Why: the settled direction requires a complete agent kernel (web search, code tooling, system tools, MCP external tools, skills, prompts) fused with Agent-Squad; implemented as four PRs across three sub-repos plus this gitlink bump.
Evidence: Agent-Native PR #3 (go vet + go test 15 pkgs ok; parity-matrix R15 re-baselined), Agent-Squad PR #3 (6 pkgs ok), Backend PR #35 (19 pkgs ok, rebased onto concurrent #34); Dev make test all green (core + backend 19 + frontend 40 + ui 68 + agent-command). Security negatives covered: SSRF guards, exec blocklist/process-group kills/env isolation, MCP fail-closed, skills fail-closed, allowlist fail-closed, budget-exceeded permanent.
Impact: deps/agent-native -> f9ab2ef, deps/agent-squad -> 9a402e4, modules/backend -> 87a3d0d. Honest boundaries recorded: run_command is not an OS sandbox; skills/MCP metadata are injection surfaces; product squad default backend unchanged (roles opt in via Backend:agent-native per the progressive-enablement clause).
Refs: .task/feature-full-agent-r1.md (B1-B10).
Why: the settled direction requires a complete agent kernel (web search, code tooling, system tools, MCP external tools, skills, prompts) fused with Agent-Squad; implemented as four PRs across three sub-repos plus this gitlink bump.
Evidence: Agent-Native PR #3 (go vet + go test 15 pkgs ok; parity-matrix R15 re-baselined), Agent-Squad PR #3 (6 pkgs ok), Backend PR #35 (19 pkgs ok, rebased onto concurrent #34); Dev make test all green (core + backend 19 + frontend 40 + ui 68 + agent-command). Security negatives covered: SSRF guards, exec blocklist/process-group kills/env isolation, MCP fail-closed, skills fail-closed, allowlist fail-closed, budget-exceeded permanent.
Impact: deps/agent-native -> f9ab2ef, deps/agent-squad -> 9a402e4, modules/backend -> 87a3d0d. Honest boundaries recorded: run_command is not an OS sandbox; skills/MCP metadata are injection surfaces; product squad default backend unchanged (roles opt in via Backend:agent-native per the progressive-enablement clause).
Refs: .task/feature-full-agent-r1.md (B1-B10).
Why: the settled direction requires a complete agent kernel (web
search, code tooling, system tools, external tool calls, skills,
prompts) fused with squad orchestration; the three sub-repos landed
their batches and this bumps the gitlinks and records the task card.
Evidence: Agent-Native PR #3 (go vet + go test 15 pkgs ok), Agent-Squad
PR #3 (6 pkgs ok), Backend PR #35 (19 pkgs ok after rebasing onto the
concurrently merged #34); Dev make test all green (core + backend 19 +
frontend vitest 40 + ui vitest 68 + agent-command).
Impact: deps/agent-native -> f9ab2ef, deps/agent-squad -> 9a402e4,
modules/backend -> 87a3d0d; task card filled with per-PR evidence and
remaining-item notes (sandbox honesty, injection surfaces,
progressive enablement, deployment validation pending).
Refs: .task/feature-full-agent-r1.md batches B1-B10.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Why: the settled direction requires a complete agent kernel (web search, code tooling, system tools, MCP external tools, skills, prompts) fused with Agent-Squad; implemented as four PRs across three sub-repos plus this gitlink bump.
Evidence: Agent-Native PR #3 (go vet + go test 15 pkgs ok; parity-matrix R15 re-baselined), Agent-Squad PR #3 (6 pkgs ok), Backend PR #35 (19 pkgs ok, rebased onto concurrent #34); Dev make test all green (core + backend 19 + frontend 40 + ui 68 + agent-command). Security negatives covered: SSRF guards, exec blocklist/process-group kills/env isolation, MCP fail-closed, skills fail-closed, allowlist fail-closed, budget-exceeded permanent.
Impact: deps/agent-native -> f9ab2ef, deps/agent-squad -> 9a402e4, modules/backend -> 87a3d0d. Honest boundaries recorded: run_command is not an OS sandbox; skills/MCP metadata are injection surfaces; product squad default backend unchanged (roles opt in via Backend:agent-native per the progressive-enablement clause).
Refs: .task/feature-full-agent-r1.md (B1-B10).