v0.2.0

What's Changed

Breaking Changes

• ContextPolicy.ttl_behavior removed (#65) - the field was never read by any pipeline stage. Remove it from any ContextPolicy(ttl_behavior=...) calls. No behaviour changes; the field had no effect in prior releases.
• InMemoryEventLog.append() now raises DuplicateItemError instead of bare ValueError - callers catching ValueError must migrate to DuplicateItemError or ContextWeaverError (#64)
• InMemoryArtifactStore.drilldown() now raises ContextWeaverError instead of bare ValueError (#64)

Added

• StoreBundle.from_dict() and InMemoryArtifactStore.from_dict() - full round-trip serialization (#66)
• DuplicateItemError(ContextWeaverError) - exported from top-level package (#64)
• Named configuration presets ("fast", "balanced", "accurate") via ProfileConfig and RoutingConfig (#133)
• FastMCP Catalog bridge adapter in �dapters/fastmcp.py - astmcp_tool_to_selectable(), astmcp_tools_to_catalog(), load_fastmcp_catalog(), infer_fastmcp_namespace() (#114). Install: pip install contextweaver[fastmcp]
• End-to-end four-phase runtime loop example (examples/full_agent_loop.py) and guide (docs/guide_agent_loop.md) (#24)
• LangChain memory replacement example (examples/langchain_memory_demo.py) (#170)
• Benchmark harness for routing and context pipeline - make benchmark (#119)
• docs/troubleshooting.md - 10 common issues, debugging techniques, 12-entry FAQ (#82)
• SECURITY.md - vulnerability disclosure policy
• llms.txt / llms-full.txt - structured docs index and full-text bundle for AI tools
• Auto-generated API reference site via MkDocs + mkdocstrings - make docs (#110)
• make test now includes branch coverage report (#165)
• CI pip dependency caching (#94)
• Reusable agent prompt workflows in .github/prompts/ (#96)

Fixed

• _strip_namespace_prefix() now handles dot- and slash-delimited FastMCP names (#177)
• astmcp_tool_to_selectable() normalizes set/rozenset/ uple metadata values to lists (#177)
• All runnable snippets in docs/troubleshooting.md corrected to match actual APIs
• Example output markers normalized to ASCII for Windows cp1252 compatibility

Full changelog: https://github.com/dgenio/contextweaver/blob/main/CHANGELOG.md

v0.1.7

What's Changed

• docs: rewrite README with compelling problem → solution narrative by @Copilot in #149
• docs: add 10-minute quickstart guide with 3 runnable examples by @dgenio in #150

Full Changelog: v0.1.6...v0.1.7

v0.1.6 — Logging Integration

What's New

Logging Integration (#111)

• Python logging integration with structured events across all subsystems
  • Loggers: contextweaver.context, contextweaver.routing, contextweaver.store, contextweaver.adapters
  • DEBUG-level messages at each context pipeline stage (candidate generation, scoring, dedup, selection, firewall, sensitivity)
  • INFO-level summary messages for context builds and route completions
  • Sensitivity guard: item text content is never logged at any level

Developer Tooling (#95)

• Path-scoped Copilot instructions for context/ and routing/

Full Changelog: v0.1.5...v0.1.6

v0.1.5 — MCP Structured Content & Output Schema

[0.1.5] - 2026-03-07

Added

• MCP structured content (structuredContent) support — JSON output stored as artifact with facts extracted from top-level keys
• MCP outputSchema support for tool definitions; SelectableItem now includes output_schema field (#102)
• MCP content types: audio (base64-decoded binary artifact) and resource_link (URI reference as ArtifactRef)
• Per-part content annotations (audience, priority) tracked in provenance["content_annotations"]
• PR template and YAML issue forms (.github/)

Fixed

• Use text/uri-list MIME for resource_link binaries payload
• Use validate=True for base64 decoding in image and audio parts
• Add isinstance guard for structuredContent fact extraction and per-part annotations
• Use is not None for output_schema checks to preserve empty dict schemas
• Set resource_link size_bytes to actual URI length
• Widen structured_content annotation to Any for MCP spec compliance

Changed

• Extracted _decode_binary_part helper for image/audio binary decoding

v0.1.4 — Pluggable Summarizer & Extractor protocols

What's New

Added

• Summarizer protocol in protocols.py — converts raw tool output into human/LLM-readable summaries
• Extractor protocol in protocols.py — extracts structured facts from raw tool output
• Pluggable summarizer and extractor parameters on apply_firewall() and apply_firewall_sync()
• ContextManager now accepts optional summarizer and extractor at construction, wired through build() / build_sync()

Fixed

• infer_namespace() now guards against empty prefixes caused by leading separators (e.g. .foo or /bar)

Full Changelog: v0.1.3...v0.1.4

v0.1.3 — Progressive disclosure for tool results

What's new

This release connects the existing progressive disclosure building blocks (ViewSpec, ArtifactStore.drilldown(), ResultEnvelope.views) into a complete agent-facing workflow. Agents can now receive structured view options for tool results and drill down into specific slices incrementally.

Added

• ViewRegistry class in context/views.py — maps content-type patterns to ViewSpec generators
• Built-in view generators for application/json, text/csv, text/plain, and binary/image content
• generate_views() function for auto-generating ViewSpec entries from artifact data
• drilldown_tool_spec() helper — generates a SelectableItem exposing drilldown as an agent-callable tool
• ContextManager.drilldown() / drilldown_sync() — agent-facing wrapper for ArtifactStore.drilldown() with optional context injection
• ContextManager.view_registry property for accessing/extending the view registry
• Auto-generated ViewSpec entries during ingest_tool_result() (both large and small outputs)
• Auto-generated ViewSpec entries during apply_firewall() via view registry
• Content-type detection heuristics for generic application/octet-stream artifacts
• Small tool outputs now stored in artifact store with artifact_ref for drilldown support

How it works

ingest_tool_result(data)
  → apply_firewall(data) → artifact_store.put() → ArtifactRef
  → view_registry.generate_views(ref, data) → list[ViewSpec]
  → attach views to ResultEnvelope
  → agent sees: summary + available views

agent calls: drilldown(handle, selector)
  → artifact_store.drilldown() → slice text
  → optionally inject into context as ContextItem

Test coverage

• 32 new view tests + 13 new manager drilldown/auto-view tests
• 480 tests total, all passing
• Full CI green: ruff format, ruff check, mypy, pytest

Closes #17

Full changelog: v0.1.2...v0.1.3

v0.1.2 - Development Workflow Improvements

Added

• Sensitivity enforcement in context pipeline: items at or above ContextPolicy.sensitivity_floor are dropped or redacted
• ContextItem.sensitivity field (default: Sensitivity.public)
• ContextPolicy.sensitivity_action field ("drop" or "redact")
• MaskRedactionHook — built-in redaction hook replacing text with [REDACTED: {sensitivity}]
• apply_sensitivity_filter() function in context/sensitivity.py
• register_redaction_hook() for user-extensible redaction hooks
• BuildStats.dropped_reasons["sensitivity"] tracks sensitivity-dropped item count
• .pre-commit-config.yaml with ruff format, ruff check --fix, and standard file hygiene hooks

Fixed

• Validate sensitivity_action to reject unknown values
• Use accumulation pattern for dropped_reasons["sensitivity"]
• Adjust total_candidates for sensitivity drops in BuildStats

v0.1.1

[0.1.1] - 2026-03-03

Added

• Catalog.hydrate(tool_id) returns a HydrationResult with full schema, examples, and constraints
• HydrationResult dataclass in envelope.py with to_dict() / from_dict()
• ContextManager.build_call_prompt() / build_call_prompt_sync() for Phase.call prompts with schema injection
• SelectableItem.examples and SelectableItem.constraints fields
• ContextManager.ingest_mcp_result() / ingest_mcp_result_sync() for one-call MCP result ingestion with artifact persistence

Changed

• Breaking: mcp_result_to_envelope() now returns (ResultEnvelope, dict, str) tuple — envelope, extracted binary data, and full untruncated text

v0.1.0

[0.1.0] - 2026-03-03

Added

• Full CLI implementation: all 7 subcommands (demo, build, route, print-tree, init, ingest, replay) with real handlers
• MCP adapter: mcp_tool_to_selectable, mcp_result_to_envelope, load_mcp_session_jsonl
• A2A adapter: a2a_agent_to_selectable, a2a_result_to_envelope, load_a2a_session_jsonl
• Sample JSONL session files: mcp_session.jsonl, a2a_session.jsonl
• before_after.py showpiece: side-by-side token comparison WITHOUT vs WITH contextweaver
• Comprehensive test_cli.py: subprocess tests for all 7 CLI commands
• Expanded conftest.py: store_bundle, sample_context_items, sample_selectable_items, large_catalog, sample_graph, context_manager, populated_manager fixtures
• Documentation: architecture.md, concepts.md, integration_mcp.md, integration_a2a.md
• Full README.md with installation, quick start, routing, CLI, examples, and development sections

Changed

• Version bumped to 0.1.0
• Makefile ci target now includes example and demo
• Example scripts updated: mcp_adapter_demo.py and a2a_adapter_demo.py now use real adapters

v0.0.4 — Adapters, Context Manager expansion & PR fixes

What's New

Adapters

• MCP adapter (mcp.py): convert MCP tool manifests and JSONL session logs into SelectableItem lists
• A2A adapter (a2a.py): convert A2A agent cards and JSONL session logs into SelectableItem lists
• Shared JSONL loader (_common.py): unified _load_session_jsonl() helper used by both adapters

Context Manager

• StoreBundle constructor for pre-wired stores
• ingest() / ingest_sync() / ingest_async() for event log appends
• ingest_tool_result() with firewall integration for large outputs
• add_fact() / add_episode() for episodic and factual memory stores
• build_route_prompt() integrating Router + ChoiceCards + context pipeline
• Episodic memory and facts injection into prompt header
• budget_tokens override for per-call budget control

Bug Fixes

• Budget bypass (blocker): fact/episodic injection is now pre-built and subtracted from the effective budget; overhead recorded in BuildStats.header_footer_tokens
• Firewall media_type: reads media_type from item metadata instead of hardcoding text/plain
• Unbounded fact injection: capped at 64 lines / 2,000 chars (_MAX_FACT_LINES, _MAX_FACT_CHARS)
• Tag deduplication: merged query_tags and hints now use sorted(set(…))
• JSONL field validation: non-dict rows and field conversion errors wrapped in CatalogError
• Version alignment: pyproject.toml and __init__.py both report 0.0.4

Housekeeping

• Removed 57 accidentally committed tmpclaude-* temp files; added pattern to .gitignore
• Moved inline from typing import Literal to module level in both adapter files
• Restored full Args/Returns docstrings on build() and build_sync()
• Clarified ArtifactRef entries are metadata-only in adapter docstrings

Tests

• 391 tests passing, mypy clean (38 source files), ruff clean
• New tests for adapters, firewall, manager (fact capping, budget accounting, route prompt), envelope