项目文件夹

文件
Seth Hobson be57c0b2e3 feat: multi-harness plugin marketplace (Codex, Cursor, OpenCode, Gemini) (#541)
* feat(adapters): multi-harness framework + harness_portability eval dimension

Turn this Claude Code plugin marketplace into a generic agentic-harness
marketplace. Adapters under tools/adapters/ emit harness-native artifacts
for OpenAI Codex CLI, Cursor, OpenCode, and Gemini CLI from a single
Markdown source. Source-of-truth stays under plugins/ — Claude Code is
unchanged.

Framework (tools/adapters/):
- base.py — PluginSource parser, HarnessAdapter ABC, write/mirror helpers
  (path-traversal guard, UTF-8-safe), inline-list + block-list + block-scalar
  YAML-ish parser, _utf8_safe_cut, _split_inline_list, _normalize_author
- capabilities.py — per-harness capability matrix, TOOL_NAME_MAPS,
  MODEL_ALIASES, resolve_model() with explicit warnings
- codex.py — emits .codex/{skills,agents}/ + AGENTS.md (≤150-line
  table-of-contents). Fence-aware body splitter, _utf8_safe_cut for
  multibyte safety, _yaml_scalar with reserved-word + special-char quoting.
  Skill/command name collision detection (and second-order __cmd fallback).
- cursor.py — emits .cursor-plugin/{plugin,marketplace}.json + curated
  .cursor/rules/*.mdc. _validate_mdc_frontmatter handles YAML block scalars
  (no false positives on colons in description body). _normalize_author
  handles dict, npm-style strings, and author lists.
- opencode.py — transpiles agents to .opencode/agents/<id>.md with
  mode:subagent + permission: deny-everything-else block (skill/task always
  allowed as base capabilities — Claude's implicit defaults).
- gemini.py — emits native skills/, agents/, and commands/ at extension
  root (April 2026 spec). Tool-allowlist remapped via TOOL_NAME_MAPS.

CLI + tooling:
- tools/generate.py — unified `make generate HARNESS=<x> [PLUGIN=<y>]`,
  with --clean (containment-guarded; case-insensitive on Darwin/Win32),
  --prune (orphan removal across all per-harness output trees), --strict
  (warnings fail), per-plugin error aggregation, refuses --clean --plugin
  (would silently wipe other plugins' artifacts).
- tools/validate_generated.py — structural validation across all four
  harness outputs. Codex 8KB cap → error. _extract_permission_block
  correctly handles nested permission keys (column-0 only).
- tools/doc_gardener.py — recurring drift detection per OpenAI harness-
  engineering principle. STALE_ARTIFACT (info), DEAD_LINK (error),
  MARKETPLACE_ORPHAN (error), SKILL_OVER_CODEX_CAP (warning), grouped
  output sorted by severity.

plugin-eval (extends existing framework):
- New harness_portability dimension (6% weight, rebalanced from existing
  static sub-scores). Surfaces non-portable patterns with concrete
  remediation hints: SKILL_OVER_CODEX_CAP, CLAUDE_TOOL_REFS,
  CLAUDE_TOOL_PROSE, AGENT_NAME_COLLISION, BARE_MODEL_ALIAS.
- _CAMEL_TOOL_PATTERN requires Claude-tool context (no false positives
  on Rust's `Task` etc.). _TOOL_PROSE_PATTERN case-sensitive on tool
  names, case-insensitive on the leading article.
- Findings do NOT also feed anti_pattern_penalty (no double-counting).

Documentation:
- Top-level guides: CODEX.md, CURSOR.md, OPENCODE.md (≤150 lines each,
  table-of-contents pattern per OpenAI harness-engineering post)
- docs/harnesses.md — capability matrix, graceful-degradation table,
  generated output paths
- docs/authoring.md — portable-content style guide (tools, models,
  collision rules, fence-respect)
- docs/round-trip-results.md — real-CLI verification recipes (OpenCode
  discovers 193 subagents, Gemini extensions validate passes, Codex
  TOMLs all parse)
- CONTRIBUTING.md — new file pointing at docs/authoring.md
- README.md — rewritten for multi-harness (145 lines, was 460)
- CLAUDE.md — trimmed to 60-line table-of-contents
- GEMINI.md — trimmed from 1500 to 500 tokens (3× over budget previously)

Tests: 181 passing (103 plugin-eval + 78 tools/tests). Real-CLI round-trip
verified for OpenCode, Gemini, and Codex (TOML parses).

Replaces tools/generate_gemini_commands.py with the unified CLI.

* refactor(skills): extract detail to references/details.md (~75 skills)

Apply Anthropic's canonical SKILL.md progressive-disclosure pattern across
the marketplace: SKILL.md body becomes a navigation tier (trigger phrasing
+ quick start), detailed templates and worked examples move to
references/details.md (loaded on demand by the agent).

Motivation: OpenAI Codex CLI hard-truncates skills at 8 KB. Before this
change, ~90 skills exceeded that cap and would silently break on Codex.
The progressive-disclosure pattern is also Anthropic's documented
recommendation for token efficiency — Claude Code reads references/ files
on demand when the body navigation says to.

What's extracted, by pattern:
- Pass 1 (## Templates section): 19 skills — full template libraries
  moved to references/details.md
- Pass 2 (## Implementation Patterns / ## Advanced Patterns): 13 skills
- Pass 3 (everything between nav-tier and wrap-tier headings): 53 skills
- Conservative re-extraction for 8 skills that got over-reduced — kept
  ~6-7 KB inline (most of the quick-start tier) plus references/ overflow

What stays inline (SKILL.md navigation tier):
- description: frontmatter (triggering — unchanged for all skills)
- ## When to Use This Skill / ## Core Concepts / ## Quick Start
- ## Best Practices / ## Troubleshooting / ## See Also wrap-ups
- A pointer note ("see references/details.md") so the agent knows where
  to look for detail

What goes to references/details.md (detail tier, on-demand load):
- ## Templates (full code template libraries)
- ## Implementation Patterns / ## Advanced Patterns (deep examples)
- Mid-skill walkthroughs that exceed the inline budget

Also in this commit:
- plugins/brand-landingpage description trimmed from 958→543 chars
  (preserves trigger phrasing, drops verbose example-quote list)

Net effect:
- SKILL_OVER_CODEX_CAP findings: 90 → 10 (88% reduction)
- All triggers unchanged — discovery behavior identical across harnesses
- 75 new references/details.md files with the extracted content
- Same depth of guidance, loaded progressively

Remaining 10 oversized skills are complex multi-section docs (e.g.
postgresql, code-review-excellence, evaluation-methodology) that need
per-skill manual judgment — flagged by `make garden` for future work.

* chore: bump all plugin versions (multi-harness release)

Patch-bump every local plugin (81) in both .claude-plugin/marketplace.json
entries and each plugins/<name>/.claude-plugin/plugin.json. Minor-bump the
top-level marketplace metadata.version (1.6.0 → 1.7.0) to signal the
multi-harness adapter framework addition.

The external git-subdir entry (qa-orchestra) is unaffected — its version
is governed by its upstream repo.

* fix(opencode): preserve explicit tools:[] + word-boundary subtask match

Addresses two Codex review findings on PR #541.

## P1 — `tools: []` silently upgraded to permissive (privilege escalation)

Before: `_build_permission_block` returned `{}` for any empty list, which
omits the `permission:` block entirely from the emitted agent. An author
who explicitly wrote `tools: []` to lock down an advisory-only agent got
an UNRESTRICTED agent in OpenCode. Affected agent in this tree:
`plugins/arm-cortex-microcontrollers/agents/arm-cortex-expert.md`.

Fix: `_build_permission_block` now takes a `has_tools_field` flag so the
caller can distinguish "tools: key missing" (Claude default permissive)
from "tools: []" (explicit lock-down). The lock-down case emits a
deny-everything block that allows ONLY the base capabilities (skill, task)
that Claude Code always grants implicitly. Verified against the real
arm-cortex-expert agent — now emits read/edit/write/bash/grep/glob/list:
deny, task/skill: allow.

## P2 — `"agent" in cmd.body.lower()` false-positives on substrings

Before: a command body containing `PerformanceReviewAgent` (class name
in a code snippet) or `useragent` triggered `subtask: true`, changing
runtime behavior based on incidental text.

Fix: switch to a compiled word-boundary regex `\b(agent|subagent)s?\b`
(case-insensitive). Tests confirm the substring `PerformanceReviewAgent`
no longer fires, while a real "spawn a subagent" sentence still does.

## Tests

3 new regression tests in tools/tests/test_adapters.py:
- `test_explicit_empty_tools_yields_locked_permission_block` (P1)
- `test_missing_tools_field_yields_no_permission_block` (P1 boundary)
- `test_subtask_inference_word_boundary` (P2)

184 total tests pass (was 181). OpenCode round-trip still discovers all
193 subagents; arm-cortex-expert agent is now properly locked down.

* test: behavioral verification + CI gates for multi-harness pipeline

Adds three layers of automated verification that pure-Python parser tests
miss, plus the CI jobs that turn them into hard gates. Catches the kinds
of issues that previously only surfaced when a real user installed the
marketplace and tried to use it.

## test_real_world.py — real-source structural tests

Runs against the actual `plugins/` tree (not synthetic fixtures). Catches
issues that only appear on real content:

- every marketplace entry resolves to a plugins/<name>/ dir
- every local plugin dir appears in marketplace.json
- marketplace.json version == per-plugin plugin.json version (catches drift)
- every plugin loads via load_plugin() without error
- no plugin name contains `__` (adapter namespace separator)
- every agent has name + description; every skill has a trigger phrase
  (same regex plugin_eval's MISSING_TRIGGER check uses)
- no agent name collides with Codex built-ins
- every refactored skill (with `references/details.md`) has:
  - meaningful detail content (>=500 B in details.md)
  - a pointer to references/ in the SKILL.md body
  - a navigation-tier heading preserved (When to Use, Overview, etc.)
  - body >= 600 B (not a stub)
- every plugin.json has name + version matching the dir

This test pass found and fixed three real defects before commit:
- ship-mate/skills/scan: description had no trigger phrase ("Use when…")
- reverse-engineering/skills/memory-forensics: nav-tier section lost
  during extraction
- reverse-engineering/skills/binary-analysis-patterns: same

All three are now fixed (preserved trigger phrasing, added When-to-Use
sections back to the skills my extraction over-trimmed).

## test_round_trip.py — generate→parse→verify

CI runs this AFTER `make generate-all`. Catches generation-time regressions:

- OpenCode/Codex/Gemini agent counts match source agent count (no skips)
- every Codex SKILL.md under 8 KB (the cap that would silently truncate)
- every Codex agent TOML has required fields + valid sandbox_mode
- every OpenCode agent has mode in {primary,subagent,all} and
  provider-prefixed model
- locked agents (source `tools: []`) emit proper deny-everything permission
  block with skill/task allow (regression guard for PR-541 P1)
- every Gemini @{path} injection resolves to a real source file
- every Gemini command TOML has prompt + {{args}} placeholder
- every context file (CLAUDE.md, AGENTS.md, GEMINI.md, etc.) within
  150-line cap
- Cursor marketplace + per-plugin manifests cover all local plugins
- .cursor/rules/*.mdc only use the 3 documented frontmatter keys

## test_cli_smoke.py — real-CLI subprocess tests

Invokes the actual harness binaries (OpenCode, Gemini, Codex, Claude Code)
against the generated artifacts. Catches CLI-level issues pure-Python
parsing can't see: schema-loader drift, plugin-discovery bugs, version
incompatibilities.

- `opencode agent list` — must succeed AND discover every source agent
  (currently 191 + 2 OpenCode built-ins)
- `gemini extensions validate <repo>` — must return success
- `codex doctor` — must report healthy install
- every Codex agent TOML must parse with stdlib `tomllib`
- `claude --version` — sanity check the Claude Code CLI loads
- marketplace.json must have owner + metadata.version for Claude Code's loader

Per-CLI tests skip gracefully when the binary isn't on PATH, so local
devs only exercise what they have installed. CI installs OpenCode +
Gemini and turns those skips into hard gates.

## Makefile + CI

- `make test` — full pytest suite (plugin-eval + tools/tests/)
- `make smoke-test` — generates if needed, then runs real-CLI smoke tests
- `.github/workflows/validate.yml` extended with:
  - `tools-tests` job — runs pytest tools/tests/
  - `multi-harness-generate` job — `make generate-all && make validate
    STRICT=1 && make garden`, uploads generated artifacts on every run
  - `cli-smoke-test` job — installs OpenCode + Gemini, runs test_cli_smoke.py

## Test counts

- Before: 184 tests
- After: 386 tests (parameterized real-source tests over all 82 plugins)
- All passing locally on OpenCode 1.15.7 + Gemini 0.42.0 + Codex 0.133.0
  + Claude Code 2.1.148
2026-05-22 08:18:21 -04:00

14 KiB

projection-patterns — templates and worked examples

Templates

Template 1: Basic Projector

from abc import ABC, abstractmethod
from dataclasses import dataclass
from typing import Dict, Any, Callable, List
import asyncpg

@dataclass
class Event:
    stream_id: str
    event_type: str
    data: dict
    version: int
    global_position: int


class Projection(ABC):
    """Base class for projections."""

    @property
    @abstractmethod
    def name(self) -> str:
        """Unique projection name for checkpointing."""
        pass

    @abstractmethod
    def handles(self) -> List[str]:
        """List of event types this projection handles."""
        pass

    @abstractmethod
    async def apply(self, event: Event) -> None:
        """Apply event to the read model."""
        pass


class Projector:
    """Runs projections from event store."""

    def __init__(self, event_store, checkpoint_store):
        self.event_store = event_store
        self.checkpoint_store = checkpoint_store
        self.projections: List[Projection] = []

    def register(self, projection: Projection):
        self.projections.append(projection)

    async def run(self, batch_size: int = 100):
        """Run all projections continuously."""
        while True:
            for projection in self.projections:
                await self._run_projection(projection, batch_size)
            await asyncio.sleep(0.1)

    async def _run_projection(self, projection: Projection, batch_size: int):
        checkpoint = await self.checkpoint_store.get(projection.name)
        position = checkpoint or 0

        events = await self.event_store.read_all(position, batch_size)

        for event in events:
            if event.event_type in projection.handles():
                await projection.apply(event)

            await self.checkpoint_store.save(
                projection.name,
                event.global_position
            )

    async def rebuild(self, projection: Projection):
        """Rebuild a projection from scratch."""
        await self.checkpoint_store.delete(projection.name)
        # Optionally clear read model tables
        await self._run_projection(projection, batch_size=1000)

Template 2: Order Summary Projection

class OrderSummaryProjection(Projection):
    """Projects order events to a summary read model."""

    def __init__(self, db_pool: asyncpg.Pool):
        self.pool = db_pool

    @property
    def name(self) -> str:
        return "order_summary"

    def handles(self) -> List[str]:
        return [
            "OrderCreated",
            "OrderItemAdded",
            "OrderItemRemoved",
            "OrderShipped",
            "OrderCompleted",
            "OrderCancelled"
        ]

    async def apply(self, event: Event) -> None:
        handlers = {
            "OrderCreated": self._handle_created,
            "OrderItemAdded": self._handle_item_added,
            "OrderItemRemoved": self._handle_item_removed,
            "OrderShipped": self._handle_shipped,
            "OrderCompleted": self._handle_completed,
            "OrderCancelled": self._handle_cancelled,
        }

        handler = handlers.get(event.event_type)
        if handler:
            await handler(event)

    async def _handle_created(self, event: Event):
        async with self.pool.acquire() as conn:
            await conn.execute(
                """
                INSERT INTO order_summaries
                (order_id, customer_id, status, total_amount, item_count, created_at)
                VALUES ($1, $2, $3, $4, $5, $6)
                """,
                event.data['order_id'],
                event.data['customer_id'],
                'pending',
                0,
                0,
                event.data['created_at']
            )

    async def _handle_item_added(self, event: Event):
        async with self.pool.acquire() as conn:
            await conn.execute(
                """
                UPDATE order_summaries
                SET total_amount = total_amount + $2,
                    item_count = item_count + 1,
                    updated_at = NOW()
                WHERE order_id = $1
                """,
                event.data['order_id'],
                event.data['price'] * event.data['quantity']
            )

    async def _handle_item_removed(self, event: Event):
        async with self.pool.acquire() as conn:
            await conn.execute(
                """
                UPDATE order_summaries
                SET total_amount = total_amount - $2,
                    item_count = item_count - 1,
                    updated_at = NOW()
                WHERE order_id = $1
                """,
                event.data['order_id'],
                event.data['price'] * event.data['quantity']
            )

    async def _handle_shipped(self, event: Event):
        async with self.pool.acquire() as conn:
            await conn.execute(
                """
                UPDATE order_summaries
                SET status = 'shipped',
                    shipped_at = $2,
                    updated_at = NOW()
                WHERE order_id = $1
                """,
                event.data['order_id'],
                event.data['shipped_at']
            )

    async def _handle_completed(self, event: Event):
        async with self.pool.acquire() as conn:
            await conn.execute(
                """
                UPDATE order_summaries
                SET status = 'completed',
                    completed_at = $2,
                    updated_at = NOW()
                WHERE order_id = $1
                """,
                event.data['order_id'],
                event.data['completed_at']
            )

    async def _handle_cancelled(self, event: Event):
        async with self.pool.acquire() as conn:
            await conn.execute(
                """
                UPDATE order_summaries
                SET status = 'cancelled',
                    cancelled_at = $2,
                    cancellation_reason = $3,
                    updated_at = NOW()
                WHERE order_id = $1
                """,
                event.data['order_id'],
                event.data['cancelled_at'],
                event.data.get('reason')
            )

Template 3: Elasticsearch Search Projection

from elasticsearch import AsyncElasticsearch

class ProductSearchProjection(Projection):
    """Projects product events to Elasticsearch for full-text search."""

    def __init__(self, es_client: AsyncElasticsearch):
        self.es = es_client
        self.index = "products"

    @property
    def name(self) -> str:
        return "product_search"

    def handles(self) -> List[str]:
        return [
            "ProductCreated",
            "ProductUpdated",
            "ProductPriceChanged",
            "ProductDeleted"
        ]

    async def apply(self, event: Event) -> None:
        if event.event_type == "ProductCreated":
            await self.es.index(
                index=self.index,
                id=event.data['product_id'],
                document={
                    'name': event.data['name'],
                    'description': event.data['description'],
                    'category': event.data['category'],
                    'price': event.data['price'],
                    'tags': event.data.get('tags', []),
                    'created_at': event.data['created_at']
                }
            )

        elif event.event_type == "ProductUpdated":
            await self.es.update(
                index=self.index,
                id=event.data['product_id'],
                doc={
                    'name': event.data['name'],
                    'description': event.data['description'],
                    'category': event.data['category'],
                    'tags': event.data.get('tags', []),
                    'updated_at': event.data['updated_at']
                }
            )

        elif event.event_type == "ProductPriceChanged":
            await self.es.update(
                index=self.index,
                id=event.data['product_id'],
                doc={
                    'price': event.data['new_price'],
                    'price_updated_at': event.data['changed_at']
                }
            )

        elif event.event_type == "ProductDeleted":
            await self.es.delete(
                index=self.index,
                id=event.data['product_id']
            )

Template 4: Aggregating Projection

class DailySalesProjection(Projection):
    """Aggregates sales data by day for reporting."""

    def __init__(self, db_pool: asyncpg.Pool):
        self.pool = db_pool

    @property
    def name(self) -> str:
        return "daily_sales"

    def handles(self) -> List[str]:
        return ["OrderCompleted", "OrderRefunded"]

    async def apply(self, event: Event) -> None:
        if event.event_type == "OrderCompleted":
            await self._increment_sales(event)
        elif event.event_type == "OrderRefunded":
            await self._decrement_sales(event)

    async def _increment_sales(self, event: Event):
        date = event.data['completed_at'][:10]  # YYYY-MM-DD
        async with self.pool.acquire() as conn:
            await conn.execute(
                """
                INSERT INTO daily_sales (date, total_orders, total_revenue, total_items)
                VALUES ($1, 1, $2, $3)
                ON CONFLICT (date) DO UPDATE SET
                    total_orders = daily_sales.total_orders + 1,
                    total_revenue = daily_sales.total_revenue + $2,
                    total_items = daily_sales.total_items + $3,
                    updated_at = NOW()
                """,
                date,
                event.data['total_amount'],
                event.data['item_count']
            )

    async def _decrement_sales(self, event: Event):
        date = event.data['original_completed_at'][:10]
        async with self.pool.acquire() as conn:
            await conn.execute(
                """
                UPDATE daily_sales SET
                    total_orders = total_orders - 1,
                    total_revenue = total_revenue - $2,
                    total_refunds = total_refunds + $2,
                    updated_at = NOW()
                WHERE date = $1
                """,
                date,
                event.data['refund_amount']
            )

Template 5: Multi-Table Projection

class CustomerActivityProjection(Projection):
    """Projects customer activity across multiple tables."""

    def __init__(self, db_pool: asyncpg.Pool):
        self.pool = db_pool

    @property
    def name(self) -> str:
        return "customer_activity"

    def handles(self) -> List[str]:
        return [
            "CustomerCreated",
            "OrderCompleted",
            "ReviewSubmitted",
            "CustomerTierChanged"
        ]

    async def apply(self, event: Event) -> None:
        async with self.pool.acquire() as conn:
            async with conn.transaction():
                if event.event_type == "CustomerCreated":
                    # Insert into customers table
                    await conn.execute(
                        """
                        INSERT INTO customers (customer_id, email, name, tier, created_at)
                        VALUES ($1, $2, $3, 'bronze', $4)
                        """,
                        event.data['customer_id'],
                        event.data['email'],
                        event.data['name'],
                        event.data['created_at']
                    )
                    # Initialize activity summary
                    await conn.execute(
                        """
                        INSERT INTO customer_activity_summary
                        (customer_id, total_orders, total_spent, total_reviews)
                        VALUES ($1, 0, 0, 0)
                        """,
                        event.data['customer_id']
                    )

                elif event.event_type == "OrderCompleted":
                    # Update activity summary
                    await conn.execute(
                        """
                        UPDATE customer_activity_summary SET
                            total_orders = total_orders + 1,
                            total_spent = total_spent + $2,
                            last_order_at = $3
                        WHERE customer_id = $1
                        """,
                        event.data['customer_id'],
                        event.data['total_amount'],
                        event.data['completed_at']
                    )
                    # Insert into order history
                    await conn.execute(
                        """
                        INSERT INTO customer_order_history
                        (customer_id, order_id, amount, completed_at)
                        VALUES ($1, $2, $3, $4)
                        """,
                        event.data['customer_id'],
                        event.data['order_id'],
                        event.data['total_amount'],
                        event.data['completed_at']
                    )

                elif event.event_type == "ReviewSubmitted":
                    await conn.execute(
                        """
                        UPDATE customer_activity_summary SET
                            total_reviews = total_reviews + 1,
                            last_review_at = $2
                        WHERE customer_id = $1
                        """,
                        event.data['customer_id'],
                        event.data['submitted_at']
                    )

                elif event.event_type == "CustomerTierChanged":
                    await conn.execute(
                        """
                        UPDATE customers SET tier = $2, updated_at = NOW()
                        WHERE customer_id = $1
                        """,
                        event.data['customer_id'],
                        event.data['new_tier']
                    )