agent-apprenticeship 0.2.0 → 0.2.1

package/README.md

@@ -1,11 +1,17 @@
-The living ecosystem where AI agents learn from real-world work through iterative workflow loops, reusable experience, and collective training signal exchange.
+The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
 
 As agents move into long-horizon, economically valuable work, Agent Apprenticeship creates the open infrastructure where real-world tasks generate reusable learning signals and complex workflows advance through agent loops that turn execution into shared improvement.
 
 Agent Apprenticeship is designed for a compounding exchange of agent work experience: economically valuable task execution generates training signals, those signals improve future work, and future work creates new reusable experience for the ecosystem.
 
-Agent Apprenticeship is built for iterative workflow loops across domains, from simple tasks to complex specialized work. Apprentice agents work with mentor agents or human experts to complete long-horizon, real-world tasks, while each workflow generates reusable learning signals for the ecosystem.
+Agent Apprenticeship is built for iterative workflow loops across domains, from simple tasks to complex specialized work. Apprentice agents work with mentor agents, users, or human experts to complete real-world tasks, while each workflow generates reusable learning signals for the ecosystem.
 
-Agent Apprenticeship is now available for anyone to start using with local agents including Codex, Cursor, Claude Code, OpenClaw, OpenCode, Hermes Agent, and custom agents, alongside different model providers. Users can run automated agent workflow loops locally, contribute agent learning signals back to the ecosystem, and use shared ecosystem signals to improve their own agents.
+Agent Apprenticeship is now available for anyone to start using with local agents, including Codex, Cursor, Claude Code, OpenClaw, OpenCode, Hermes Agent, and custom agents, alongside different model providers. Users can run automated agent workflow loops locally, contribute agent learning signals back to the ecosystem, and use shared ecosystem signals to improve their own agents.
 
 Agent Apprenticeship is about the future of work and the economic value of agents. For every task executed through Agent Apprenticeship, the system can estimate task-level economic value, especially across specialized domains. It is built for everyday use to improve agent performance and outcome quality, while enabling users to exchange agent work experience with each other and with domain-expert-led agents in one living ecosystem.
+
+## Quick Start
+
+```bash
+npx agent-apprenticeship init
+```

package/docs/dataset_schema.md

@@ -33,7 +33,7 @@ Typical local package content:
 - `grading/`, `feedback/`, and `signals/`
 - `mentor_checkpoints/` when expert or organization workflows record checkpoints
 - `experience_compiler/`
-- optional legacy `tdo/` compatibility outputs
+- optional legacy compiler compatibility outputs
 
 `actual_outputs.json` remains the canonical output contract. Final/static outputs are represented by actual outputs, deliverable refs, artifact refs, and copied files rather than large top-level trace fields.
 

package/docs/v0.2_release_notes.md

@@ -1,6 +1,6 @@
-# Agent Apprenticeship v0.2.0 Technical Release Notes
+# Agent Apprenticeship v0.2.1 Technical Release Notes
 
-Agent Apprenticeship v0.2.0 expands the Experience Compilation system from Runtime Training reuse into a fuller package for agent training, evaluation, replay, verifier/reward work, and provenance audit.
+Agent Apprenticeship v0.2.1 includes the v0.2 Experience Compilation system plus a small npm-package polish patch for the public README intro, first-run npm runtime setup, and installed Runtime Training metadata.
 
 ## Core Product Changes
 
@@ -10,6 +10,8 @@ Agent Apprenticeship v0.2.0 expands the Experience Compilation system from Runti
 - Ecosystem consumption is centered on two actions: Export Full Experience Compilation and Install Runtime Training.
 - Runtime Training install/use records installed skill refs, selected Runtime Training refs, confidence metadata, injected sections, and compact contract-focused context.
 - `apprentice bundle check` accepts local Experience Compilation folders that use task/package/compiler manifests, including regenerated seed task packages.
+- v0.2.1 adds a first-run npm runtime setup lock so concurrent CLI invocations share one Python runtime bootstrap safely.
+- v0.2.1 records `package_version` and `runtime_training_confidence` in installed Runtime Training metadata.
 
 ## Experience Compiler And Training Packages
 
@@ -55,7 +57,7 @@ Use the wording “505 Experience Compilations plus 39,835 normalized Data Viewe
 
 ## Release Boundary
 
-- The package version is 0.2.0 for release-candidate builds.
-- The regenerated Seed Dataset v0.2 was generated before npm v0.2.0 publication and records the local package metadata present at generation time.
+- The package version is 0.2.1 for this npm patch release candidate.
+- The regenerated Seed Dataset v0.2 records the local package/compiler metadata used for its generation and later metadata restamp.
 - No model weights are included.
 - No official ALE benchmark score is claimed for the mirrored transfer tasks.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-apprenticeship",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "description": "The living ecosystem for AI agents learning from real-world work through iterative loops and training-signal exchange.",
   "license": "MIT",
   "repository": {

package/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agent-apprenticeship"
-version = "0.2.0"
+version = "0.2.1"
 description = "Open framework for turning real agent work into transferable agent experience"
 readme = "README.md"
 requires-python = ">=3.11"

package/src/agent_apprenticeship_trace/__init__.py

@@ -1,2 +1,2 @@
 """Agent Apprenticeship framework."""
-__version__ = "0.2.0"
+__version__ = "0.2.1"

package/src/agent_apprenticeship_trace/config.py

@@ -584,7 +584,7 @@ def update_settings(**updates: Any) -> Settings:
     if updated.data_sharing_level not in DATA_SHARING_LEVELS:
         raise ValueError(f"Unsupported Sensitive Info Masking setting: {updated.sensitive_info_masking}")
     if updated.mentor_mode not in MENTOR_MODES:
-        raise ValueError(f"Unsupported mentor mode: {updated.mentor_mode}")
+        raise ValueError(f"Unsupported legacy apprenticeship mode setting: {updated.mentor_mode}")
     if updated.apprenticeship_mode not in APPRENTICESHIP_MODES:
         raise ValueError(f"Unsupported Apprenticeship Mode: {updated.apprenticeship_mode}")
     if updated.sensitive_info_masking not in SENSITIVE_INFO_MASKING_LEVELS:

package/src/agent_apprenticeship_trace/mentor_checkpoints.py

@@ -375,7 +375,7 @@ def write_mentor_checkpoints(
         )
     (root / "README.md").write_text(
         "# Mentor Checkpoints\n\n"
-        "These files record expert-led or hybrid human audit checkpoints for the apprenticeship session. "
+        "These files record Expert-Led or Organization Custom audit checkpoints for the apprenticeship session. "
         "They are local audit artifacts and do not contain raw provider secrets.\n"
     )
     _mark_source_artifact_audited(pkg, source=source, mode=mode, input_source=input_source, stages=enabled_stages)