Skip to main content

pyrunir-mcp

pyrunir-mcp is a typed Python API for planning-and-learning agents. Callers keep domains, tasks, candidates, validation results, and history in memory; filesystem artifacts are written only at the dump boundary.

See docs/api.md for the API and docs/index.md for workflow/output tables.

Basic Flow

from pyrunir_mcp import (
    ValidationHistory,
    create_domain_context,
    create_policy,
    create_task_context,
    dump_result,
    execute_policy,
    generate_tasks,
)

domain = create_domain_context("domain.pddl")
task = create_task_context(domain, "problem.pddl")
policy = create_policy(domain, "policy.txt")
history = ValidationHistory()

result = execute_policy(task, policy)
feedback = history.fold(result.observation)
dump_result(result, "artifacts/execute-policy")

Entry Points

Context/candidates:

  • create_domain_context(domain_file)
  • create_task_context(domain_context, problem_file, num_threads=1)
  • create_policy(domain_context, policy_file); pass None for an empty policy
  • write_empty_policy(domain_context, policy_file) for canonical empty policy text
  • create_module_program(domain_context, module_program_file); pass None for the built-in empty module program
  • create_classifier(domain_context, classifier_file); pass None for an empty classifier

runir.task_generation:

  • describe_generator(domain_name)
  • get_generator_path(domain_name) / get_generator_domain_path(domain_name)
  • generate_tasks(domain_name, output_dir, batch_name, configs, allow_invalid=False)

Validation:

  • execute_policy(task_context, policy, classifier=None, ...)
  • prove_policy(task_context, policy, evidence_classifier=None, ...)
  • execute_module_program(task_context, module_program, classifier=None, ...)
  • prove_module_program(task_context, module_program, evidence_classifier=None, ...)
  • prove_classifier(task_context, classifier, ...)

Dumping:

  • dump_result(result, output_dir, formats=(DumpFormat.JSON,))
  • dump_validation_history(history, output_dir, formats=(DumpFormat.JSON,))

DumpFormat.PSV, DumpFormat.MD, and DumpFormat.JSON request LLM-readable PSV, human-readable Markdown, and machine-readable JSON. Validation calls do not write files.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pyrunir_mcp-0.0.21.tar.gz (93.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pyrunir_mcp-0.0.21-py3-none-any.whl (80.4 kB view details)

Uploaded Python 3

File details

Details for the file pyrunir_mcp-0.0.21.tar.gz.

File metadata

  • Download URL: pyrunir_mcp-0.0.21.tar.gz
  • Upload date:
  • Size: 93.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for pyrunir_mcp-0.0.21.tar.gz
Algorithm Hash digest
SHA256 6488e2c9a9c63e30068c921283a977e5033a55c6e49504e3157a7855abd03359
MD5 1bc177cc80cf458438276a4829305a2d
BLAKE2b-256 f70c4cbc34d270366ef74cbfd5a1e884d2c58d9e6cfdb2628ff18aca4c43ab9e

See more details on using hashes here.

Provenance

The following attestation bundles were made for pyrunir_mcp-0.0.21.tar.gz:

Publisher: release.yml on planning-and-learning/runir-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file pyrunir_mcp-0.0.21-py3-none-any.whl.

File metadata

  • Download URL: pyrunir_mcp-0.0.21-py3-none-any.whl
  • Upload date:
  • Size: 80.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for pyrunir_mcp-0.0.21-py3-none-any.whl
Algorithm Hash digest
SHA256 291f020bc36ab3a5887dabab17a7594ad1e81001282dbd4fbf0fcf1798ea9232
MD5 b089fd2caedc0e5c602ff57926c09610
BLAKE2b-256 a9dbf5daa2fd472913829c70ede3f3f5f5a489a54aab5132b07e34eff1a3b0ed

See more details on using hashes here.

Provenance

The following attestation bundles were made for pyrunir_mcp-0.0.21-py3-none-any.whl:

Publisher: release.yml on planning-and-learning/runir-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page