Added
Stable tool-contract APIs
The released tool surface supports copied schema normalization, deterministic canonical JSON, SHA-256 fingerprints, exact contract checks, and safe catalog optimization.
Changes with consequences.
LLMSlim releases document what shipped, what changed, and where the boundary remains. Phase 2 is an engineering and benchmark milestone—not an invented package version.
Python releasev0.4.021 Aug 2026Released
Contract-safe tool context.
This Python release adds stable, conservative tool-schema infrastructure while keeping retrieval and selective exposure research-only.
489 / 0 tests90.93% coverage375 schemas / 18 catalogs
View verified source ↗Boundary
Retrieval remains research-only
Lexical, dense, hybrid retrieval, selective exposure, and lazy hydration are explicit experiments. They do not authorize or execute tools, and compress() keeps its established behavior.
Measured
Schema-tax evidence stays transparent
The v0.4.0 release gate records 489 passing tests, 90.93% coverage, and 375 generated tool schemas in 18 catalogs. The compact baseline produced 0.00% lossless reduction.
Python releasev0.3.113 Aug 2026Released
Provenance and verification.
This security-focused Python release strengthens caller-declared trust boundaries and makes token-counter provenance visible in the public result.
432 / 0 tests92.57% coverageRuff passed
View verified source ↗Security
Provenance-aware priority locking
ContextRole distinguishes system, developer, user, assistant, tool, RAG, and general content. Untrusted RAG, tool, and assistant text cannot become hard-locked priority from imperative wording, safety patterns, or preserve patterns.
Security
Nonce-protected rewrite template fences
User text containing a template-fence-like delimiter remains byte-for-byte unchanged while the template uses a content-preserving nonce fence, preventing fence breakout.
Added
Context roles and token-counter telemetry
The public Python API exports ContextRole and records token_counter_used so callers can distinguish tiktoken from the documented heuristic fallback.
Fixed
Inline code and CJK sentence boundaries
Inline backtick code spans no longer create false sentence boundaries, and the CJK ideographic stops 。, ！, and ？ are recognized by the sentence-splitting paths.
Changed
Pipelines preserve provenance
Document compression defaults retrieved context to RAG, while chat compression propagates supplied system, developer, user, assistant, and tool roles instead of flattening them.
Fixed
Benchmark collection reports real pytest results
The release runner collects actual pass/fail reports rather than replaying stale tuples. The checked-in release record reports 432 passing tests, zero failures, 92.57% branch coverage, and Ruff passing.
Python releasev0.3.018 Jul 2026Released
Hybrid prompt optimization.
v0.3.0 expanded the package from its offline extractive default into an extensible rewrite and hybrid framework without bundling an LLM provider.
Extractive defaultProvider abstractionValidation pipeline
View verified source ↗Added
Rewrite and hybrid strategies
compress() gained extractive, rewrite, and hybrid strategies. Rewrite-capable paths require a caller-supplied provider; the default extractive path remains offline and deterministic.
Added
Provider and validation contracts
BaseRewriteProvider, CallableProvider, RewriteRequest, RewriteMetadata, versioned templates, and structural, instruction, entity, and similarity validation were added as public building blocks.
Changed
Rewrite work moved into a focused sub-package
Prompt construction, execution, and validation were separated into llmslim.rewrite modules, with strategy benchmarking and a CLI strategy flag added alongside them.
Python releasev0.2.013 Jul 2026Released
High-performance semantic compression.
v0.2.0 deepened the original extractive engine with instruction and entity protection, chunking improvements, cost tooling, and a fuller command-line and benchmark surface.
Instruction retentionEntity preservationCLI + benchmarks
View verified source ↗Added
Instruction and entity retention
The release added explicit instruction prioritization plus regex and heuristic preservation for names, dates, financial metrics, technical identifiers, and URLs.
Added
Chunking, embeddings, and cost tooling
It introduced semantic and hybrid chunking, optional sentence-transformers support, model cost estimation, an interactive/file-based CLI, and comprehensive benchmark tooling.
Changed
Richer ranking and result telemetry
TF-IDF plus PageRank-style sentence centrality, optional tiktoken accounting, and a standardized CompressionResult with detailed telemetry became part of the release.
Python releasev0.1.016 Jun 2026Released
Initial public release.
The first LLMSlim release established the installable Python package and its simple offline compression entry point.
Python 3.8+TF-IDF rankingPublic compress() API
View verified source ↗Added
Installable LLMSlim package
v0.1.0 published the llmslim package for Python 3.8+ with the public compress(), ContextCompressor, CompressionResult, token, pipeline, and cost utility exports.
Added
Offline prompt compression foundation
The initial engine provided ratio-driven prompt compression using TF-IDF sentence scoring and thresholding, with optional semantic, fast-token, and NLTK extras.
Important: LLMSlim mitigates compression-induced instruction elevation. It does not claim to solve prompt injection completely, authenticate caller-provided roles, or ship an npm, Rust, or WASM runtime.