dianel555/dskills/ace-tool

ACE-Tool - Semantic Code Search & Prompt Enhancement

High-performance semantic search, code indexing, and AI-powered prompt enhancement. Standalone CLI (no MCP dependency).

Execution Methods

# Prerequisites: pip install httpx tenacity "pathspec>=1.1.1,<2"
# Environment: ACE_API_URL, ACE_API_TOKEN (optional for local fallback)
 
# Index project for remote search (upload code blobs to ACE service)
python scripts/ace_cli.py index -p /path/to/project
 
# Search codebase with natural language (remote if API configured, else local fallback)
python scripts/ace_cli.py search_context -p /path/to/project -q "function that handles authentication"
 
# Enhance prompt (interactive mode - default, opens browser)
python scripts/ace_cli.py enhance_prompt -p "implement login feature" -H "User: what auth method?\nAssistant: JWT"
 
# Enhance prompt (non-interactive, JSON output)
python scripts/ace_cli.py enhance_prompt --no-interactive -p "implement login feature"
 
# Enhance prompt with project context (enables cloud retrieval for all endpoints)
python scripts/ace_cli.py enhance_prompt -p "implement login feature" --project-root /path/to/project
 
# Enhance prompt with specific endpoint
python scripts/ace_cli.py --endpoint claude enhance_prompt -p "implement login feature"
 
# Enhance prompt with codex endpoint
python scripts/ace_cli.py --endpoint codex enhance_prompt -p "implement feature"
 
# Check configuration
python scripts/ace_cli.py get_config

Tool Routing Policy

Prefer ACE-Tool Over Built-in Tools

When to Use Built-in Tools

• Exact string matching (known identifiers)
• File path patterns (known naming conventions)
• Simple text replacement

Command Reference

index

Index project files for remote codebase retrieval. Scans, hashes, and uploads whole files (up to 128 KiB) with their original paths to the ACE batch-upload API; chunking is left to the service. Uses incremental indexing with gzip JSON cache at .ace-tool/index.json.gz; legacy chunk-based caches are rebuilt once. Respects both .gitignore and .aceignore patterns. The supplied project root is the index and upload boundary; each root keeps its own cache, and indexing a parent does not delete child caches. Symbolic links, junctions and other reparse points below the root are never followed, so only real files inside the root are read and uploaded; an unreadable or out-of-boundary path is skipped instead of falling back to a plain path read. The backend must confirm upload hashes and support the OCE-compatible /agents/blob-status endpoint; indexing, search, and scoped enhancement wait for readiness and report a timeout or unsupported status explicitly. Unknown blobs trigger one rebuild and re-upload.

python scripts/ace_cli.py index -p <project_root>
 
Options:
  -p, --project-root    Project root path (required)

search_context

Search codebase using natural language descriptions. Routes to remote API (POST /agents/codebase-retrieval) when configured, with local keyword fallback for remote errors or empty results. Upload and readiness failures remain explicit errors. Local fallback supplies matching file paths, not semantic code snippets.

python scripts/ace_cli.py search_context -p <project_root> -q <query>
 
Options:
  -p, --project-root    Project root path (required)
  -q, --query           Natural language query (required)

enhance_prompt

Enhance prompts with codebase context and conversation history. All endpoints inject cloud retrieval context when --project-root is provided. Third-party endpoints additionally support search context injection via PROMPT_ENHANCER_INCLUDE_SEARCH_CONTEXT.

python scripts/ace_cli.py [--endpoint TYPE] enhance_prompt -p <prompt> [options]
 
Global Options:
  --endpoint            Endpoint type: new, old, claude, openai, gemini, codex (default: new)
  --api-url             Override API base URL
  --token               Override API token
 
Command Options:
  -p, --prompt          Original prompt (required)
  -H, --history         Conversation history: "User: xxx\nAssistant: yyy"
  --history-file        File containing conversation history
  --project-root        Project root path (enables cloud retrieval context)
  --no-interactive      Disable web UI, output JSON directly
  --no-browser          Don't auto-open browser, just print URL
  --port                Port for web server (default: 8765)

get_config

Show current configuration status including endpoint resolution, env readiness, authentication source, and search context injection state.

python scripts/ace_cli.py get_config

Output fields:

• base_url - Currently configured API base URL
• endpoint - Active enhancer endpoint (new/old/claude/openai/gemini/codex)
• endpoint_effective - Resolved endpoint after env variable resolution
• endpoint_env_ready - Whether required endpoint configuration is complete
• token_configured - Whether authentication token is set
• third_party_configured - Whether third-party endpoint config is complete
• auth_source - Authentication source: constructor | session.json | AUGMENT_SESSION_AUTH | ACE_API_TOKEN | none
• search_context_injection - Whether search context injection is enabled

Interactive Enhancement

Default mode opens web UI with actions:

Keyboard Shortcuts: Ctrl+Enter Send | Esc Cancel

Endpoint Architecture

Supported Endpoints

Note: The official Augment endpoints (new and old) are currently experiencing service issues. Use third-party endpoints for prompt enhancement.

Endpoint Resolution Order

PROMPT_ENHANCER_ENDPOINT > ACE_ENHANCER_ENDPOINT (legacy) > --endpoint CLI flag > new (default)

Third-Party Endpoints

claude, openai, gemini, codex are third-party endpoints. They require:

• PROMPT_ENHANCER_BASE_URL — API base URL
• PROMPT_ENHANCER_TOKEN — API key/token
• PROMPT_ENHANCER_MODEL — (optional) override default model

Missing configuration raises ValueError immediately (hard error, no silent fallback).

URL Construction

All HTTP calls use build_api_url(base_url, path) which handles /v1/, /v1beta/ version prefix deduplication. No hardcoded f-string URL construction.

Environment Variables

Authentication (Priority Order)

ACE-Tool supports multiple authentication methods with the following priority:

1. Constructor parameters (highest priority, programmatic use only)
2. `~/.augment/session.json` (recommended, created by auggie login)
3. `AUGMENT_SESSION_AUTH` (CI/CD and headless environments)
4. Legacy `ACE_API_*` (deprecated, backward compatibility only)

Recommended: Use `~/.augment/session.json`

Create this file via auggie login, or manually with this format:

{
  "accessToken": "your-token-here",
  "tenantURL": "https://api.example.com/",
  "scopes": ["email"]
}

For CI/CD: Use `AUGMENT_SESSION_AUTH` environment variable

export AUGMENT_SESSION_AUTH='{"accessToken":"token","tenantURL":"https://api.example.com/"}'

Migration Guide: Legacy to New Format

If currently using ACE_API_URL and ACE_API_TOKEN:

1. Option A (Recommended): Use auggie login to create ~/.augment/session.json
2. Option B: Convert to AUGMENT_SESSION_AUTH:

``bash export AUGMENT_SESSION_AUTH='{"accessToken":"YOUR_ACE_API_TOKEN","tenantURL":"YOUR_ACE_API_URL"}' ``

1. Remove old variables (optional, they'll be ignored if new format exists)

Legacy variables continue to work for backward compatibility but are not recommended for new setups.

Endpoint Configuration

Settings are positive and finite. The byte budget counts content only, excluding JSON/HTTP overhead, and each blob must fit within it. Read/write and other uncertain transport errors, or HTTP 408, 429, and 5xx responses, trigger /agents/blob-status polling before retransmission. Previously uncertain blobs receive a 5-second grace period when status is unknown; pending blobs are polled up to 180 seconds. These are not strict wall-clock limits because HTTPX read timeouts measure inactivity. When status remains uncertain or unavailable, unresolved blobs are retried automatically up to three potentially sent attempts per blob across process restarts. The server may still be processing an earlier request, so this does not guarantee exactly-once server work. Exhausted attempts, authentication failures, and unsafe recovery state produce explicit errors.