feat(core): add SkillContext and named skill chains (#330) - #332
Merged
Conversation
Add SkillContext for multi-skill registry host context (discovery filters, brief/directives modes, progressive prepare/execute, provider tool adapters). Add chains: YAML config, run_chain() with step when: skip, and skillware context/chain CLI. Docs and tests close ARPAHLS#297: skill_chaining.md, agent_loops ripple, README link, integration and host-simulation stress suite.
Add sanitize_input_chain_demo.py and skill_context_gemini_loop.py; refactor ollama_skills_test.py to use SkillContext. Cross-link skill pages and agent_loops; extend example smoke tests. Fix black/flake8 on host_simulation_report.py.
Ripple skill_chaining, ollama, introduction, cli; one-line chain links on middleware catalog pages.
Contributor
Author
|
Follow-up commits on top of the initial feature landing:
No further core API changes after the first commit, additive docs, examples, and CI hygiene only. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Adds SkillContext for multi-skill agent hosts and named skill chains for repeatable middleware pipelines — closing the gap where every host had to hand-roll discovery, brief assembly, tool wiring, and sequential
execute()loops.Closes #330 · Closes #297
SkillContext— filters, modes,prepare()/execute(), provider toolsskillware/context.pychains:YAML,run_chain(), stepwhen:skipskillware/chains.py,skillware/core/chains_config.pychains: { default: [] }safe)skillware/core/config.pyskillware context/skillware chainCLIskillware/cli.py,docs/usage/cli.mddocs/usage/skill_chaining.mddocs/usage/agent_loops.md,README.mdtests/test_skill_context.py,tests/test_chains*.py,tests/test_context_and_chains_integration.py,tests/test_host_simulation_stress.pyStrictly additive —
SkillLoader.load_skill()and existing CLI commands unchanged unless callers opt in.Type of Change
SkillContext, chains runner, config parsingcontext show,chain list|show|validate|run|dry-runskill_chaining.md, agent loops, README, CHANGELOGChecklist (all PRs)
pytest tests/pass locally (363 passed, 4 skipped)CHANGELOG.mdupdated under[Unreleased]examples/README.md— N/A (no new example scripts)pytest tests/test_registry_docs.py— N/A (no skill catalog matrix changes)New or updated skill
N/A — framework and docs only.
Related Issues
Closes #330
Closes #297