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,
    find_solution,
    generate_tasks,
)

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

result = find_solution(task, policy)
feedback = history.fold(result.observation)
dump_result(result, "artifacts/find-solution")

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:

find_solution(task_context, policy_or_module_program, classifier=None, universal=False, ...)
prove_termination(domain_context, policy_or_module_program, ...)
prove_classifier(task_context, classifier, ...)

Dumping:

dump_result(result, output_dir, formats=(DumpFormat.JSON,), include_witness=True, include_witness_trace=True, include_plan_trace=True, include_successors=True)
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.

Release files for pyrunir-mcp 0.0.34

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

Source distribution (sdist)

Source distribution for pyrunir-mcp 0.0.34
File	Size	Uploaded
pyrunir_mcp-0.0.34.tar.gz	92.4 kB	Aug 23, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for pyrunir-mcp 0.0.34
File	Interpreter	ABI	Platform	Reset
pyrunir_mcp-0.0.34-py3-none-any.whl 68.7 kB Aug 23, 2026	Python 3	none	any	Details

Total release size: 161.2 kB

Release files / pyrunir_mcp-0.0.34.tar.gz

Download URL	pyrunir_mcp-0.0.34.tar.gz
Size	92.4 kB
Tags	Source
SHA-256 checksum How to use checksums	`4dacd84a16bf0fd118bfef4858730ab29a6bd793d03785d0de191c9547e7c19b`
BLAKE2b-256 checksum How to use checksums	`c07128ebcd4c4a529379917e893c8f1ddc43c3e0092e2cf8800d5a62147c0d7f`
Upload date	Aug 23, 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/planning-and-learning/runir-mcp
Publishing commit: github.com/planning-and-learning/runir-mcp/tree/118b06ef20386dd7711037f22ecc9ce22d620c91

Workflow

Publishing configuration: github.com/planning-and-learning/runir-mcp/blob/118b06ef20386dd7711037f22ecc9ce22d620c91/.github/workflows/release.yml
Publishing logs: github.com/planning-and-learning/runir-mcp/actions/runs/32639343018/attempts/1

Artifact

Subject: pyrunir_mcp-0.0.34.tar.gz
SHA-256 checksum: 4dacd84a16bf0fd118bfef4858730ab29a6bd793d03785d0de191c9547e7c19b Verifying attestations

Release files / pyrunir_mcp-0.0.34-py3-none-any.whl

Download URL	pyrunir_mcp-0.0.34-py3-none-any.whl
Size	68.7 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`f5cb7ca6fef3b7c9cac24ff347e6a9b61039c763466c55accea8767fda3f4d59`
BLAKE2b-256 checksum How to use checksums	`0f029e64aec4a40d1a420d8e12bfd2ddde607edda680f5b0c33b0620b4c341d0`
Upload date	Aug 23, 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/planning-and-learning/runir-mcp
Publishing commit: github.com/planning-and-learning/runir-mcp/tree/118b06ef20386dd7711037f22ecc9ce22d620c91

Workflow

Publishing configuration: github.com/planning-and-learning/runir-mcp/blob/118b06ef20386dd7711037f22ecc9ce22d620c91/.github/workflows/release.yml
Publishing logs: github.com/planning-and-learning/runir-mcp/actions/runs/32639343018/attempts/1

Artifact

Subject: pyrunir_mcp-0.0.34-py3-none-any.whl
SHA-256 checksum: f5cb7ca6fef3b7c9cac24ff347e6a9b61039c763466c55accea8767fda3f4d59 Verifying attestations