xrtm-forecast v0.12.0

The Runtime Engine for XRTM.

xrtm-forecast provides the agents, providers, topologies, and orchestration to build AI forecasting systems. It's a composable framework — import the pieces you need and wire them together.

What's new in v0.12

Baselines: MarketImpliedBaseline (the honest benchmark for prediction markets), BaseRateBaseline, and ConstantBaseline.
Lexical retrieval: zero-dependency BM25 LexicalRetriever for archive search/dedup without embedding models.

What's new in v0.11

Search-result cache: CachedSearchTool caches tool results with a TTL, cutting external API calls and making backtests reproducible.

What's new in v0.10

Reasoning-model ready: thinking-mode toggle, reasoning_content handling, and explicit EmptyContentError (plus a larger-max_tokens retry) instead of silent parse failures.
Structured output + telemetry: provider-enforced JSON, parse_status, token usage (including cached/reasoning tokens), and model/prompt provenance on every forecast.
Typed decisions: DecisionProvider (LLM and TypeSafe Jev) with an escalation router for cheap System-One gating.
Cost policies: currency-aware pricing (DeepSeek CNY preset), cost ledgers, hard budgets, and off-peak scheduling.
Reliability: token-bucket rate limiting, jittered retries, cache TTL, and deterministic-only caching by default.

Installation

pip install xrtm-forecast

Quick Start

from xrtm.forecast.kit.agents.specialists.analyst import ForecastingAnalyst
from xrtm.forecast.core.config.inference import OpenAIConfig
from xrtm.forecast.providers.inference.factory import ModelFactory

# Use any OpenAI-compatible endpoint


config = OpenAIConfig(
    model_id="your-model",
    base_url="$OPENAI_BASE_URL",
    api_key="your-api-key",
)
provider = ModelFactory.get_provider(config)
analyst = ForecastingAnalyst(model=provider, name="forecaster")

# Ask a forecasting question
from xrtm.data import ForecastQuestion
question = ForecastQuestion(
    id="fed-march-2025",
    title="Will the Fed raise rates in March 2025?",
)
forecast = await analyst.run(question)
print(f"Probability: {forecast.probability:.2f}")

What's Included

OpenAI-compatible Provider

One provider that works with any OpenAI-compatible API: any OpenAI-compatible endpoint. Set base_url to point anywhere.

Agents

ForecastingAnalyst — Full forecast agent: structured prompts, causal reasoning traces, JSON output parsing
LLMAgent — Base agent with tool retrieval, output parsing
RoutingAgent — FAST/SMART tiered routing for cost optimization
ToolAgent / GraphAgent — Wrap functions or sub-graphs as agents

Topologies

Composable multi-agent patterns in kit/topologies/:

RecursiveConsensus — Parallel analysts → aggregate → supervisor → loop
create_debate_graph() — Pro/Con/Judge debate pattern
create_fanout_graph() — Parallel workers → aggregator

Orchestration

Orchestrator — DAG state machine for workflow graphs
AsyncRuntime — Chronos-aware async runtime

Infrastructure

InferenceCache — SQLite cache for LLM responses (enabled by default)
Retry with backoff — 2 retries on API errors
LeakageGuardian — Temporal leakage prevention for backtests

XRTM Ecosystem

Part of the XRTM forecasting stack:

Package	Role	Version
`xrtm-data`	Schemas & question sources	0.3.0
`xrtm-eval`	Scoring (Brier, ECE, LogScore)	0.3.0
`xrtm-forecast`	Runtime engine (this package)	0.7.0
`xrtm-train`	Backtesting & optimization	0.3.0
`xrtm`	Product CLI	0.9.0

License

Apache 2.0

Metadata

Release files for xrtm-forecast 0.13.2

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

Source distribution (sdist)

Source distribution for xrtm-forecast 0.13.2
File	Size	Uploaded	Provenance
xrtm_forecast-0.13.2.tar.gz	89.6 kB	Oct 16, 2026	With provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for xrtm-forecast 0.13.2
File	Interpreter	ABI	Platform	Reset
xrtm_forecast-0.13.2-py3-none-any.whl 141.2 kB Oct 16, 2026 With provenance	Python 3	none	any	Details

Total release size: 230.8 kB

Release files / xrtm_forecast-0.13.2.tar.gz

Download URL	xrtm_forecast-0.13.2.tar.gz
Size	89.6 kB
Tags	Source
SHA-256 checksum How to use checksums	`a0cccca5b6aedb5d97b9903a928b8b6bd7505acafa426f1c30c63ab072b3a237`
BLAKE2b-256 checksum How to use checksums	`5fe9b3eda33f1474e73c6c59c99d124a7282bec932b570392b5b0985a27ec21b`
Upload date	Oct 16, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/xrtm-org/forecast
Publishing commit: github.com/xrtm-org/forecast/tree/4cb9de2fe5cd30634219d7156c53c26651d39cbd

Workflow

Publishing configuration: github.com/xrtm-org/forecast/blob/4cb9de2fe5cd30634219d7156c53c26651d39cbd/.github/workflows/publish.yml
Publishing logs: github.com/xrtm-org/forecast/actions/runs/38942507992/attempts/1

Artifact

Subject: xrtm_forecast-0.13.2.tar.gz
SHA-256 checksum: a0cccca5b6aedb5d97b9903a928b8b6bd7505acafa426f1c30c63ab072b3a237 Verifying attestations

Release files / xrtm_forecast-0.13.2-py3-none-any.whl

Download URL	xrtm_forecast-0.13.2-py3-none-any.whl
Size	141.2 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`833f074695a7c9ea3eae51f254022438894e397fbaaa690fe00464dfb8d72026`
BLAKE2b-256 checksum How to use checksums	`338df256090524bfe32b8ff7e549dea8dce5ee3273ee7c2b207b0c1db8b481cf`
Upload date	Oct 16, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/xrtm-org/forecast
Publishing commit: github.com/xrtm-org/forecast/tree/4cb9de2fe5cd30634219d7156c53c26651d39cbd

Workflow

Publishing configuration: github.com/xrtm-org/forecast/blob/4cb9de2fe5cd30634219d7156c53c26651d39cbd/.github/workflows/publish.yml
Publishing logs: github.com/xrtm-org/forecast/actions/runs/38942507992/attempts/1

Artifact

Subject: xrtm_forecast-0.13.2-py3-none-any.whl
SHA-256 checksum: 833f074695a7c9ea3eae51f254022438894e397fbaaa690fe00464dfb8d72026 Verifying attestations

Security for xrtm-forecast 0.13.2

Report project as malware

Provenance

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Attestation for xrtm_forecast-0.13.2.tar.gz

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/xrtm-org/forecast
Publishing commit: github.com/xrtm-org/forecast/tree/4cb9de2fe5cd30634219d7156c53c26651d39cbd

Workflow

Publishing configuration: github.com/xrtm-org/forecast/blob/4cb9de2fe5cd30634219d7156c53c26651d39cbd/.github/workflows/publish.yml
Publishing logs: github.com/xrtm-org/forecast/actions/runs/38942507992/attempts/1

Artifact

Subject: xrtm_forecast-0.13.2.tar.gz
SHA-256 checksum: a0cccca5b6aedb5d97b9903a928b8b6bd7505acafa426f1c30c63ab072b3a237 Verifying attestations

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.