 0-5).
+
+Output: `query`, `matches` (`path`, `line`, `kind`, `text`, `context`), `truncated`.
+
+## compress_output
+
+Input:
+
+- `text` or `file` (one required).
+- `max_chars` (optional, default 4000).
+- `head_lines` / `tail_lines` (optional).
+
+Output: text plus `original_lines`, `kept_lines`, `error_lines`, `truncated`.
+
+## review_code
+
+Input:
+
+- `path` or `text` (one required).
+- `max_findings` (optional, default 200).
+
+Rules: bare-except, eval-exec, shell-true, debug-print, todo-comment,
+mutable-default.
+
+Each finding contains `path`, `line`, `rule`, `severity`, `evidence`, `suggestion`.
+
+## review_diff
+
+Input:
+
+- `diff_text` or `path` (one required).
+- `base` (optional git revision when `path` is used).
+- `max_findings` (optional).
+
+Only added lines are reviewed. Output: `files`, `findings`, `truncated`.
+
+## mcp_doctor
+
+Input:
+
+- `skills_dirs` (optional array).
+- `config_paths` (optional array).
+
+Output: `skills`, `mcp_configs`, `issues`, `checked_skills`, `checked_configs`.
+
+## scan_secrets
+
+Input: `path` or `text`, optional `max_findings`, optional `include_git_history`
+(bounded, default false).
+
+Output: `findings` with `path`, `line`, `rule`, `severity`, redacted `evidence`,
+`suggestion`; `truncated`.
+
+## scan_dependencies
+
+Input: `path`.
+
+Output: `manifests`, `lockfiles`, `issues` (`missing-lockfile`,
+`unpinned-dependency`, `insecure-source`, `local-dependency`,
+`typosquat-suspicion`), and counts. Offline heuristics only.
+
+## check_publish_readiness
+
+Input: `path`.
+
+Output: `ok`, `files`, `versions` (package / skill / changelog / engine when
+present), `issues`.
+
+## run_checks
+
+Input: `kind` (`python-unittest` / `pytest` / `python-compile` / `npm-test` /
+`npm-lint`), `cwd`, optional `timeout`, explicit `allow_execute=true`.
+
+Output: `exit_code`, `passed`, bounded `summary`, compressed `output`,
+`timed_out`.
+
+## scaffold_skill
+
+Input: `name`, `output_dir`, optional `description`, explicit `apply=true`.
+
+Output: `target`, `files`, `applied`. Default is dry-run; existing non-empty
+targets are rejected.
+
+## workflow_state
+
+Input: `root`, `action` (`read` / `append-log` / `append-file`), optional
+`date`, `text`, `file`, explicit `apply=true`.
+
+Output: `ok`, `files`, `missing`, `excerpts` for read; `target`, `applied`,
+`preview` for writes. Writes are atomic and keep a `.bak` of an existing file.