Skip to content

escapeboy/agent-fleet-o

v1.22.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-orchestration agentic-ai ai-agents ai-automation autonomous-agents claude
+14 more
crewai-alternative langgraph-alternative laravel livewire llm-workflow mcp-server model-context-protocol multi-agent n8n-alternative ollama openai php self-hosted workflow-automation

Affected surfaces

auth

Summary

AI summary

Added tool search auto‑discovery from team‑wide pool, Anthropic Fast Mode beta header, and environment/reasoning_effort fields across agents and APIs.

Full changelog

What's changed

  • docs: 1.22.0 release — MCP observability + README/SEO overhaul (e3ed0fa8)
  • docs(mcp): promote Phase 3 deferred work from implicit to explicit (1d8c3efe)
  • feat(mcp): Phase 2c — retrofit 129 more MCP tools (final retrofit pass) (99ebb26c)
  • feat(mcp): Phase 2b — retrofit 71 more MCP tools with structured errors (74ac3539)
  • hardening(mcp): Phase 2 security review fix — classify InvalidArgumentException (f1647469)
  • feat(mcp): Phase 2 — retrofit 121 MCP tools with structured error codes (886b463c)
  • hardening(mcp): Phase 1 security review follow-ups (07e77644)
  • feat(mcp): Phase 1 observability — structured errors, deadlines, SSE backpressure, OpenTelemetry (6c278be3)
  • fix(test): pin anthropic key in ScanListingRiskTest (c4fa6f1f)
  • fix(docker): install GD extension in base PHP image (e539298f)
  • fix(users): add is_super_admin column to base schema (12a1e62b)
  • fix(test): isolate browser policy tests from cloud plan gates (cb8dc7c7)
  • fix(website): wire managing_crew_id + annotate mcp write tools (8f2366f3)
  • fix(chatbot): own MemoryContextProviderInterface, drop Barsy coupling (a73fc96c)
  • fix(test): assert decoded breadcrumbs array, not raw JSON string (de56c0e8)
  • fix(signal): include signal_comments in bug-report delegation thesis (f7af150d)
  • fix(llm): replace hardcoded 'anthropic' default with cascading helper (60915357)
  • fix(sanitize): strip control chars, not non-ASCII — preserve UTF-8/Cyrillic (d9b02161)
  • fix(composer): unblock consumers — VCS repos + optional plugins (5e18e759)
  • fix(website): add missing Generating case to WebsiteStatus enum (99fc9297)
  • feat(tool): enforce network_policy.allowed_domains on browser tools (61bf5a76)
  • fix(ui): show bug-reports pagination summary even on single page (aba68558)
  • fix(migrations): remove duplicate websites create-table migrations (b08733a3)
  • fix(livewire): hook form Cancel button throws 500 on agent detail (b99aa2d3)
  • fix(blade): @php() short syntax crashes compiler in agent detail overview (d1fe72fd)
  • fix(ui): security + content + a11y polish from fresh review (6735e511)
  • feat(ui): UI coverage + content polish for shipped features (d4c02c0e)
  • fix(ai): propagate new DTO fields through all gateway/middleware copies (9c166535)
  • fix(security): UUID guard on tool search filter + CRLF strip on fast-mode beta (2de58e0e)
  • feat(ai): Anthropic Fast Mode per-request beta header (a09ad365)
  • feat(tool): tool search observability stats (part 4/4) (c2178373)
  • feat(tool): tool search debug page + append-only log (part 3/4) (c71fa539)
  • feat(tool): tool search — UI + API + MCP surface (part 2/4) (4730ecae)
  • feat(tool): tool search auto-discovery from team-wide pool (part 1/4) (d19c5e12)
  • feat(steering): audit log entries for queue + consume events (e061305f)
  • feat(experiment): Steer button + modal in ExperimentDetailPage (4d64562b)
  • feat(experiment): add steering injection for running experiments (MVP) (77480db6)
  • feat(agent): expose environment + reasoning_effort in detail view and resource (5d21ba06)
  • feat(api,mcp): expose environment and reasoning_effort in agent surface (dfbd51d5)
  • feat(agent): add environment preset for auto-attaching tool bundles (2906bdbb)
  • fix(agent): validate reasoning_effort at config boundary (076f088f)
  • feat(agent): wire reasoning_effort through UI, config, and execution (0186e36a)
  • fix(ai): cap thinkingBudget at 32K, forward effort in normalizeCustomEndpoint (edc5ebf5)
  • feat(ai): add ReasoningEffort enum and effort-based thinking budget (64faa418)
  • fix: remove null byte from delegate action test (Postgres JSONB rejects \u0000) (6ab55db4)

Upgrade

git fetch --tags origin
git checkout tags/v1.22.0
composer install --no-dev --optimize-autoloader
php artisan migrate --force
php artisan optimize

Docker users: Pull the latest image and restart your containers.

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track escapeboy/agent-fleet-o

Get notified when new releases ship.

Sign up free

About escapeboy/agent-fleet-o

AI Agent Mission Control with 200+ MCP tools. Manage agents, experiments, workflows, crews, skills, and more via stdio + HTTP/SSE. Self-hosted, open-source (AGPL-3.0)

All releases →

Beta — feedback welcome: [email protected]