Files
shannon/docs/development.md
T
ezl-keygraph 5ff40f8c6f feat(worker): migrate agent runtime from Claude Agent SDK to pi harness (#389)
* feat(worker): migrate agent runtime from Claude Agent SDK to pi harness

* feat: remove Google Vertex AI provider support

* fix(worker): route Bedrock and custom-base-URL providers from env

* feat(prompts): instruct agents to call submit_exploitation_queue and submit_auth_result

* fix(worker): count sub-agent cost and surface compaction failures

* refactor(worker): rename claude-executor to pi-executor

* feat(worker): pi-event-driven output formatting

* fix(worker): gate adaptive thinking to Opus models, drop CLAUDE_THINKING_LEVEL

* fix(worker): restore minLength/minItems on vuln-collector schemas

* feat(worker): give task sub-agent write+bash, align tool descriptions

* feat(worker): add glob custom tool and route code_path globs to it

* refactor(prompts): use pi tool names (task, todo_write, read, bash, glob)

* refactor(prompts): drop stale MCP terminology for collector tools

* refactor(prompts): drop collector server names from deliverable instructions

* fix(worker): restore minLength/minItems on pre-recon and exploit collector schemas

* feat(worker): load playwright-cli skill via pi resource loader

* refactor(cli): remove CLAUDE_CODE_MAX_OUTPUT_TOKENS config

* build: drop @anthropic-ai/claude-code from worker image

* docs: remove vertex references from llms context

* docs(worker): update stale sdk comments

* refactor(worker): unify provider precedence between preflight and executor

* feat(worker): enforce bounded bash timeouts via pi extension

* ci: bump the beta release line to 2.0.0 (#356)

* fix(cli): pin npx command hints to beta tag

* fix: render agent deliverables before the success commit so resume preserves them (#377)

* feat(cli): restructure run folder and improve terminal UX (#383)

* feat: surface report at run root and nest run internals under .shannon

* feat: use plain-language wording in user-facing terminal messages

* feat(cli): guide users to watch scan progress and surface report path on start

* docs: sync run-folder layout and CLI wording across docs and comments

* feat(cli): add version command reporting package version or git SHA

* feat(cli): detect TTY for interactive prompts, color, and progress output

* docs: document --yes flag, version command, and tty module

* fix(cli): FORCE_COLOR precedence and plain uninstall --yes output

* fix(cli): respect empty NO_COLOR

* fix(cli): let NO_COLOR take precedence over FORCE_COLOR

* docs: mark claude-code-router integration as removed

* refactor(worker): converge shared core with shannon-oss (#388)

* fix(worker): port keygraph shared-core correctness fixes

* refactor(worker): adopt collectors/ and ai/pi/ layout; add task budget cap and cancellation

* refactor(worker): drop inconsistent Collector "Server" suffix

* refactor(worker): drop unused providerConfig/apiKey seams, resolve credentials from env only

* refactor(worker): port oss code_path pattern expansion + external_directory allow

* fix(worker): preserve dotfile paths in code_path avoid patterns (.env no longer stripped to env)

* feat(worker): render Unprocessed Vulnerabilities section in exploit deliverable (align with oss)

* feat(worker): request set_blind_spots for all vuln classes (align auth/ssrf with production prompts)

* refactor(worker): adopt unified permissionSystem* naming and helper layout

* refactor(worker): inline blind_spots into vuln deliverable section array

* chore(worker): drop unused zod dependency (tree is typebox-native)

* fix(worker): normalize base32 TOTP secret to accept padding and whitespace

* refactor(worker): adopt shared toolResult helper and flatSchema naming in collectors

* refactor(worker): use undefined over null in queue-schema builders

* docs(worker): converge renderer/collector doc comments to current pi terminology

* refactor(worker): adopt schema.ts cleanInput/stringEnum helpers in collectors

* feat(worker): converge exploit-collector/renderer with vendored; capture and render overview for blocked findings

* refactor(worker): converge session-tools/pipeline/exploitation-checker with vendored

* refactor(worker): converge task-tool usage reporting with vendored onUsage callback

* refactor(worker): converge structured output onto a submitTool executor channel

* docs(worker): expand exploit-renderer docstring to match shannon-oss

* docs(worker): adopt richer vuln-renderer docstring from shannon-oss

* docs(worker): neutralize billing-detection wording for shannon-oss parity

* fix(worker): verify checkpoint hash in the deliverables clone being reset

* fix(worker): fail fast on malformed exploitation queue JSON

* fix(worker): honor retryable flag when classifying exploitation-queue check failures

* fix(worker): fail fast on corrupted session.json in run-scope validation

* feat(worker): propagate Temporal cancellation signal into agent and auth pi sessions

* fix(worker): mark exploit agent complete when exploitation is skipped so resume skips it

* prompts: drop scan description from executive report prompt

* refactor(worker): add createGenericSubmitTool for raw JSON-schema submit tools

* refactor(worker): gate playwright-cli skill to browser agents via skillsOverride (adopt shannon-oss mechanism)

* docs(worker): correct formatLogTime comment to UTC to match toISOString

* refactor(worker): converge queue-schemas with shannon-oss (guarded count, decl order)

* refactor(worker): converge task-tool with shannon-oss (byte-identical; modelRegistry optional)

* fix(worker): use replaceLiteral for all prompt value insertions to prevent $-mangling

* fix(worker): classify agent execution failures by error type instead of hardcoding validation

* fix(worker): cap auth-failure detail at 250 chars to match shannon-oss

* style(worker): apply biome formatting

* refactor(worker): remove per-session task delegation cap from task tool

* style(cli): collapse usage hint now that the beta tag is gone

* chore: mark the pi harness migration as a breaking change

BREAKING CHANGE: Google Vertex AI is no longer a supported provider. The
CLAUDE_CODE_USE_VERTEX, ANTHROPIC_VERTEX_PROJECT, CLOUD_ML_REGION, and
GOOGLE_APPLICATION_CREDENTIALS environment variables, along with the
use_vertex, vertex_project, and cloud_ml_region config.toml keys, are
removed. Vertex users must switch to Anthropic, AWS Bedrock, or a custom
Anthropic-compatible base URL.

The CLAUDE_CODE_MAX_OUTPUT_TOKENS environment variable and the
max_output_tokens config.toml key are also removed.
2026-07-16 19:13:13 +05:30

3.7 KiB

Source Build and CLI Commands

This guide covers the source-build workflow, common CLI commands, repository paths, and output locations. For the fastest first run, use the npx workflow in the main README.

Prerequisites

  • Docker
  • Node.js 18+
  • pnpm
  • AI provider credentials

Clone and Build

Use the source-build workflow if you want to run Shannon from a local clone, modify the open-source CLI, or keep the worker image built locally.

# 1. Clone Shannon.
git clone https://github.com/KeygraphHQ/shannon.git
cd shannon

# 2. Configure credentials.
cp .env.example .env

# 3. Install dependencies and build.
pnpm install
pnpm build

# 4. Run a pentest.
./shannon start -u https://your-app.com -r /path/to/your-repo

At minimum, your .env file should include one supported AI provider credential, such as:

ANTHROPIC_API_KEY=your-api-key

Environment variables can also be exported directly:

export ANTHROPIC_API_KEY="your-api-key"

Prepare Your Repository

Shannon can scan any repository on your machine. Pass an absolute or relative path with -r.

npx @keygraph/shannon start -u https://example.com -r /path/to/repo
./shannon start -u https://example.com -r ./relative/path

The target repository is mounted read-only inside the worker container.

Common Commands

Monitor progress:

npx @keygraph/shannon logs <workspace>
npx @keygraph/shannon status
npx @keygraph/shannon version

Source-build equivalents:

./shannon logs <workspace>
./shannon status
./shannon version

Open the Temporal Web UI for detailed monitoring:

open http://localhost:8233

Stop Shannon:

npx @keygraph/shannon stop
npx @keygraph/shannon stop --clean       # confirms first; add --yes (or -y) to skip
npx @keygraph/shannon uninstall          # confirms first; add --yes (or -y) to skip

Source-build equivalents:

./shannon stop
./shannon stop --clean                   # add --yes (or -y) to skip the confirmation

Usage examples:

# Basic pentest.
npx @keygraph/shannon start -u https://example.com -r /path/to/repo

# With a configuration file.
npx @keygraph/shannon start -u https://example.com -r /path/to/repo -c /path/to/my-config.yaml

# Custom output directory.
npx @keygraph/shannon start -u https://example.com -r /path/to/repo -o ./my-reports

# Named workspace.
npx @keygraph/shannon start -u https://example.com -r /path/to/repo -w q1-audit

# List all workspaces.
npx @keygraph/shannon workspaces

Source-build examples:

./shannon start -u https://example.com -r /path/to/repo
./shannon start -u https://example.com -r /path/to/repo -c /path/to/my-config.yaml
./shannon start -u https://example.com -r /path/to/repo -o ./my-reports
./shannon start -u https://example.com -r /path/to/repo -w q1-audit
./shannon workspaces

# Rebuild the worker image.
./shannon build --no-cache

Output and Results

Results are saved to the workspaces directory:

  • ./workspaces/ in source-build mode
  • ~/.shannon/workspaces/ in npx mode

Use -o <path> to copy deliverables to a custom output directory after a run completes.

Output structure — the run directory's top level holds only the final report; everything else is nested under a hidden .shannon/ directory:

workspaces/{hostname}_{sessionId}/
|-- Security-Assessment-Report.md   # the final report (the deliverable)
`-- .shannon/                       # internals
    |-- deliverables/               # report source, per-phase analysis, queues
    |-- agents/                     # per-agent logs
    |-- prompts/                    # rendered prompts
    |-- scratchpad/                 # screenshots, scripts
    |-- session.json                # resume state
    `-- workflow.log