agentic-context-engine releases

This is the merger of two release lines that had not yet shipped to PyPI: the 0.11.0 architectural rewrite and the 0.12.0 SkillManager hardening. Skipping a separate v0.11.0 tag — v0.12.0 supersets it.

0.11.0 — Architectural rewrite

• RecursiveAgent core abstraction extracted from RR (ace/core/recursive_agent.py). Generic recursive PydanticAI agent with sandbox, microcompaction, default tool set, depth-aware sub-agent registration.
• RR collapsed into a single RRStep. Orchestrator/worker split, batch machinery, and AttachInsightSourcesStep removed. RR is now a true recursive loop.
• Skillbook v2 — full schema rewrite, section-grouped storage (context / harness), richer InsightSource provenance, BM25-backed retrieval (rank-bm25 runtime dep). Skillbook.as_prompt() now returns markdown; python-toon dropped.
• Agentic SkillManager (first cut) — tool-calling loop (ace/implementations/sm_tools.py) with atomic mutation tools (add_skill, update_skill, remove_skill, tag_skill) and read-only tools (search_skills, read_skill).
• Reflector skillbook tools — Reflector can introspect / propose updates from inside the recursive loop.
• Anthropic prompt caching enabled by default for RR; cache_read_tokens / cache_write_tokens forwarded in run metadata.
• Logfire spans around recursive agent sessions.
• Online / offline mode in the ACE runner.
• record_observation renamed to think.

0.12.0 — SM hardening

• Cross-trace generalization gate (four-criterion: ≥3 instances across ≥2 domains, named slot, no API-specific params in action, verifiable runtime trigger). Backed by skill_generalization.md (14 cited sources).
• Action-equivalence rule — splits on action, not trigger surface.
• Atomicity rule for insight — one trigger + one action; explicit good/bad shape examples.
• ICL-grounded insight format drawn from icl_skill_formatting.md: 15-50 word cap, imperative voice, positive framing default.
• Evidence-only tagging — SM no longer iterates injected_skill_ids; tags only skills the reflection actually implicates.
• Broaden-via-comparison for UPDATE — same root cause in different niches → broaden issue, don't duplicate.
• Prompt caching for SM via CachePoint(ttl="5m"), mirroring RR.
• Hard removal cap removed — harmful_count >= 3 no longer auto-REMOVES skills.
• update_skills signature: source is optional; SkillbookView dropped from parameters.
• Skillbook v1 legacy aliases removed — v2 is the only schema.

End-to-end retail result (Haiku 4.5)

| Metric | Value |
|---|---|
| Baseline pass@1 | 45.0% |
| With learned skillbook | 67.5% |
| Δ pass@1 | +22.5 pp (12 improved, 3 regressed) |
| Skillbook size | 35 skills |

Tau-bench fix

evaluation_type=ALL_WITH_NL_ASSERTIONS on both run_task and run_tasks call sites in ace-eval/src/ace_eval/e2e/benchmarks/tau_bench.py. Retail and any future benchmark with NL_ASSERTION in reward_basis now produces real reward numbers instead of crashing in reward computation.

See CHANGELOG.md for full details.

Initial release of the OpenClaw tracing plugin.

Registers as an OpenClaw plugin (`kayba-tracing`) and ships one structured Kayba trace per agent turn — user message, full LLM input/output with thinking, tool calls, final reply — with sessionId, userId, request/response previews, and folder tagging. No client SDK changes required.

Capture knobs (`plugins.entries.kayba-tracing.config`):

• `captureSystemPrompt`: capture system prompt once per session (default: true)
• `captureHistory`: `delta` (default, per-session cursor — eliminates N² bloat) | `full` | `none`
• `maxAttributeBytes`: per-attribute truncation (default: 64 KiB)

Recursively unwraps OpenClaw's pre-stringified `content` fields so the trace dashboard renders clean JSON instead of multi-level escaped strings.

See `sdk/openclaw/README.md` for setup.

TypeScript SDK release. (No changes to ace-framework or kayba-tracing Python in this release.)

Added

• kayba.setSession(id) / getSession() — auto-injects mlflow.trace.session metadata on every subsequent trace, so multiple traces produced by the same agent run can be filtered together in the dashboard.
• kayba.setUser(id) / getUser() — auto-injects mlflow.trace.user metadata for per-user attribution.
• kayba.updateTrace({ tags, metadata }) — escape hatch for attaching per-call values (e.g. tool call ids) to the active trace.

Changed

• Internal injectFolderTag renamed to injectKaybaContext; folder, session, and user are now emitted in a single updateCurrentTrace call.
• package-lock.json corrected (was stuck on a stale @kayba/[email protected] lockfile name with stray openai/dotenv deps).

Back-compat

Additive only — existing callers using configure, trace, startSpan, setFolder are unchanged.

Added

• Usage metering hook — RecursiveConfig.usage_callback: (RequestUsage, model_id) -> None fires once per pydantic-ai model request (orchestrator turns, sub-agent runs, tool-call follow-ups). Implemented via ace.rr.MeteredModel, a pydantic_ai.models.wrapper.WrapperModel subclass, so metering lives at the framework's own model boundary — one firing site, no per-call-site plumbing. Callback exceptions are caught and logged so metering never crashes the pipeline.
• Pre-built model instance support — RRStep, create_rr_agent, create_sub_agent, and RecursiveConfig.subagent_model now accept either a model-id string or a pre-built pydantic_ai.models.Model instance. Enables callers that need a custom provider (e.g. a Bedrock model carrying STS-assumed credentials) to inject a fully-configured model rather than resolving from a string.
• Sub-agent model_settings — create_sub_agent now threads an explicit ModelSettings parameter into its PydanticAgent constructor.

Back-compat

Existing RRStep(model="...") callers are unchanged. The widened type signatures are additive.

TypeScript SDK

What's new

• TypeScript tracing SDK (@kayba_ai/tracing) — instrument Node.js agents and send traces to Kayba, mirroring the Python SDK API
• Standalone Python tracing package (kayba-tracing) — can be installed independently without the full ace-framework
• ace.tracing continues to work as before (re-exports from kayba-tracing)
• CI publishes all three packages (ace-framework, kayba-tracing, @kayba_ai/tracing) on release

• Kayba tracing SDK — ace.tracing module wraps MLflow tracing with Kayba-native configuration, folder organization, and input sanitization (pip install ace-framework[tracing])

Full Changelog: https://github.com/kayba-ai/agentic-context-engine/compare/v0.9.3...v0.9.4

• Structured design docs — split ACE_DESIGN.md into architecture, reference, and decisions docs under docs/design/
• Simplified Skill model — removed unused tag counters (helpful/harmful/neutral) and TagStep from the pipeline
• Cleaner InsightSource provenance — restored error_identification and learning_text fields

Full Changelog: https://github.com/kayba-ai/agentic-context-engine/compare/v0.9.2...v0.9.3

What's changed

Added

• Insight source provenance — InsightSource typed model captures the origin of each skillbook update (trace ID, sample question, epoch/step, reflection summary, integration metadata); AttachInsightSourcesStep automatically enriches UpdateBatch operations with provenance and is wired into the default learning tail
• Claude SDK step — ClaudeSDKStep integration for running Claude Code sub-agents from within ACE pipelines
• RR sub-agent code execution — Recursive Reflector can now delegate to code-execution sub-agents at runtime
• RR raw trace batch helpers — build_raw_trace_batches and related runtime utilities for feeding raw traces directly into the RR pipeline

Fixed

• Logfire scrubbing — added scrubbing callback to stop Logfire over-redacting trace content (reasoning, answers, messages now visible in Logfire UI)
• RR combined-batch normalization — fixed ordering/deduplication of combined task batches in multi-sample runs

Docs

• Logfire query API guide clarifications
• MCP client setup guide and compatibility tests
• Design docs updated to reflect insight source provenance model

Full changelog: https://github.com/kayba-ai/agentic-context-engine/blob/main/CHANGELOG.md

Fixed

• CLI packaging — include .md data files in wheel so kayba setup and skill install work on pip/uv-installed packages

Full Changelog: https://github.com/kayba-ai/agentic-context-engine/compare/v0.9.0...v0.9.1

Added

• PydanticAI migration — ACE roles (Agent, Reflector, SkillManager) rebuilt on PydanticAI agents with structured output, replacing the legacy role system
• Recursive Reflector — PydanticAI-powered trace analysis agent with sandboxed code execution, sub-agent delegation, and working memory (save_notes tool)
• Kayba CLI — full hosted API client with trace upload/management, interactive run, insights, prompts, batch processing, materialization, and integration commands (kayba entry point)

Full Changelog: https://github.com/kayba-ai/agentic-context-engine/compare/v0.8.9...v0.9.0

Thread CancellationToken through TraceAnalyser.run() for pipeline cancellation support.

Introducing the Kayba CLI: automated agent self-improvement from your terminal

We built a CLI that plugs into Claude Code, Codex, or any coding agent and turns your agent's execution traces into improvements.

Upload traces → Kayba surfaces failure patterns → your coding agent proposes edits to your codebase. Pick what makes sense, implement, and repeat.

First test on tau2-bench: 34.3% improvement after a single cycle auto-accepting all changes.

🚀 Try it free

7-day free trial (no credit card required) at kayba.ai:

• Automated agent self-improvement
• CLI for Claude Code, Codex & more
• Hosted dashboard & analytics
• Team collaboration

The core engine (ACE) stays open source and MIT licensed. Run kayba setup to get started.

Added

• Pipeline hooks & cancellation — PipelineHook protocol and CancellationToken for observing and controlling pipeline execution
• Kayba pipeline skills for Claude Code — 7-stage dynamic evaluation pipeline that generates custom benchmarks tailored to your agent's domain. Instead of static test suites, the skills analyze your API, build domain-aware metrics and rubrics, create action plans, and run human-in-the-loop validation — all as composable Claude Code skills
• kayba setup command — one command to install the full evaluation skill pipeline into your .claude/skills/ directory, ready to use inside Claude Code out of the box

Full Changelog: https://github.com/kayba-ai/agentic-context-engine/compare/v0.8.7...v0.8.8

• Improved Opik trace naming — traces now display the question text (first 80 chars) instead of generic names like "ace_pipeline" or "rr_reflect"
• Thread ID support for Opik — OpikStep and RROpikStep accept an optional thread_id parameter for grouping related traces

Full Changelog: https://github.com/kayba-ai/agentic-context-engine/compare/v0.8.6...v0.8.7

What's New

• Kayba CLI — New kayba CLI for the hosted API with commands: upload, insights generate/list/triage, prompts generate/list/pull, status, materialize, batch, setup
• HTTP client — KaybaClient with Bearer auth for the Kayba hosted API
• Agent integration — kayba setup prints/appends coding agent instructions (CLAUDE.md, AGENTS.md, .cursorrules)

Full Changelog

https://github.com/kayba-ai/agentic-context-engine/compare/v0.8.5...v0.8.6

• Self-contained RR module (ace_next/rr/) — sandbox, subagent, trace_context, config extracted from ace/reflector/
• v5.6 prompt promoted as default — prompt evolution (v4 → v5.1–v5.6) for the RR pipeline
• build_steps() API — all runners gain a build_steps() classmethod for pipeline customization
• Shared CallBudget — single budget instance shared across RR pipeline steps
• ACE MCP server (optional) — stdio MCP server with tools: ace.ask, ace.learn.sample, ace.learn.feedback, ace.skillbook.get/save/load
• MCP packaging + CLI — optional mcp extra and ace-mcp entrypoint
• Composing pipelines guide — new docs/guides/composing-pipelines.md
• RR examples — rr_demo.py, rr_opik_demo.py, compose_custom_pipeline.py
• Opik made opt-in — moved from hard dependency to observability extra

Full Changelog: https://github.com/kayba-ai/agentic-context-engine/compare/v0.8.4...v0.8.5

What's New

• OpenClaw integration — learn from OpenClaw session transcripts (JSONL) via new OpenClawToTraceStep and LoadTracesStep pipeline steps (#86)
• ExportSkillbookMarkdownStep — export skillbook to markdown file
• OpenClaw example script and integration docs

• Pipeline engine — generic pipeline framework with branching, async boundaries, and parallel execution (#78)
• Trace passthrough — _build_traces() helper and raw trace data passed to RecursiveReflector sandbox

Full Changelog: https://github.com/kayba-ai/agentic-context-engine/compare/v0.8.2...v0.8.3

• RecursiveReflector None-response guard — gracefully handles empty/None LLM responses (e.g. from Gemini) with retry prompt instead of crashing
• LiteLLMClient.complete_messages() — native multi-turn completion that preserves structured message lists

Full Changelog: https://github.com/kayba-ai/agentic-context-engine/compare/v0.8.1...v0.8.2

Insight Source Tracing

Track where every skill in your skillbook came from.

Added

• Insight source tracing — InsightSource dataclass tracks skill provenance (epoch, sample, trace refs, error identification, learning text)
• Sample.id promoted to first-class field with UUID auto-generation
• Skillbook query API — source_map(), source_summary(), source_filter() for skill lineage
• Insight sources wired through OfflineACE, OnlineACE, and async learning pipelines
• UpdateOperation.learning_index for linking operations to reflector learnings
• Bedrock e2e example (examples/litellm/bedrock_insight_source_test.py)
• docs/INSIGHT_SOURCES.md guide

Full Changelog: https://github.com/kayba-ai/agentic-context-engine/compare/v0.8.0...v0.8.1

What's New

• TAU-bench integration: Full benchmark framework for evaluating agents on TAU-bench tasks
• Recursive Reflector: New reflector module with sandbox execution, trace context, and sub-agent support
• Skillbook tools: Clean, consolidate, and merge skillbooks via new utility scripts

Full Changelog: https://github.com/kayba-ai/agentic-context-engine/compare/v0.7.0...v0.8.0

Release v0.7.3

What's New

Agentic System Prompting

New workflow to automatically optimize your agent's system prompts using your own data. Feed in past traces or conversations, and ACE analyzes what worked and what failed to generate actionable prompt suggestions.

Traces / Conversations → ACE → Prompt Suggestions

Each suggestion includes the recommended prompt text, justification for why it helps, and evidence from your actual traces. You review and decide what to implement.

See examples/agentic-system-prompting/ for the full workflow.

Other Changes

• Fix: Align test matrix with Python 3.12 requirement
• Fix: Use setup-uv action for Windows CI compatibility