Skip to main content

Infinium Claude Code Connector

Bridge between Claude Code hooks and Infinium agent tracing. Automatically captures Claude Code sessions — tool calls, prompts, subagent activity — and sends structured traces to the Infinium platform for Maestro analysis.

Quick Start

Navigate to your project, install, and set up:

cd /path/to/your/project
pip install infinium-claude-code-connector
infinium-claude init
infinium-claude test

That's it. Now just use Claude Code as you normally would — every session is automatically traced to Infinium. No server to run, no extra terminal, nothing to remember.

If infinium-claude is not on your PATH, use python -m infinium_connector as a drop-in replacement.

How It Works

After infinium-claude init, everything is automatic. You use Claude Code exactly as before — the connector works silently in the background via hooks.

Claude Code ──command hook──> python -m infinium_connector.hook
                                  │
                                  ├─ append event to session JSONL file
                                  │
                                  └─ on Stop/SessionEnd:
                                       replay events → aggregate → send trace
                                                                      │
                                                                      ▼
                                                              Infinium API
                                                          POST /agents/{id}/trace
  1. Claude Code fires a command hook for each event (tool call, prompt, etc.)
  2. The hook script appends the event to a session JSONL file on disk
  3. On turn completion (Stop) or session end, all events are replayed, aggregated into a structured trace, and sent to Infinium via the Python SDK
  4. Maestro interprets the trace (grading accuracy, efficiency, prompt adherence)

CLI Reference

infinium-claude init

Interactive setup wizard. Configures credentials and Claude Code hooks.

Options:
  --agent-id TEXT        Agent ID (skip prompt)
  --agent-secret TEXT    Agent Secret (skip prompt)
  --base-url TEXT        API base URL
  --no-interactive       Use flags only, no prompts (for CI/scripting)

infinium-claude test

Send a test trace to verify your setup works end-to-end.

Options:
  -v, --verbose    Show the full trace payload before sending

infinium-claude status

Show current configuration: tracing state, credentials, config source, hook locations, pending retries.

infinium-claude pause / infinium-claude resume

Temporarily stop or restart tracing. Hooks stay installed — events are silently skipped while paused.

Aliases: stop / continue

infinium-claude history

View recently sent traces.

Options:
  -n, --limit N    Number of entries (default: 10)
  --json           Output raw JSON lines
  --clear          Delete all history

infinium-claude retry

Resend traces that failed due to network issues.

Options:
  --dry-run    Show what would be retried without sending

infinium-claude update-credentials

Update your Agent ID or Secret.

infinium-claude uninstall

Remove the connector completely — hooks, config file, and keyring secret.

Options:
  -y, --yes    Skip confirmation prompt

infinium-claude cleanup

Remove stale session files (housekeeping).

infinium-claude start

Start HTTP server mode (alternative to command hooks, requires pip install infinium-claude-code-connector[server]).

Per-Project Configuration

Each project traces to its own Infinium agent:

cd /path/to/project-a
infinium-claude init    # Enter Agent A credentials

cd /path/to/project-b
infinium-claude init    # Enter Agent B credentials

Config resolution order:

  1. Project config (.infinium/config.json in the working directory)
  2. Environment variables (INFINIUM_AGENT_ID, INFINIUM_AGENT_SECRET — override for CI/Docker)

Add .infinium/ to your .gitignore.

Credential Storage

  • Agent ID and API URL are stored in the project config file (.infinium/config.json)
  • Agent Secret is stored in your OS keyring:
    • Windows: Credential Manager
    • macOS: Keychain
    • Linux: Secret Service (GNOME Keyring / KWallet)
  • Environment variables (INFINIUM_AGENT_ID, INFINIUM_AGENT_SECRET) override stored values — useful for CI/Docker

What Gets Traced

Field Source
name Session summary (e.g., "Claude Code session (3 turns)")
description First user prompt (200-char preview)
input_summary First user prompt, up to 3000 chars — what Maestro reads as the request
output_summary Last assistant response, up to 8000 chars — what Maestro reads as the deliverable
duration Total session duration in seconds
steps Ordered list: user prompts, tool calls, subagent spawns (input_preview up to 200 chars, output_preview up to 1500 chars)
errors Tool failures with error messages
environment Model, session source, working directory, permission mode

Captured Events

Event What It Captures
SessionStart Model, source (startup/resume), working directory
UserPromptSubmit User prompt text (200-char step preview; the first prompt is kept up to 3000 chars as input_summary)
PreToolUse / PostToolUse Tool name, input (up to 200 chars), output (up to 1500 chars), duration
PostToolUseFailure Error details
SubagentStart / SubagentStop Subagent lifecycle (cowork, agent teams)
Stop Assistant's final response (1500-char step preview; the last response is kept up to 8000 chars as output_summary) — triggers trace flush
SessionEnd Session cleanup — triggers final flush

Configuration

Environment variables (all optional — init handles the common case):

# Credentials (override config file + keyring)
INFINIUM_AGENT_ID=...
INFINIUM_AGENT_SECRET=...
INFINIUM_BASE_URL=...

# Connector behavior
CONNECTOR_QUIET=false              # Suppress output
CONNECTOR_FLUSH_ON_STOP=true       # Send trace after each turn
CONNECTOR_FLUSH_ON_SESSION_END=true
CONNECTOR_SESSION_TTL=3600         # Stale session cleanup threshold (seconds)
CONNECTOR_SESSION_DIR=...          # Override temp directory for session files

# Payload caps (characters) — defaults match what Maestro's trace judge renders
CONNECTOR_MAX_INPUT_PREVIEW=200    # Per-step input_preview
CONNECTOR_MAX_OUTPUT_PREVIEW=1500  # Per-step output_preview (tool results, turn responses)
CONNECTOR_MAX_INPUT_SUMMARY=3000   # Top-level input_summary (first user prompt)
CONNECTOR_MAX_OUTPUT_SUMMARY=8000  # Top-level output_summary (last assistant response)

Documentation

Full documentation: i42m.ai/docs/claude-code

License

MIT

Metadata

Release files for infinium-claude-code-connector 1.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for infinium-claude-code-connector 1.4.0
File Size Uploaded
infinium_claude_code_connector-1.4.0.tar.gz 66.3 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for infinium-claude-code-connector 1.4.0
File Interpreter ABI Platform
infinium_claude_code_connector-1.4.0-py3-none-any.whl Python 3 none any Details

Total release size: 119.0 kB

Release files / infinium_claude_code_connector-1.4.0.tar.gz

Download URL infinium_claude_code_connector-1.4.0.tar.gz
Size 66.3 kB
Tags Source
SHA-256 checksum
How to use checksums
e1747a11fdbd6ea289e9e8532aab78b59e53724087ae0e323b65f200a5407d0c
BLAKE2b-256 checksum
How to use checksums
90b78f8dad9329cbb669eeca4435c30974750d00a6e78553349c8d9c912d9377
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Release files / infinium_claude_code_connector-1.4.0-py3-none-any.whl

Download URL infinium_claude_code_connector-1.4.0-py3-none-any.whl
Size 52.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
0cc84b5a99d40a6cfe1e74871ca5ae14f109419daad86ad562d06188a4b6594f
BLAKE2b-256 checksum
How to use checksums
e31801094969fb8b20bb23514ce90afc85e844cf4a964a751b4631aa44207f65
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Release history Release notifications | RSS feed

This release

1.4.0 This release

2 release files

1.3.0

2 release files

1.2.1

2 release files

1.2.0

2 release files

1.1.1

2 release files

1.1.0

2 release files

1.0.3

2 release files

1.0.1

2 release files

1.0.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page