fruxon 0.10.0

The Fruxon SDK is a lightweight Python client for integrating with the Fruxon platform.

fruxon

Run, build, and orchestrate AI agents from your terminal — the official Python SDK and CLI for the Fruxon platform.

Install

pip install fruxon

Requires Python 3.10+.

30-second quickstart

fruxon login                                       # opens a browser; stores the token in your OS keychain
fruxon agents list                                 # see what's deployed in your workspace
fruxon agents schema my-agent                      # learn what parameters my-agent expects
fruxon agents draft pull my-agent                  # fetch the working copy locally
fruxon agents draft validate my-agent              # lint the flow structure before pushing
fruxon agents draft run my-agent -p question="hi"  # run the draft to validate it

Production invocation of a deployed agent isn't a CLI concern — call it from your app via the Python client. The CLI is for building and maintaining agents.

fruxon doctor will tell you if anything's misconfigured.

The CLI

Top-level discovery commands — useful whether you're a human or an AI agent driving the CLI:

Command	What it does
fruxon describe	Dump the entire CLI surface as one JSON document (paths, args, options, types, defaults, choices, examples). The right entry point for an LLM driver — read it once, fluent.
fruxon examples [topic]	Curated, pasteable invocations grouped by topic (draft, agents, executions, …).
fruxon completion {bash|zsh|fish}	Print a shell-completion script. eval "$(fruxon completion zsh)" to install.
fruxon guides list / show <id>	Bundled CLI playbooks. Start with fruxon-meet; AI-agent drivers should load fruxon-agent-mode first.
fruxon doctor	Diagnose local setup (interpreter, SDK version, credentials, API reachability, auth).

Auth:

Command	What it does
fruxon login	Browser-based sign-in. token goes to your OS keychain (Keychain on macOS, Secret Service on Linux, Credential Manager on Windows). --token $KEY for headless. --preset observer|operator|developer|maintainer|admin declares the access level the key is minted with (default: developer); the approval page shows it for the user to approve or deny.
fruxon whoami	Show the active key/workspace and where each value came from (flag, env, keychain, file).
fruxon logout	Forget stored credentials.
fruxon config list / get / set / unset	Read/edit the persistent CLI config.

Execution:

Command	What it does
fruxon agents draft run <agent> -p k=v	Run the agent's draft revision (Origin=TEST — owner-scoped, no prod spend). The CLI's one execution surface. Streams text by default; pass --output json or --no-stream for the full result envelope. Under agent mode, emits NDJSON on stdout — one JSON record per SSE event.
fruxon agents executions list <agent>	List past executions, newest-first. Filter by --status, --origin (PRODUCTION default / TEST), --revision, --since/--until, --limit. The discovery step — find a record id.
fruxon agents executions get <agent> <record-id>	Record summary for one execution — status, duration, cost, tokens.
fruxon agents executions trace <agent> <record-id>	Step-by-step trace of one execution — LLM/tool calls, durations.
fruxon agents executions result <agent> <record-id>	The final output one execution produced.
fruxon agents approvals list/get/respond/cancel <agent>	Operate a step's human-in-the-loop gate — see what a run is blocked on and answer it. respond/cancel confirm first and refuse without --yes in agent mode (an LLM must not silently auto-approve).
fruxon agents memory list/subjects/get/forget-subject <agent>	Inspect and prune what an agent remembers. list filters server-side by --subject/--search/--scope; forget-subject is a GDPR-style delete (confirms; refuses without --yes in agent mode).
fruxon agents topics list/search/get/messages <agent> + fruxon agents inbox <agent>	Read the conversation spine — the agent's topics (threads), one topic's transcript, and its inbox (what it's focused on). list/search filter server-side by --state/--participant/--query. Read-only.
fruxon agents sandbox open/turn/fire/resolve-input/stream/answer/close <session>	Drive an agent-network sandbox end-to-end without real channels — send turns as participants, test-fire triggers, and watch the run (stream, NDJSON in agent mode). Sandbox captures the reply and hard-blocks every real send; --await makes consult/approval gates suspend so they can be resolved (answer for consults, approvals respond for approvals).
fruxon agents sandbox test <file-or-dir>	Run scenario-based e2e tests of an agent's network behavior. A scenario (YAML/JSON) declares steps (turns / trigger fires), responders (scripted consult/approval answers), and expect assertions (reply / routing / no-leak / outcome); the runner drives a sandbox session and returns one verdict — exit 0 (pass) / 1 (fail) / 12 (bad file), with --junit for CI. An optional setup block provisions real resources first — an asset (uploaded + ingestion-waited), participant, or agent — templated as ${asset.catalog.id} and torn down afterwards even on failure (--keep to inspect). Assertions are deterministic by default; reply_judge: {metric, min_score} adds an opt-in semantic check that scores the reply against a tenant eval metric. The thing an agent runs to prove the agent it built works.

Invoking a deployed agent in production goes through the Python client (FruxonClient.stream / execute), not the CLI.

Agent authoring + management:

Command	What it does
fruxon agents list	Browse every agent in your workspace. --output id for shell pipes; --include-disabled (-a) to include disabled ones.
fruxon agents get <id>	Inspect one agent — display name, deployed revision, tags, expected parameters.
fruxon agents schema <id>	Typed parameter metadata — names, types, required, options. The shape a run will accept.
fruxon agents validate <id> -p k=v	Pre-flight a payload against the schema. Catches missing-required / wrong-type / invalid-option client-side, surfacing every finding in one pass.
fruxon agents create --file <body.json>	Provision a new agent shell. Pair with --schema to print the JSON schema for the body first.
fruxon agents draft schema	Print the JSON Schema for a draft body (DraftPayload) — the flow file you author, full step-capability closure inlined.
fruxon agents draft validate <id> [--online]	Lint a draft body's flow structure locally (no network): missing entry/exit, slot ids, tool→slot wiring, AGENT provider config, dangling edges. --online also resolves references against the live catalog (unknown/unpublished config, unreal model, bad tool id). {valid, errors, warnings} envelope (the same errors as agents validate); exits 12 on any error. warnings[] are advisory wiring gaps (consult_unwired, approver_slot_undeclared) that never flip valid or the exit code.
fruxon agents draft run <id> --file <def.json>	Run a draft flow definition against an existing agent without publishing it. A CI gate for agent changes.
fruxon agents revisions create/get/deploy	Mint and deploy immutable revisions. create --deploy does both in one step.
fruxon agents check <id>	Audit whether a deployed agent is wired to run end-to-end, beyond the flow body: a deployed revision, an inbound path (bound trigger / channel), a consult roster if a step enables consult, declared approver slots, every bound trigger populating the agent's required params, and that the revision's references resolve. {overall, checks[]} (doctor-style); exits non-zero only on a hard fail (no deployed revision) — advisory warn rows stay exit 0.
fruxon agents draft pull/push/status/undo/redo/reset/discard	Local working-copy authoring loop — same draft an open studio tab edits.
fruxon agents draft evaluate <id> --dataset <uuid>	Score the draft against a golden dataset (expensive — every sample is a full agent run).
fruxon agents tests list/show/watch/cost/delete	Browse + tail the test-chat sessions you've run on an agent (owner-scoped).
fruxon agents budget list/get/set/delete	Per-origin (PRODUCTION / TEST) cost caps and spend visibility.

Integrations + tools:

Command	What it does
fruxon integrations list/get/create/update/verify/open	Manage external integrations — the connections agents draw tools from. create/update/verify take a --file JSON body; open opens the dashboard.
fruxon integrations configs list/get	Inspect the per-integration auth/config records.
fruxon integrations authorize <integration>	Mint an application-level OAuth authorization URL to connect an integration — auto-detects its OAuth2 method (--auth-method to pick, --scope/--config-param to tune). OAuth needs a browser consent step, so the CLI hands you the link; a human clicks it, and the connection is saved as a tenant config a slot can pin.
fruxon integrations triggers <integration>	List the event types an integration can fire an agent on — each descriptor's id is the eventType a trigger listens for, plus the payloadFields (dotted paths) a binding's parameterMappings can read. Discovery for wiring an inbound-event trigger without guessing.
fruxon integrations mcp …	Inspect and enable the MCP server for an integration.
fruxon tools list/get/create/update/delete/test	Manage the tools inside an integration. Integration-scoped. test runs a tool with sample params before wiring it into an agent.
fruxon keys list/mint/revoke/delete/history/scopes	Audit and revoke scoped tokens. Minting opens the dashboard so the secret never enters the CLI process.
fruxon llm-providers list/get/models	Browse LLM providers and models supported at the tenant level.
fruxon assets create/list/get/wait/operations/delete	Manage knowledge-base (RAG) assets a step can query — upload local files, wait for async ingestion, inspect operations, and use the ids for assetConfig.assetIds. delete confirms + refuses without --yes in agent mode.
fruxon metrics list	Browse the evaluation-metric catalog — the ids a step's LLM-judge config (judge.metrics[]) binds, with a default weight each.
fruxon triggers list/get/create/update/delete/fire/bind/unbind	Manage triggers — the schedule/event sources that fire agents. create/update take --file (+--schema); bind/unbind wire which agents fire; fire runs it now. fire/delete/unbind confirm + refuse without --yes in agent mode. The control plane for autonomy.
fruxon secrets list/get/grants	Discover tenant secrets a step can reference — the ids for allowedSecretIds and the {{secret.KEY}} names, with publish-state and per-agent grants. Metadata only; values are never returned.
fruxon participants list/get/create/update/delete/enable/disable	Manage agent-network participants (people / groups / agents the network routes to). create/update take --file (+--schema); enable/disable toggle routing; delete confirms + refuses without --yes in agent mode.
fruxon capabilities list/get/create/update/delete	Manage the consult-routing vocabulary (capabilities = name/area/description) that roster bindings and pins reference. create/update take --file (+--schema); delete --yes-gated in agent mode.
fruxon participants bind/unbind/roster + fruxon agents roster	Wire a participant onto an agent's consult roster and set its policy (roles / urgency / response policy); agents roster reads who advises an agent. unbind --yes-gated.
fruxon consult-pins list/get/create/delete	Deterministic capability→participant routing overrides (skip the network's scoring). create takes --file (+--schema); delete --yes-gated.
fruxon triggers list/get	Discover tenant triggers — the scheduled / event sources that fire agents, invisible to draft authoring otherwise.
fruxon agents channels list / agents endpoints	Inspect how a networked agent receives inbound — its channel bindings and resolved provider endpoints (with bot identity).
fruxon skills list/show	Browse the tenant's product-skill catalog (resources that attach to agents at runtime).

fruxon agents draft run — examples

fruxon agents draft pull my-agent                                  # fetch the working copy first
fruxon agents draft run my-agent -p question="Hello" -p lang=en
fruxon agents draft run my-agent -p temp:=0.7 -p tags:='["a","b"]' # ':=' for typed JSON
fruxon agents draft run my-agent -p prompt=@./prompt.md            # '@file' reads from disk
fruxon agents draft run my-agent --params ./params.json            # whole-object input
cat params.json | fruxon agents draft run my-agent --stdin
fruxon agents draft run my-agent --output json                     # full result envelope
fruxon agents draft run my-agent --file my-agent.draft.json        # push local edits, then run

Agent mode (CI, Claude Code, custom orchestrators)

When CLAUDECODE=1, CI=1, or FRUXON_AGENT_MODE=1 is set, the CLI flips to a contract designed for parseability:

• JSON by default. Every --output flag defaults to json. Every read command emits a stable shape; every write echoes the server's response.
• NDJSON streaming. fruxon agents draft run and fruxon agents tests watch emit one JSON record per line on stdout ({"type":"text","delta":"..."}, {"type":"tool_call",...}, {"type":"done",...}).
• Typed exit codes. 10 = auth_required, 11 = not_found, 12 = validation, 13 = conflict, 14 = server_error, 15 = network_error, 16 = interactive_required. Match on the number, not on prose.
• Structured errors. Every failure emits a one-line JSON envelope on stderr: {"error":{"code","message","exit_code","hint"}}.
• Interactive guards. Any path that would block on stdin (browser login, --edit, missing --yes) fails fast with EXIT_INTERACTIVE_REQUIRED and a hint naming the bypass flag.
• Cold-start manifest. Bare fruxon invocation emits a one-line JSON manifest with next-step commands so an LLM driver learns the surface without --help walking.

Full contract: fruxon guides show fruxon-agent-mode.

The Python client

from fruxon import FruxonClient

client = FruxonClient(token="...", workspace="acme-corp")

# One-shot
result = client.execute(
    "support-agent",
    parameters={"question": "How do I reset my password?"},
)
print(result.response)
print(f"{result.trace.duration}ms · ${result.trace.total_cost:.4f}")

# Multi-turn — thread the session ID into subsequent calls
followup = client.execute(
    "support-agent",
    parameters={"question": "Tell me more"},
    session_id=result.session_id,
)

# Streaming
for chunk in client.stream_text("support-agent", parameters={"question": "Hi"}):
    print(chunk, end="", flush=True)

# Lower-level: typed SSE events (text, tool_call, tool_result, done, …)
for event in client.stream("support-agent", parameters={"question": "Hi"}):
    ...

# Discovery
for agent in client.list_agents():
    print(agent.id, agent.current_revision)

# Typed parameter metadata — what `execute` / `stream` will accept
schema = client.get_agent_parameter_metadata("support-agent", revision=1)
for p in schema["metadata"]:
    print(p["name"], p["type"], "required" if p.get("required") else "optional")

# Test a draft flow without publishing it (same result shape as execute)
result = client.test("support-agent", {"flow": {...}, "baseRevision": 3, "parameters": {...}})
for event in client.stream_test("support-agent", {"flow": {...}}):
    ...

# Integrations & tools — the connections + capabilities agents are built from
for integ in client.list_integrations(types=["CUSTOM"]):
    print(integ.id, integ.type)
client.create_integration({"id": "github", "displayName": "GitHub", "configMetadata": {...}})
for tool in client.list_tools("github"):
    print(tool.id, tool.tool_type)
client.create_tool("github", {"id": "list_commits", "integrationId": "github", "descriptor": {...}})
client.test_tool("github", {"descriptor": {...}, "parameters": {"repo": "fruxon-sdk"}})

# Assets — local files become RAG knowledge sources after async ingestion
created = client.create_asset_from_file("./handbook.pdf", name="Support handbook")
asset_id = created["asset"]["id"]
client.wait_for_asset(asset_id, operation=created["longOperation"]["id"])
for asset in client.list_assets():
    print(asset.id, asset.vectorized)

The client picks up FRUXON_TOKEN, FRUXON_WORKSPACE, and FRUXON_BASE_URL only if you read them yourself — the constructor takes explicit values. The CLI resolves them automatically (flags → env → stored config).

Credentials & storage

The CLI resolves auth in this order (first non-empty wins):

1. Explicit flags — --token / --workspace / --base-url
2. Environment — FRUXON_TOKEN / FRUXON_WORKSPACE / FRUXON_BASE_URL
3. Stored credentials (managed by fruxon login)

The stored layer is split:

• token → OS keychain via keyring. Set FRUXON_NO_KEYRING=1 or let the keyring be unavailable to fall back to a 0600 JSON file.
• Non-secrets (workspace, base_url) → plain JSON under ~/.fruxon/credentials.

fruxon config list shows both sources side by side.

Environment variables

Var	Effect
FRUXON_TOKEN	Default token.
FRUXON_WORKSPACE	Default workspace.
FRUXON_BASE_URL	Override the API base URL (staging / self-hosted).
FRUXON_CONFIG_DIR	Override the credentials directory (default ~/.fruxon).
FRUXON_DASHBOARD_URL	Override where fruxon login points the browser.
FRUXON_AGENT_MODE=1	Opt into the agent-mode contract (JSON outputs, NDJSON streams, typed exits, structured errors). Also auto-detected from CLAUDECODE=1 / CI=1.
FRUXON_NO_KEYRING=1	Force the JSON-file fallback for the token.
FRUXON_CA_BUNDLE	Path to a PEM file of extra trusted CAs (corporate TLS proxies).
FRUXON_INSECURE=1	Disable TLS verification (dev/staging only — never production).
FRUXON_NO_BANNER=1	Suppress all branding chrome.
FRUXON_NO_UPDATE_CHECK=1	Opt out of the "newer version available" notifier.
NO_COLOR=1	Standard convention — disables color output.

Docs

• Installation
• CLI reference
• Python client
• Auth & configuration

In-CLI:

• fruxon describe — the whole command tree as JSON
• fruxon guides list — bundled procedural playbooks (orientation, build-agent, agent-mode contract, debug-revision, …)

License

MIT — see LICENSE.