Repository navigation
Add declarative hive language and guarded self-edits - #120
Merged
Merged
Conversation
Co-authored-by: Medulla <medulla@tinyhumans.ai>
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
Tiny Sweeper review
|
|
Warning Review limit reached
This review includes 104 billable files and costs up to $26.00. View limit details
Comment |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add
tinyhivemind-lang, a pure typed hive package format with JSON manifests and Markdown side files. It validates and lowers hive structure, goals, policies, capabilities and memory bindings, supports guarded edits, and records content-addressed evaluated lineage with a Pareto frontier. Hosts retain storage, evaluation, memory contents and activation authority.Includes DeepSWE and PE1006 packages, a SWE-compatible run-memory regression, and a deterministic self-edit example demonstrating accepted and rejected proposals.
Related issue
Closes #112
API or behavior changes
ManagementRequest::CreateAgentadds optional boxed memory metadata. Existing JSON remains compatible; Rust constructors must supplymemory: Nonewhen unbound.AgentFactory::create_with_memorypreserves existing unbound factories. Bound factories must install and enforce the complete memory contract before registration; unsupported bindings are refused.inherit: trueis refused because the current engine also includes global-root memory; explicit bounded ancestor reaches remain available.Validation
All passed:
cargo fmt --all -- --checkcargo clippy --all-targets --all-features -- -D warningscargo build --all-targets --all-featurescargo test --all-features.github/scripts/assert-pure.shRUSTDOCFLAGS="-D warnings" cargo doc --no-deps --all-featurescargo llvm-cov -p tinyhivemind-lang --json --output-path target/hive-language-coverage.json— every reported language implementation file exceeds 90% line coverage (minimum 92.86%).cargo run -p tinyhivemind-lang --example self_editgit diff --checkTests
Wire representations, validation failures, parse/lower and diff/apply, atomic patch guards, protected evaluator/telemetry fields, canaries, read-only and bounded memory, share/reassign/fork, persistent memory watermarks, archive verification and Pareto selection are covered. Regression cases include unknown nested policy fields, implicit root-memory inheritance, purpose-directory escapes, long goal chains, and uppercase Markdown extensions. Adapter tests verify memory installation and backward-compatible decoding.
External evaluation and memory-store transactions remain host ports; the pure crate does not open stores or execute models. Hosts must implement pinned reads or forks for reproducible persistent-memory evaluation.
Documentation
Checklist
#[allow(...)],#[ignore], or relaxed lints.envcontents in the diff or the description