v3.26.0

Changelog

• 745e805: feat(skills): add skill-process-delegate — master subagent delegation ( <>)
• 8d7f05e: feat(ultra-audit): CEO team audit fixes — 16 issues fixed in parallel ( <>)
• 5e8705c: fix(ecosystem): sync research__* to ECOSYSTEM.md, remove ghost repos, fix archived refs ( <>)
• f9bf526: fix(skills): skill-process-delegate validation — lifecycle, description length, compatibility list ( <>)
• 59d3420: fix: 8 issues fixed in parallel (#460-#467) ( <>)
• b20a841: chore(deps): bump marocchino/sticky-pull-request-comment from 2 to 3 (#468) (@dependabot[bot])
• f4441f9: chore(deps): batch-merge 11 dependabot PRs + add 2 repos to ECOSYSTEM.md ( <>)
• 8a2f3e5: ci: trigger n8n-delegated CI with configured webhook secret ( <>)
• e5adbe0: fix(ci): add checkout+setup-go to workflows with go vet pre-check ( <>)
• 4668146: feat(tui): SOTA TUI improvements — collapsible blocks, slash menu, welcome screen, verify gate indicator, diff approval ( <>)
• de25ccd: feat(tui): typewriter streaming, copy/yank mode, URL links, context meter, chat export ( <>)
• bc5a9c0: fix(tui): wire 5 dead features into rendering pipeline + fix key conflicts ( <>)
• 80aba94: fix(tui): rendering quality — truncate tool output, wrap code blocks, handle empty responses ( <>)
• 60b36db: fix(tui): auto-scroll respect, tab path completion, /model command ( <>)
• 1a64729: fix(tui): virtualized rendering, empty message guard, typewriter copy, render cache ( <>)
• 6e24b62: fix(tui): /help opens overlay, /search scrolls to match, structured errors ( <>)
• f96fabc: fix(tui): wire compact toggle, crash recovery on quit, block input during streaming ( <>)
• 70b9fbf: fix(core): fire 9 missing hooks, add permission entries for 9 chat tools ( <>)
• dbbb4f5: fix(tui): wire 8 dead slash commands + /undercover full toggle ( <>)
• 23b5a29: fix(core): remove 3 dead files, wire spawn_subgoal, fix golden help, add 30 tests ( <>)
• d2fbebd: feat(orchestrator): wire 3 sub-agents into Run() — Cartographer, Adversary, Governor ( <>)
• 285e150: fix(tests): update 12 stale AllGoTools tests (7→0, tools absorbed into binary) ( <>)
• 606b8e4: test(coverage): boost autonomy 79→82%, orchestrator 73→82%, 74 new tests ( <>)
• a7226c8: refactor: split commands.go god file (6464→7 lines) + boost 3 package coverages ( <>)
• ab9b604: refactor: split tui/update.go (3206→1729 lines) + boost eval/stack coverage ( <>)
• cbcabca: test(coverage): boost 4 packages — evalharness 60→77%, telemetry 60→96%, compress 61→75%, testgen 67→88% ( <>)
• bc095de: refactor: split 10 god files into 45+ focused modules ( <>)
• c1d4344: feat: production-ready CLI — config fallback, async MCP, TUI fixes, onboarding, updated NIM models ( <>)
• babd204: feat(cli): production-ready UX — clean output, streaming, --json, --verbose, SilenceUsage ( <>)
• 3d54176: feat(cli): production-ready UX — bare sin-code→chat, friendly errors, spinner, categorized help, TUI input history ( <>)
• 234ed18: feat: sin_web_search chat tool — free DuckDuckGo + Tavily/SerpAPI/Brave multi-provider web search ( <>)
• d002431: feat: youtube-for-ai-agents MCP integration — 9 YouTube tools (search, transcript, clip, reel) ( <>)
• b782120: refactor: split 4 god-files — update.go 1747→371, chat_render.go 1107→307, chat_tools_extra.go 1126→192, loop.go 1009→465 ( <>)

Verify this release

cosign verify-blob \
  --certificate checksums.txt.pem \
  --signature checksums.txt.sig \
  --certificate-identity-regexp "github.com/OpenSIN-Code/SIN-Code" \
  --certificate-oidc-issuer "https://token.actions.githubusercontent.com" \
  checksums.txt
sha256sum -c checksums.txt --ignore-missing

v3.25.0

Changelog

• f3bda89: feat(v3.25.0): doctor, diff, benchmark, tokens cost — 4 new subcommands ( <>)

Verify this release

cosign verify-blob \
  --certificate checksums.txt.pem \
  --signature checksums.txt.sig \
  --certificate-identity-regexp "github.com/OpenSIN-Code/SIN-Code" \
  --certificate-oidc-issuer "https://token.actions.githubusercontent.com" \
  checksums.txt
sha256sum -c checksums.txt --ignore-missing

v3.24.1

Changelog

• 55a42c7: fix(ci): pass TAP_GITHUB_TOKEN to goreleaser for homebrew tap push ( <>)
• d9d0559: fix(production): multi-subagent production-readiness sweep ( <>)

Verify this release

cosign verify-blob \
  --certificate checksums.txt.pem \
  --signature checksums.txt.sig \
  --certificate-identity-regexp "github.com/OpenSIN-Code/SIN-Code" \
  --certificate-oidc-issuer "https://token.actions.githubusercontent.com" \
  checksums.txt
sha256sum -c checksums.txt --ignore-missing

v3.24.0 — TUI live progress + complexity cleanup + analyzer fixes

What's New

TUI/Agentloop Live Progress (issue #424)

• Live tool timing: ToolStart/ToolEnd callbacks with elapsed duration
• NDJSON progress output (--progress json, --progress-dest, --progress-file)
• Live token/cost footer updates every 250ms during streaming
• Esc cancels in-flight TUI prompt
• Autonomy trigger loops exit promptly on context cancellation

sin-code analyse-image (issue #423)

• Vision-capable LLM model for image analysis
• No Tesseract/CGO dependency
• New MCP tool sin_analyse_image

Security Scanning V2

• sin-code security scan secrets/sast/sca/sbom/container/all
• SARIF 2.1.0 output (--format sarif)
• Apple container runtime preferred, Docker fallback
• CEO-audit security gate integration

Complexity Cleanup (55+ files merged)

• All single-export subcommand files merged into natural caller modules
• Zero unapproved findings, zero removable lines
• All 5 complexity analyzers fixed (cross-file interface counting, cobra-constructor exemption, method-wrapper/test-hook skipping, cross-file dead-flag detection, 10-line approval scan window)
• Scoring corrected: 100 - NetLines/100 (clean = A+)
• sin-debt scanner skips .md documentation files

Test Suite Hardening

• Docker-dependent tests auto-skip when daemon unavailable
• Parallel DAG timing race eliminated
• Cron/watch enqueue race fixed
• Security/harvest tests environment-independent
• Browser popup fixed during test runs

Metrics

• CEO Audit: Score 100, Grade A+, 48/48 gates pass
• Complexity: 0 unapproved findings, 0 removable lines
• Rot-risk: 0 (116 markers, all with upgrade trigger)
• Build: pass | Lint: 0 issues | Tests: green

Downloads

• brew install opensin-code/sin/sin-code (Homebrew)
• curl -fsSL https://raw.githubusercontent.com/OpenSIN-Code/SIN-Code/main/install.sh | bash
• Direct binaries for linux/darwin/windows × amd64/arm64

v3.23.0

Unified sin-code binary with 46+ subcommands, MCP server mode, and cross-platform builds.

What's Changed

• feat: SIN Fusion v1 — plan-merge, Oracle default, modelperf registry (#393, #394, #395) by @Delqhi in #397
• feat: sin-analyse-suite full integration — eval, skill, tests, docs (v3.22.0 follow-up) by @Delqhi in #398
• feat(browser): native Go browser facade with HTTP-direct driver (#382) by @Delqhi in #400
• fix: repair main build drift + feat: sin-code research command (issue #384) by @Delqhi in #408
• feat(swebench): add comprehensive test suite for SWE-bench loader and scorer (issue #363) by @Delqhi in #407
• feat(skills): scientific research skill for PubMed, USPTO, arXiv (issue #387) by @Delqhi in #409
• feat: sin_apply_diff and sin_generate_diff chat tools (issue #365) by @Delqhi in #410
• feat: dynamic MCP server discovery (issue #368) by @Delqhi in #411
• docs: v3.23.0 changelog and AGENTS.md roadmap reconciliation by @Delqhi in #412
• feat: unify chat sin_edit with MCP surgical editor and add sin_replace (issue #373) by @Delqhi in #414
• merge: v3.23.0 batch 2 — reactive permission, semantic retrieval, containerized goals by @Delqhi in #417

Full Changelog: v3.22.0...v3.23.0

v3.20.0: Predictive Multi-Agent Orchestrator + Claude Code Leak Inspiration

Release Notes — v3.20.0

Predictive Multi-Agent Orchestrator + Claude Code Leak Inspiration

Release date: 2026-06-17
Previous tagged release: v3.17.0 (2026-06-13)
Commits in this release: 243

---

Highlights

• Predictive Multi-Agent Orchestrator — the orchestrator is now a
  real-time, anticipatory system: a DeepPlanner emits parallel DAGs with
  probability scores, agents are pre-warmed before they're needed, the
  dispatcher is event-driven (channel-based, no polling), and past sessions
  inform future plans via pattern learning. The MockAgent placeholder has
  been replaced with a real LLM-backed LoopAgent.
• Claude Code-Inspired Chat UX — /btw side-questions, /undercover
  AI identity hiding, lazy tool loading (134K → 5K tokens), session
  switcher with preview, model selector with live switching, and a
  complete TUI rewrite with streaming text, visual message blocks, diff
  popups, and syntax highlighting.
• SIN Fusion v1: Verify-Tournament (issue #290) — when the sacred
  verify-gate (M3) fails, the task is fanned out to 6 Fireworks models in
  parallel (MiniMax M3, Kimi K2.7 Code Fast/Pro, DeepSeek V4 Pro, Qwen
  3.7 Plus, GLM 5.2). First PoC-pass wins; losers cancelled. Cost-governor
  and difficulty gate included. Off by default (fusion.enabled = false).
• Tool Coverage Enforcement (issues #248–#253) — runtime
  ToolCoverageEnforcer rejects completion when required tools are
  missing or forbidden tools were used. M6 system-prompt fragment
  mandates SIN tools over naive built-ins. Tool-usage telemetry drives
  ledger tools --heatmap/--coverage/--unused. Unified catalog via
  sin-code catalog.
• Test-First Verify-Loop — sin_test, sin_test_generate,
  sin_quality_gate, sin_mutation, sin_fuzz, sin_property close
  the loop from code written to tests verified. LLM case filling with
  generate/execute/repair cycle.
• 50+ New Subcommands & Features — install, compress, debt,
  audit, ceo-audit, review, catalog, triage, grill, profile,
  compile-spec, cover, autopr, subagent, checkpoint, rewind,
  sessions fork/tree, and more.

---

New Features

Orchestrator

• DeepPlanner (issue #282) — parallel DAG planning with probability
  scores per node. The planner emits multiple plan branches and scores
  them, selecting the highest-probability path.
• Event-driven DAG dispatcher (issue #283) — replaced 50 ms polling
  loop with channel-based dispatch. Latency improvement: tasks start as
  soon as their dependencies complete, no polling delay.
• Anticipatory agent pre-warming (issue #285) — the orchestrator
  pre-warms agents for likely next tasks based on the current plan DAG,
  reducing cold-start latency by spawning goroutines ahead of demand.
• Real LLM-backed LoopAgent (issue #287) — the MockAgent placeholder
  has been replaced with a real LoopAgent that drives agentloop.Loop
  instances. PreWarmer interface implemented for integration with the
  pre-warming system.
• Pattern learning from past sessions (issue #288) — the orchestrator
  now learns from completed sessions, building a pattern store that
  informs future plan generation.
• Parallel subagent spawning (issue #284) — N sub-agents can now run
  concurrently instead of sequentially, with bounded concurrency.
• Caveman-style output contracts (issue #174) — Critic, Adversary,
  Governor, and Cartographer emit byte-stable one-liners with 5 closed
  tags (delete, simplify, rebuild, risk, verify) and em-dash
  separators. Hedging is forbidden and rejected by VerifyFindings.
• Orchestrator ToolChain (issue #252) — the planner attaches a
  deterministic ToolChain to every Plan for classified intents
  (security, review, architecture, test, codebase, docs).

TUI

• Complete TUI rewrite — modern chat-based rendering with markdown
  support, streaming text, visual message blocks, animated spinner,
  context bar, branded welcome screen, and tool cards.
• Chat search, compact mode, file browser, inline diff, syntax
  highlighting — full SOTA chat UX matching Claude Code / opencode.
• Session switcher with preview and recency sorting (issue #259).
• Model selector with performance metrics and live LLM switching
  (issue #259).
• Permission dialog with diff-view overlay (issue #259) —
  Enter=allow, Esc=deny, popup border.
• Token tracking + chat history persistence — per-session chat
  history saved and restored on session switch.
• DAG Visualizer view for the orchestrator (issue #286) — visual
  representation of the DAG in the TUI.
• 5 additional TUI features (issues #267–#280) — context visualizer,
  agent dashboard, keymaps, layout debug, status line.
• Auto-compact context at 80% token limit — prevents context window
  overflow without manual intervention.
• Git TUI, LSP diagnostics, /init, watch mode, benchmarks, E2E
  tests — integrated git operations, live LSP diagnostics in the TUI.
• Image graph generation — deterministic ECharts JSON rendering
  (bar/line/pie/area) with dark theme, gradients, glow, and animations.

LLM

• Context compaction + prompt caching (issues #278, #277) —
  automatic context compaction and prompt caching to reduce token costs.
• Fable/Mythos providers (issue #275) — new LLM provider integrations.
• Thinking field for extended reasoning models — thinking field
  in wire request sends {"thinking":{"type":"enabled"}} for Fireworks
  models that support extended reasoning.
• Verbosity / compression mode (issue #167) — five canonical modes
  (default, verbose, normal, terse, ultra) with byte-stable
  output per (mode, skillBody) pair. Auto-clarity clause ensures
  normal prose around destructive/security-relevant actions (M3).
• SIN Fusion v1: Verify-Tournament (issue #290) — multi-model
  fan-out on verify-fail. 6-model Fireworks pool, thinking/reasoning
  mode, cost-governor (USD kill-switch), difficulty gate, PoC-only.
  New internal/fusion/ package with fireworks_pool.go,
  difficulty.go, tournament.go, provider_pool.go,
  provider_adapter.go. 264 tests, all -race clean. Off by default.

Permission

• YOLO risk classifier + frustration detection (issues #272, #271) —
  classifies --yolo requests by risk level and detects user frustration
  patterns to adjust permission prompts.
• Session-wide permission modes (issue #193) — plan, acceptEdits,
  bypass modes for session-scoped permission policies.
• macOS Seatbelt sandbox backend (issue #199) — --sandbox flag with
  native macOS Seatbelt sandbox support alongside the existing Linux
  Landlock backend.
• Agent profile tool surface (issue #249) — bundled profiles now set
  tools_allow to the full sin_* surface + all registered MCP prefixes.
  Destructive builtins remain at ask tier (M4).

Memory

• autoDream background memory consolidation (issue #273) —
  background memory consolidation inspired by Claude's auto-compaction.
• Byte-stable MEMORY.md surface (issue #192) — auto_mem/ package
  with memory auto-* CLI commands. Claude-Auto-Memory parity, M3-safe.
• RAG over instinct store (issue #160) — internal/rag/ package with
  Embedder interface, HashEmbedder (deterministic, 384-dim), Index
  with persister, WorkerPool (bounded concurrency), and Retriever.
  sin instinct search "<query>" for top-5 cosine-similarity search.
• Continuous-learning subsystem (instinct) — internal/instinct/
  with learned-instinct storage, embedding, and system-prompt injection.
• sin-code compress (issue #172) — deterministic + LLM compaction
  for lessons, instincts, summaries, memory, and AGENTS.md. Three
  strategies (deterministic, llm, hybrid). Atomic snapshot +
  rollback for lossless Apply. Content-addressed plans.

Git

• Git-worktree primitives (issue #194 part 2) — internal/isolation/
  with git-worktree-based workspace isolation. chat --worktree flag.
• Workspace checkpointing + rewind (issue #194) — sin-code checkpoint and sin-code rewind subcommands. --rewind <checkpoint>
  flag on sin-code chat for headless workspace restore.
• Session fork + tree lineage (issue #194) — sessions fork and
  sessions tree with parent_id lineage. Idempotent ALTER TABLE
  migration for pre-existing DBs.

LSP

• LSP diagnostics in TUI — live LSP diagnostics rendered in the TUI
  chat interface.
• LSP servers detection — sin-code lsp lists detected LSP servers
  on PATH (gopls, pyright, tsserver, rust-analyzer).

Chat

• /btw side-questions (issue #276) — ask side-questions without
  losing the main conversation context.
• /undercover AI identity hiding (issue #274) — hide the AI
  identity in chat output for user-testing scenarios.
• Lazy tool loading (issue #270) — 134K → 5K tokens via tool_search.
  Tools are loaded on demand instead of all upfront.
• Auto-activation hook (issue #176) — per-session rule injection on
  SessionStart + UserPrompt. --activate <rule> + --no-trigger
  flags. Project-local .sin-code/autoactivate.toml.
• Sub-agent delegation (issue #153) — sin-code subagent CLI for
  isolated-context sub-agent spawning (wraps issue #192).
• Self-Reflection-Turn before completion (issue #152) — the agent
  performs a self-reflection turn before reporting task completion.
• Token/cost budget with hard cap (issue #151) — configurable
  token and cost budgets with hard caps that abort the loop.
• Stagnation detection + adaptive stop-budget (issue #150) —
  detects when the agent is spinning without progress and adjusts the
  stop budget adaptively.
• Path-scoped rule loader (issue #195) — .sin-code/rules/<topic>.md
  files loaded contextually based on file paths being edited.
• Autolevel prompt-intent classifier (issue #198) — `--auto...

v2.5.0

Unified sin-code binary with 13 subcommands, MCP server mode, and cross-platform builds.

Full Changelog: v1.7.3...v2.5.0

v1.7.3

Unified sin-code binary with 13 subcommands, MCP server mode, and cross-platform builds.

Full Changelog: v2.4.0...v1.7.3

v2.4.0

Unified sin-code binary with 13 subcommands, MCP server mode, and cross-platform builds.

Full Changelog: v2.3.0...v2.4.0

v2.3.0

Unified sin-code binary with 13 subcommands, MCP server mode, and cross-platform builds.

Full Changelog: v2.2.0...v2.3.0