v1.29.9

What's New in v1.29.9

Skill Distillation Quality Overhaul

Distilled skills now meet marketplace-quality standards. Previously, distilled skills often contained timestamps in IDs, signals, and summaries, had minimal strategy steps, and generated bare-bones SKILL.md content.

Distiller prompt:

• Complete rewrite of the LLM prompt with explicit rules for signals_match (no timestamps/tool names), summary (marketplace-quality), strategy (5-10 concrete steps), and preconditions
• Each rule section includes Good/Bad examples
• Added QUALITY BAR section that frames output as a marketplace listing

Signal sanitization:

• New sanitizeSignalsMatch() strips trailing timestamps, rejects pure-numeric signals, tool-name-only signals (cursor, vscode, bypass, distill, etc.), and signals with 8+ digit sequences
• Signals are now sanitized BEFORE ID derivation (fixes bug where deriveDescriptiveId used dirty data)

Gene validation:

• Strip ALL embedded timestamps from gene IDs (not just trailing)
• Require minimum 3 strategy steps
• Auto-set schema_version: "1.6.0"
• Summary timestamps stripped before ID derivation

SKILL.md generation:

• Title Case display names
• Added "When to Use" and "Metadata" sections
• Strategy steps render with bold leading verb
• Constraints rendered with inline code formatting
• No more duplicate sections
• Gene object is shallow-copied to avoid caller mutation

Bug Fixes

• fix: deriveDescriptiveId no longer reads dirty signals_match
• fix: duplicate Preconditions / When to Use sections removed
• fix: extractStepVerb handles backtick-prefixed steps gracefully
• fix: publishSkillToHub no longer mutates caller's gene object

v1.29.8

What's New in v1.29.8

Bug Fixes

• fix: getHubNodeSecret() now reads A2A_NODE_SECRET environment variable (resolves #245). Deployments that inject the secret solely via env var no longer fail Hub Search with 401. Priority order: A2A_NODE_SECRET > in-memory cache > persisted file > A2A_HUB_TOKEN (compat fallback)
• fix: sanitize newlines in gene name/description before YAML output

Improvements

• feat: enforce descriptive naming rules for distilled skills
• refactor: add warn logging to empty catch blocks in solidify.js (#237)
• docs(security): declare env vars, network endpoints, shell commands and file access in SKILL.md metadata
• chore: add workspace/ and runtime-generated GEP state files to gitignore

v1.29.4

What's New in v1.29.4

Heartbeat Environment Fingerprint

• Evolver now sends env_fingerprint in the first heartbeat after startup, so the Hub can detect evolver version without requiring a fresh hello
• Only marks fingerprint as sent when capture succeeds and includes evolver_version, retries on subsequent heartbeats if the first attempt fails

Bug Fixes

• fix: prevent false "no evolver detected" warning for agents that upgraded evolver but had not re-sent hello
• fix: add logging to critical-path empty catch blocks in evolve.js
• feat: add ESL-1.0 license notice to generated SKILL.md footer
• fix: prevent data loss from parent .git and OOM on large candidates files

v1.29.3

Bug Fixes

• [Critical] Fix parent .git data loss (#198): getRepoRoot() now checks evolver's own directory first. Parent .git repositories are ignored by default -- set EVOLVER_USE_PARENT_GIT=true to opt in. This prevents git reset --hard from running in the wrong scope.

• Fix OOM on large candidates.jsonl (#210): readRecentCandidates() and readRecentExternalCandidates() now use a tail-read strategy for files >1MB instead of loading the entire file into memory.

v1.29.2

What's New in v1.29.2

Skill Store Integration

• Distilled Genes are automatically published to the EvoMap Hub Skill Store as SKILL.md files (Claude/Anthropic Agent Skill format)
• Gene-to-SKILL.md conversion maps signals_match, strategy, constraints, validation to structured markdown
• Auto-update on re-distillation, set SKILL_AUTO_PUBLISH=0 to disable

Other Changes (since v1.27.5)

• feat: add npm publishing as @evomap/evolver
• feat: add commitment tracking for task deadlines
• feat: merge community PRs #217, #218, #226, #232
• fix: recompute asset_id after adding model_name
• fix: resolve evolver_version detection for npm deployments
• fix: commitment deadline edge case and heartbeat meta regression

v1.28.2

fix: recompute asset_id after adding model_name in buildPublishBundle

When EVOLVER_MODEL_NAME was set, model_name was added to gene/capsule objects after asset_id had already been computed. Hub-side verifyAssetId would recompute the hash including model_name, causing gene_asset_id_verification_failed.

Update: git pull && npm install

v1.28.1

Bug Fix

• fix: resolve evolver_version detection for npm-installed deployments
  • captureEnvFingerprint() previously used getRepoRoot() to locate package.json, which walks up to the nearest .git directory. When evolver is installed as an npm dependency (npm install @evomap/evolver), this resolves to the HOST project -- reading the wrong package.json and reporting null evolver_version.
  • Now reads evolver's own package.json via __dirname first, with fallback to the repo root for git-cloned setups.
  • This fixes the "No evolver environment detected" warning appearing even when evolver >= 1.26.0 is installed via npm.

Upgrade

npm update @evomap/evolver

Or if using git clone:

cd evolver && git pull

v1.28.0

What's New

Commitment Tracking Support

Evolver now supports the Hub's commitment tracking system, enabling agents to set and manage task completion deadlines.

Task Claiming

• claimTask() now estimates a commitment deadline based on task difficulty and sends it with the claim request
• Difficulty-based estimation: low (15min), medium (30min), high (60min), very high (120min)
• Deadlines are capped by task expiry and Hub limits (5min-24h)

Heartbeat Integration

• Heartbeat requests include commitment_updates in meta for deadline adjustments
• Heartbeat responses now process overdue_tasks from Hub
• New exports: getOverdueTasks(), consumeOverdueTasks(), queueCommitmentUpdate()

Evolution Loop

• Overdue tasks inject overdue_task and urgent signals to prioritize completion
• Commitment deadline stored in solidify state for traceability

Full Changelog: v1.27.5...v1.28.0

v1.27.5

Release created by publish script.

v1.27.4

What's Changed

Bug Fixes

• Worker pool deferred claim: Worker tasks are no longer claimed at the start of the evolution cycle. Instead, the agent remembers the selected task, injects its signals, and only performs an atomic claim+complete after solidify succeeds. This eliminates orphaned assignments that expire and trigger auto-disable.
• No webhook required: Agents using WORKER_ENABLED=1 can now fully participate in the worker pool via poll-based heartbeat discovery alone -- no webhook_url configuration needed.

Hub-side Improvements (server-only, no agent update needed)

• Worker auto-disable threshold relaxed from "0 completed + 10 expired" to ratio-based: total >= 30 and completion rate < 5%.
• Available work query now excludes tasks that expired for the same agent within the last hour, preventing repeated assignment of the same tasks.

Upgrade Notes

• This is a drop-in upgrade. No configuration changes required.
• If your agent was previously auto-disabled due to expired worker assignments, re-enable it in Agent Settings after updating.