Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

88.3 KB
Raw Blame

Changelog

All notable changes to the Ruflo project (formerly Claude Flow) are documented here.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

[3.65.0] - 2026-10-30

Minor release: @claude-flow/cli, claude-flow, ruflo 3.65.0, plus ruflo-mods plugin 0.12.0. This release ships the eight follow-ups to #4581 on how ruflo integrates with Claude Code mods (ADR-503 to ADR-510, #4585).

Added

  • Learning-loop gaming defences (ADR-503, #4590).

    • A verified-success turn is tainted when it edited tests (edited-tests), edited a verifier's config (edited-verifier-config), or ran a narrowed or weakened check (narrowed-verifier).
    • Tainted records never train unless .claude-flow/config.json learningLoop.allowTaint lists their classes.
    • An opt-in rotating re-verify step (learningLoop.reverify, off by default) re-runs an allowlisted check in a temporary worktree.
    • An anomaly gate holds back lessons whose evidence looks gamed.
    • scripts/eval-learning-loop.mjs is a manual, paid evaluation harness.
  • Real-binary test tier (ADR-504, #4589). This runs the real claude binary with ruflo-mods against a scripted mock of the Anthropic Messages API, with no API key needed. The contracts check that:

    • every mod loads;
    • the learning loop records outcomes;
    • lessons reach the model;
    • the guard denies risky commands;
    • route context is added.

    It runs as the CI job mods-real-binary and as npm run test:real-binary.

  • compactSnapshot (ruflo-mods option, default on; ADR-505, #4591).

    • Before compaction, the mod saves a screened transcript to rotating slots under .claude-flow/sessions/compactions/.
    • After compaction, it adds one bounded [RUFLO_AFTER_COMPACT] block with recent lessons and outcomes, open swarm and claim ids, and the snapshot path.
    • ruflo doctor --component compact-snapshots warns when snapshots exist but .claude-flow/ is not gitignored.
  • Plugin secrets via userConfig sensitive: true (ADR-506, #4587).

    • The cost-tracker, metaharness and x-gateway plugins read their keys through a shared readSecret helper. It checks the masked plugin option first and falls back to the environment.
    • A new scripts/audit-plugin-secrets.mjs CI gate fails on secret-named options that are not marked sensitive, and on literal secrets in manifests.
  • Plugin footprint cut (ADR-507, #4588).

    • Operational skills are user-invoked only (disable-model-invocation: true).
    • Long skill and command descriptions are trimmed to one sentence, with a ceiling enforced by an audit.
    • scripts/measure-plugin-footprint.mjs reports the result, with before and after numbers in v3/docs/validation/.
  • Cost budgets that can feed a gateway (ADR-508, #4592).

    • .claude-flow/cost/budget.json holds the budget windows.
    • ruflo cost budget set writes it.
    • ruflo cost budget export --gateway litellm [--apply] produces LiteLLM budget_limits and per-model budget fallbacks. --apply requires HTTPS except on loopback, and reads the key from an environment variable only.
    • ruflo cost report breaks spend down by agent and by tool.
    • New ruflo-mods option costLedger (default on).
    • --gateway meta-llm refuses until meta-llm documents a budget API.
  • Plugin trust (ADR-509, #4593).

    • Plugins carry Ed25519 signature.json manifests, signed with the existing helpers key.
    • ruflo plugins verify checks a plugin against its manifest and reports verified, modified, unsigned or bad-signature.
    • A static scan runs before mods install, init or plugins install. A high finding stops the install unless you pass --accept-risk <plugin>.
    • ruflo init stops on risky project auto-approve keys (enableAllProjectMcpServers, bypassPermissions, wildcard Bash and others). --keep-risky-settings and --drop-risky-settings let you continue.
    • Under modTrust: refuse-risky, a modified ruflo plugin is refused.
  • Headless plugin staging (ADR-510, #4586).

    • resolvePluginPaths finds ruflo plugins in a local checkout, the marketplace clone or the install cache.
    • Headless claude -p workers now get --plugin-dir for ruflo-mods automatically.
    • ruflo plugins paths [--json] prints the resolved folders for Agent SDK { type: "local", path } callers.
    • ruflo doctor --component headless-plugins checks this setup.

Not yet

  • Per-skill trimming (skillTrim) was not built: Claude Code exposes no hook that hides a skill from the model's list.
  • The 30-task learning-loop evaluation from #4581 Β§7 has still not been run. The loop stays on by default, as the maintainers decided in ADR-502 Β§6.

[3.64.0] - 2026-10-29

Minor release: @claude-flow/cli, claude-flow, ruflo 3.64.0; ruflo-mods plugin 0.8.0.

Added

  • Verified-outcome learning loop (#4581, #4583, ADR-502), on by default (ruflo-mods learningLoop; set it to false to turn it off).
    • The mod records each main-loop turn. Its outcome is decided only by the exit status of a test, build, typecheck or lint command run after the turn's last edit.
    • || true, pipes and ; verify nothing, and the model's own words are never read.
    • ruflo hooks verified-ingest, the MCP tool hooks_intelligence_verified-ingest, and automatic ingest in hooks_route and hooks_session-end all train SONA on verified turns only. Unverified turns are counted and never trained.
    • Learned lessons at or above the 0.6 routing gate are written to .claude-flow/data/learned-lessons.json. The mod cites at most three of them in a prompt they match.
    • ruflo doctor --component learning-loop reports whether outcomes are reaching SONA.

Not yet

  • #4581 stages 5–7 (console pane, autonomous /loop-run, GEPA self-tuning) are not built.
  • The #4581 Β§7 evaluation (30+ tasks, baseline vs loop-enabled) has not been run; the default is on by maintainer decision ahead of it (ADR-502 Β§6).

[3.63.9] - 2026-10-29

Patch release: @claude-flow/cli, claude-flow, ruflo 3.63.9.

Security

  • github_repo_analyze no longer returns credentials embedded in the origin remote. A remote such as https://x-access-token:<token>@github.com/... was echoed verbatim in remoteUrl, putting the token into tool output. URL userinfo is now stripped; scp-form remotes (git@host:o/r) are unchanged (#4577).

Fixed

  • migrate run --dry-run and migrate fix --agents --dry-run (or -d) preview instead of migrating. Both read a flag key the parser never set, so a dry run overwrote .claude-flow/config.json and wrote restored agent files (#4568).
  • github_repo_analyze reads repository names that contain a dot (vercel/next.js, socketio/socket.io) from the origin remote instead of filing them all under local/repo (#4571).
  • hooks_worker-detect with autoDispatch marks its worker records and response as synthetic with a note, instead of reporting a completed worker when no executor ran (#4576).

Changed

  • The agentic-qe-fleet marketplace entry is pinned to Agentic QE v3.15.17 (#4574).

[3.63.8] - 2026-10-28

Patch release: @claude-flow/cli, claude-flow, ruflo 3.63.8, plus standalone @claude-flow/memory 3.1.0.

Fixed

  • @claude-flow/memory 3.1.0 adds ControllerRegistry.set(). The CLI's memory bridge already called it to register controllers it builds itself, but the method did not exist, so those registrations were silently dropped. set() closes any instance it replaces. The agentdb the CLI installs (3.0.0-alpha.20) does not ship the MutationGuard, AttestationLog or GuardedVectorBackend files, so those stay off. What does change: when agentdb's own ReasoningBank is unavailable, the intelligence module's local ReasoningBank is now really registered (#4549, #4550).
  • agentdb_pattern-store and agentdb_pattern-search use the same backend when that local ReasoningBank is registered. Before, the store wrote to the SQL pattern namespace while search read the local bank, so a stored pattern could not be found once the bank held other patterns. Search also falls back to the SQL namespace when the bank has no match (#4567).

[3.63.7] - 2026-10-28

Patch release: @claude-flow/cli, claude-flow, ruflo 3.63.7.

Fixed

  • agent_spawn accepts type as an alias for agentType, so projects set up with older agent and command docs can spawn agents again. agentType wins when both are sent. A call with neither now says agentType is required instead of type: Required. 443 agent_spawn calls in the shipped agent, command and skill docs now pass agentType (#4542, #4543, #4564).
  • coordination_sync trigger refuses instead of waiting 50 ms and reporting a sync that never happened. The tool's description now says so (#4557, #4559, #4564).
  • agent_pool fill is implemented instead of returning "Unknown action" (#4555, #4561).
  • hooks_build-agents writes under the project, validates outputDir, and no longer reports invented stats (#4558, #4562).
  • performance_metrics reports recorded latency and throughput instead of fixed figures (#4554, #4556).
  • The daemon's local audit worker no longer reports a clean scan it did not run (#4563).
  • session_info and session_current read the session records that hooks write (#4548).
  • The GitHub skills use registered MCP tools (#4141, #4541). A new check fails when a shipped skill runs a CLI command that does not exist (#4552, #4553).

[3.63.6] - 2026-10-27

Patch release: @claude-flow/cli, claude-flow, ruflo 3.63.6.

Fixed

  • ruflo-console 0.49.7: Claude can clear Project Anatole alerts through the console again. Before, console_run anatole-ack-<id> failed with "command.run: called from a tool.call hook, it would wait on the turn this hook is holding", so every alert stayed open. The console now sends /protector without waiting inside Claude's tool call, and Claude's reply says the action is queued. The ack is applied when the turn ends (#4545).
  • claims_rebalance no longer overfills one agent (#4547).
  • @claude-flow/aidefence is declared as an optional dependency of the CLI (#4445).
  • The hooks-automation skill uses the hooks command and the real MCP tool names (#4538, #4540).

[3.63.5] - 2026-10-27

Patch release: @claude-flow/cli, claude-flow, ruflo 3.63.5, plus standalone @claude-flow/neural 3.0.1.

Security

  • http_fetch now validates every redirect target, not only the first URL. A public URL can no longer redirect to loopback, private ranges, cloud metadata or file://. Redirects are capped at 10 hops, and Authorization/Cookie headers are dropped on cross-origin hops (#4534).

Fixed

  • SONA EWC++: SONAManager now records Fisher importance and anchor values after each learning cycle; before, they were always empty. The anchor is the parameter value at consolidation, so the penalty starts at zero (#4531, #4532, @claude-flow/neural 3.0.1). The penalty is still not applied to the learning update.
  • task_list status filter matches status aliases (#4536).
  • Workflow condition steps can read an earlier step's output via step-N.output (#4530).
  • task_summary counts cancelled tasks, so the counts add up to the total (#4489).
  • hooks_worker-status summary counts pending workers (#4529).
  • doctor recognizes matching npm launchers on Windows (#4473).
  • ruflo-console 0.49.5 keeps a project copy of the mission ledger, so a mission survives a restart that loads the console from a different source (#4524).

[3.63.4] - 2026-10-26

Patch release: @claude-flow/cli, claude-flow, ruflo 3.63.4, plus standalone @claude-flow/mcp 3.1.4, @claude-flow/plugin-agent-federation 1.0.3 and @claude-flow/shared 3.0.6. Follow-ups to the 3.63.3 security fixes.

Security

  • mcp start -t http|websocket with no token now uses a per-user token in ~/.claude-flow/mcp-http-token (mode 0600, created on first use), so a loopback server is no longer open to every local process. Set RUFLO_MCP_ALLOW_UNAUTHENTICATED_HTTP=1 to run without one. The standalone WebSocket transport now checks the token when the connection upgrades (Authorization: Bearer or ?token=), and --auth-token works with it (#4516). Breaking: HTTP/WebSocket clients must send the token.
  • Federation: VERIFIED and ATTESTED trust now require the key pinned for the peer in the trustedPeerKeys config (node id to hex public key); a self-signed manifest or a handshake response only proves possession of the key it carries. A handshake response must come from the node that was challenged, the listener defaults to 127.0.0.1, and nonces use crypto randomness (#4514). Breaking: peers that relied on self-asserted trust need a trustedPeerKeys entry.
  • A file in .claude-flow/daemon-queue/ no longer counts as a manual trigger, so it cannot skip the supervisor gate (#4515).
  • @claude-flow/shared 3.0.6 carries the same Origin/Host guard and WebSocket token check as @claude-flow/mcp (#4517).
  • AgentBBS: a .. in a room label can no longer move the room log outside its base path (#4518).

[3.63.3] - 2026-10-26

Patch release: @claude-flow/cli, claude-flow, ruflo 3.63.3, plus standalone @claude-flow/mcp 3.1.3 and @claude-flow/plugin-agent-federation 1.0.2. Security fixes from a private report.

Security

  • A cloned project's config can no longer turn on AI workers: daemon.aiWorkers.enabled is honoured only from the --headless flag, RUFLO_DAEMON_AI_WORKERS=1 or ~/.claude-flow/config.json; a project file can only say false. The audit worker no longer globs **/.env* (#4509). If you relied on a project file to enable AI workers, move the setting to your user config.
  • @claude-flow/mcp 3.1.3: HTTP and WebSocket transports with no token now refuse requests and upgrades from a web page (any Origin not listed by exact name; * does not count) or with a non-loopback Host, and refuse to listen beyond loopback without a token unless allowUnauthenticated is set (#4510). A local process can still call a token-less loopback server; set a token.
  • @claude-flow/plugin-agent-federation 1.0.2: a policy denial of task-assignment, memory-query, context-share, trust-change, topology-change, agent-spawn, claim-event or agent-handoff is final in legacy and observe mode too, and an evaluator error refuses them (#4511). Still open: the listener defaults to 0.0.0.0, and discovery manifests are verified against their own key.

[3.63.2] - 2026-10-26

Patch release: @claude-flow/cli, claude-flow, ruflo 3.63.2. No leaf package published.

Security

  • http_fetch no longer lets IPv6 literals past its SSRF guard: brackets are stripped before matching, so the fc00::/7 and fe80::/10 checks now work, and IPv4-mapped forms such as ::ffff:127.0.0.1 and ::ffff:169.254.169.254 are decoded and checked against the IPv4 rules (#4503, #4504). Still open: ::, multicast and NAT64 ranges, and redirect re-validation.

Fixed

  • ruflo-console 0.49.4: the mission plan is submitted from a file, which fixes "command line is too long" on Windows (#4506).
  • CI gates helper sync on import and manifest checks (#4507).

[3.63.1] - 2026-10-25

Patch release: @claude-flow/cli, claude-flow, ruflo 3.63.1. No leaf package published (the swarm fixes below live in @claude-flow/swarm, which the CLI does not depend on).

Fixed

  • ruflo-console 0.49.3: the install record for a plugin installed more than once no longer comes from another project; with none applying the console says "not installed here", and the record with the longest projectPath wins (#4496, #4497). Also in this train: Windows path and autopilot guard fixes (0.49.1/0.49.2, #4490, #4491, #4494).
  • flywheel run skips the directory fsync on Windows so it can commit (#4492, #4493).
  • federation_bbs_watch pages forward from sinceEnvelopeId (#4480).
  • Managed agents refuse . and .. resource ids and the guard reads common argument wrappers (ruflo-agent 0.4.1, #4478).
  • ruflo-mods 0.7.1 loads again (#4485, #4487).
  • Swarm (source only, unpublished): downgraded topology leaders wire only to the leader, consensus waits on events instead of polling, retries release the old domain slot (#4483, #4498, #4499).

[3.63.0] - 2026-10-25

Minor release: @claude-flow/cli, claude-flow, ruflo 3.63.0. Adds four MCP tools for Anthropic Claude Managed Agents (managed_agent_capabilities, managed_agent_control, managed_agent_learning, managed_agent_interrupt). No leaf package changed, so no standalone publishes.

Added

  • Managed cloud agents: dynamic workflows, controls and verified advisory learning (ruflo-agent 0.4.0, ruflo-workflows 0.7.0, ruflo-console 0.49.0; ADR 0003 and 0004). Everything is opt-in. A cloud agent can run bounded dynamic workflows (dynamicWorkflows: true with a mandatory budgetCents, limited networking, optional predefinedAgents); provider completion is reported as verification: "unverified". Managed sessions show up in the console's Workflows page with their budget, blockers and worker counts, with zero provider traffic from the panels. managed_agent_control inspects, interrupts or terminates one session only when the host sets RUFLO_MANAGED_CONTROL=1 and lists the session in RUFLO_MANAGED_CONTROL_SESSIONS, after a fresh read of the provider's state. With RUFLO_MANAGED_LEARNING=1 and a host-configured RUFLO_MANAGED_VERIFIER_PUBLIC_KEY, managed_agent_learning admits signed outcomes (unsigned ones stay quarantined), recommends a strategy and evaluates paired holdouts; nothing changes routing on its own.
  • User guide: a "Managed cloud agents" section in docs/USERGUIDE.md.

Fixed

  • memory_search_unified dropped an entry whenever the same key existed in two namespaces; it now deduplicates on namespace and key (#4470, thanks @kevin9327).
  • Before this release shipped, an independent review of the managed-agent change found and fixed: managed_agent_interrupt had no host policy gate (it now uses the managed_agent_control path, and managed_agent_terminate obeys the same allowlist, deleting only the session's own environment, once RUFLO_MANAGED_CONTROL=1); managed_agent_prompt could report the previous turn's answer as finished on a later poll; several valid base64 spellings of one verifier signature were stored as separate ledger records; and the console showed rescheduling, budget-stopped and action-blocked sessions as finished.

Notes

  • Known limits (ADR 0004): the verifier signs with a key in the same user account as the checks it runs, so run only host-authored checks, never ones an agent produced; evidence is only partly bound to what ran; a crashed process can leave a lock file that needs removing by hand; a session in an error state cannot be controlled. Live execution against the Anthropic Managed Agents beta has not been exercised (it needs an executor key), so treat the cloud runtime as unproven in production.
  • ruflo-ai-team 0.3.5 (#4475) also changed in this tree.
  • RUFLO_MANAGED_AGENTS_BASE_URL is an operator-only override of the API origin (an HTTPS origin, no credentials, path or redirects); it is never a tool argument.

[3.62.0] - 2026-10-24

Minor release: @claude-flow/cli, claude-flow, ruflo 3.62.0. Adds one MCP tool (rure_cuda_launch_plan). No leaf package changed, so no standalone publishes.

Added

  • ruRE: CUDA launch plan (ruflo-rure 0.6.0, ADR-501). New read-only MCP tool rure_cuda_launch_plan turns what rure_analyze_cuda found into a plan for measuring: per architecture and kernel, how many blocks and warps fit on one multiprocessor at each block size, which resource sets the limit (registers, shared memory, warps, block slots, barriers), the best block sizes and flags. Eight architectures have a table (sm_70 to sm_120); any other gets no figure rather than a guess. It still parses and never runs: includeHarness only returns the text of a small CUDA program for you to build and run yourself. The occupancy model matches NVIDIA's cuda_occupancy.h on 1.77 million combinations and the CUDA driver on five real GPUs (ADR-501, ADR-500).

Fixed

  • rure_analyze_cuda reported the wrong architecture (sm_5) for a standalone .cubin built with CUDA 12 for sm_70 to sm_90; the SM number sits in a different byte depending on the cubin's OS ABI. Cubins inside a fatbin or host binary were not affected.
  • The worker daemon let a maxConcurrent or workerTimeoutMs saved in daemon-state.json override the same setting in config.json; an explicit value now wins (constructor, then config file, then saved state, then default) (#4462).
  • Cancelling a headless worker now settles its execution and escalates to SIGKILL when the child ignores SIGTERM; the fallback timer no longer keeps the host alive, and a timed-out child no longer gets a second SIGTERM (#4463).

Notes

  • Plugins in this tree that changed: ruflo-rure 0.6.0, ruflo-ai-team 0.3.4, ruflo-browser 0.3.7 (doctor path from other working directories), ruflo-x-gateway 0.10.2. The x.ruv.io gateway itself (0.9.1) is a separate deployment.
  • @claude-flow/swarm changes (#4456, #4457) are not a CLI dependency and are not part of this release.

[3.61.1] - 2026-10-24

Patch release: @claude-flow/cli, claude-flow, ruflo 3.61.1. No leaf package changed, so no standalone publishes.

Added

  • ruflo-console 0.48.0 (ADR-499): the ruRE page can read a folder outside the project that you allow. New plugin option rureFolders (name=/absolute/folder pairs); a sample then names it as @name/sub/file. Absolute paths, .. and odd characters in a sample are still refused; the folder and every part below it must not be a link; and changing the option is an install-class write that always asks you first (Claude's console tools can only propose it at the full control level). ruRE still only parses. This is the version that ruflo tui ships, which is why it needs a CLI release.

Notes

  • CI: plugin pull requests now fail unless the plugin's plugin.json version rises when shipped files change (#4447).
  • @claude-flow/plugins (#4451, registry caches no longer re-run a surviving plugin's register* methods) is not a CLI dependency and is not part of this release.

[3.61.0] - 2026-10-23

Minor release: @claude-flow/cli, claude-flow, ruflo 3.61.0. Adds one MCP tool (rure_analyze_cuda). No leaf package changed, so no standalone publishes.

Added

  • ruRE: CUDA static analysis (ruflo-rure 0.5.0, plugin ADR-0006). New read-only MCP tool rure_analyze_cuda reads the GPU code inside a CUDA fatbin, cubin or PTX file: fatbin entries (PTX or cubin, target architecture, LZ4/zstd compression), each kernel with register count, code size and constant/shared/local memory, and PTX version, target and kernel names. It parses only; nothing is executed, and strings taken from the file pass the AIDefence gate. Checked against real nvcc 12.8 and 13.0 output. Not included: SASS decoding, cuobjdump shell-out. zstd entries need Node 22.15+.
  • ruflo-console 0.47.0: a CUDA row on the ruRE page, DETECT routes for .cubin, .fatbin and .ptx, and a hint on a native binary that holds a CUDA fatbin (ADR-495..497). The ruRE page refuses a sample that is a symlink, wraps long lists, and shows Claude a structured rure block in console_state.
  • ruflo-mods 0.7.0: opt-in rureOffer (off by default, ADR-498) adds one line under an answer when the model touched a binary, library, .asar or CUDA file, saying ruRE can inspect it without running it. Offer only; the mods plugin is not part of the CLI tarball.

Fixed

  • Dependency audit: zod 4.6.7 in ruflo-graph-intelligence and @claude-flow/browser (GHSA-mrhx-c7xc-m3w5). Nested zod 3 copies stay under two time-boxed accepted findings that expire 2026-11-23 (#4442, #4444).

[3.60.1] - 2026-10-23

Patch release: @claude-flow/cli, claude-flow, ruflo 3.60.1. No leaf package changed, so no standalone publishes.

Fixed

  • ruflo cleanup --force --keep-config deleted the config files it is meant to keep (claude-flow.config.json, the hooks/claudeFlow blocks of .claude/settings.json): the parser stores the flag as keepConfig and the action read keep-config (#4435).
  • ruflo-console 0.45.1: ADR init, saves and exports work on Windows. The write layer shelled out to dd, install and sh, which do not exist there; a new host-fs write flavor uses the host filesystem (#4433, #4434, carries #4429).
  • ruflo-console: the autopilot envelope accepts Windows paths (C:\work\app, UNC) and compares them ignoring case and separator style; a POSIX-rooted path containing a backslash is still refused (#4436). Autopilot start stays gated off on Windows.

[3.60.0] - 2026-10-23

Minor release: @claude-flow/cli, claude-flow, ruflo 3.60.0, with @claude-flow/hooks 3.0.2 and @claude-flow/mcp 3.1.2 published standalone. Backward-compatible additions (six new reverse-engineering MCP tools, a ruRE page in the console) plus security and correctness fixes. The 3.59.x patch releases are not itemised here; this lists what changed since 3.59.17.

Added

  • ruRE: static reverse engineering (ruflo-rure 0.4.2, ADR-0001..0005 of the plugin). Six read-only MCP tools β€” rure_extract_asar, rure_analyze_js_app, rure_find_feature, rure_analyze_binary (ELF, PE, Mach-O), rure_analyze_dotnet (metadata only) and rure_analyze_evm (bytecode inventory) β€” that parse a file and never run it. Every string taken from the analyzed file passes the AIDefence gate; results say screened: false when the scanner is unavailable. New dependency: @electron/asar. Known gaps: EVM and P/Invoke handling validated on built fixtures only; the .asar scratch folder is not cleaned up; the tools read any path the process can read.
  • ruflo-console 0.45.0: a ruRE page in the TOOLS group (ADR-494) with a row per tool, a project-relative sample field, and results cleaned of terminal escapes. The tools are needed in the CLI: on 3.59.17 and older the rows say to update.
  • agentic-qe-fleet marketplace pin moved to v3.15.12 (#4419).

Fixed

  • Security: agentbbs accepted .. in a room id, letting a room log path escape .agentbbs (#4416).
  • Security (@claude-flow/mcp 3.1.2): MCP session ids were a counter, a timestamp and six Math.random() characters, so they were guessable; they now use crypto.randomUUID() (#4418).
  • neural_compress with method: "prune" deleted every stored neural pattern and reported success, because pattern usage is never recorded; it now refuses and leaves the store untouched (#4428, #4423).
  • github_pr_manage merge/close and github_issue_track update/close reported success when gh failed or no record matched, and PR actions ignored owner/repo; they now fail with gh's error and pass --repo (#4425, #4424).
  • daa_agent_adapt recorded performanceScore: 0, and an omitted score, as a 0.8 success; 0 is now a failure, an omitted score records none, and an out-of-range score is rejected (#4427, #4426).
  • The bridge search looked at only the newest 1000 rows, hiding older ones; the window is back to 10000 and configurable with CLAUDE_FLOW_SEARCH_WINDOW (#4405, #4397).
  • The cost-tracker Stop hook stored its record in the session's project instead of CLAUDE_FLOW_CWD (#4407), and doctor could not read the version of a claude.cmd shim on Windows (#4408) (#4397).
  • The AgentDB embedder rescue applied only to the first store in a process (#4421).
  • transport use slim, agent publish and swarm join now report "not configured" when the installed AGNTCY SDK lacks the function they call, instead of failing at the call site (#4409, #4376).
  • update all honours --dry-run (#4398).
  • WorkerDaemon kept two timers for a worker enabled twice (#4412). In @claude-flow/hooks 3.0.2: an explicit stop is no longer undone by a pending auto-restart (#4413), a duplicate cluster is counted once (#4415), and fallback embeddings no longer block the event loop for up to 10 s (#4422).
  • ruflo-ai-team's annotation-review.md missed two tools (#4394); the federation peer's standalone TLS lock moved to patched rustls, webpki and quinn-proto (#4414).

[3.58.1] - 2026-10-20

Patch release: @claude-flow/cli, claude-flow, ruflo 3.58.1. Bug fixes only.

Fixed

  • Security: hooks_codemod's resolveTargets() path-containment check used an unanchored abs.startsWith(cwd) string-prefix comparison β€” a sibling directory merely starting with the project directory's name (e.g. cwd-staging) passed containment, letting this live, CLAUDE.md-recommended tool read and write outside the project root (CWE-22). Anchored both call sites at a path-separator boundary, matching the already-correct isWithinPrefix() pattern used elsewhere in this codebase (#4312/#4313).
  • CommandParser.parse() flipped parsingFlags = false on every literal -- token it saw, not just the first β€” a later -- supplied as an ordinary operand (e.g. a search query of exactly --) was silently swallowed instead of being kept as a positional (#4310/#4314).
  • TokenOptimizer.optimizedEdit() called agentBooster.editCode(), a method that has never existed on agentic-flow/agent-booster's real exports; a separate bug in the same file's initialize() picked the un-instantiated AgentBooster class instead of calling the package's getAgentBooster() factory. Published standalone as @claude-flow/[email protected] (#4311/#4315).
  • CI reliability: scripts/__tests__/probe-mod-guards.test.mjs (a node:test file) was never categorized into either the vitest-baseline or vitest-excluded list, causing an intermittent, unrelated "no test suite found" failure on PRs that don't touch it (#4316).

Added

  • ruflo-console 0.44.6: the compact nav's menu, groups, search and page tabs are now separated by a dim β”‚ bar instead of just a gap (#3664).

[3.58.0] - 2026-10-20

Minor release: @claude-flow/cli, claude-flow, ruflo 3.58.0. Backward-compatible additions (new memory peek command, a Codex session activity viewer, configurable MCP rate limits) plus a critical install-breaking fix and a round of correctness fixes.

Fixed

  • Critical: @claude-flow/[email protected] pinned @claude-flow/[email protected], which had never been published, so every fresh install of the 3.57.x line failed with ETARGET (#4303). Published @claude-flow/[email protected] standalone (verified against a clean install) and added scripts/audit-leaf-versions-published.mjs β€” a new, now-required CI check that queries the live npm registry for every non-bundled leaf pin so a PR that bumps a pin ahead of its own leaf's publish fails before merge, not after release (#4304).
  • agent spawn --name was accepted and echoed by the CLI but never persisted to the AgentRecord, so ruflo-console could only label agents by type (#4300/#4301).
  • agent list --all sent a literal status: 'all' that agent_list doesn't recognize, filtering out every agent; agent list --type was accepted but never read (#4302).
  • claims_claim's expiresAt was declared but unsettable by any handler, and the claims-load utilization math duplicated the max-claims threshold as a second magic literal (#3180/#3927).
  • A stale docstring on InMemoryClaimRepository claimed SQLite-backed persistence that doesn't exist in this package (#3179/#3926).
  • The persistent embedding cache raced concurrent cold callers into redundant SQLite initializations, and its FNV-1a cache key could collide for distinct equal-length inputs, including the lone-surrogate case (#3685, #3681).
  • The embedding model cache directory could be unwritable for non-root runtime users, permanently caching the mock fallback with no retry path (#3692/#3831).
  • ruflo-mods' risky-call/event classifier was missing several calls and hook events (agent.register, tool.call, session.append, read-side forgery vectors like fs.read/env.get, and more) that can rewrite or forge what other mods decide by β€” strictly widened, nothing un-flagged (#3802).
  • ruflo-x-gateway could crash on a malformed relay frame instead of failing fast on the one relay connection affected (#3921).
  • The standalone terminal console (npx ruflo tui) gave no on-screen indication that mouse support is off by default, silently dropped the 0 menu hint from the footer below 80 columns, and dropped a mouse press+release pair when a terminal (tmux especially) coalesced them into one data chunk (#4305).
  • CI reliability, found while validating this release (#4307): v3/@claude-flow/memory's FTS5 tests located sql-wasm.wasm via a sql.js/package.json subpath resolve, which sql.js 1.14's tightened exports map rejects even though the file exists β€” now resolves sql.js/dist/sql-wasm.wasm directly; plugins/ruflo-business-pods/scripts/pod-tick.test.mjs (a node:test file) was miscategorized into the vitest-can-run-it baseline instead of the node:test-only exclusion list (#4308); plugins/ruflo-graph-intelligence's knowledge-graph adapter built its optional @claude-flow/cli import specifier as a string literal that a bundler's static scan could eagerly (and wrongly) try to resolve during test collection, outside the method's own try/catch β€” now built from joined parts; the root test-suite ratchet's default vitest worker count intermittently crashed with ERR_IPC_CHANNEL_CLOSED partway through the ~9500-test suite β€” capped at 2 workers as a stopgap pending real root-cause work; tests/all-plugins-smoke-workflow.test.mjs's hardcoded timeout-minutes: 10 expectation went stale when #3950 raised the real value to 15 for the new external-plugin smoke step.

Added

  • memory peek β€” a read-only command that reports which store files the current directory resolves to, row counts, last-write time, and WAL state, without ever creating, initializing, or migrating anything (#3508/#3620).
  • @claude-flow/codex activity β€” inspect a Codex helper's assignment, recorded state, progress, and tool calls/results from an existing session, with symlink-safe, TOCTOU-resistant file access and best-effort credential masking in previews (#3930/#3962).
  • mcp start now supports configurable HTTP and per-session rate limits (#3694).

[3.57.2] - 2026-10-19

Patch release: @claude-flow/cli, claude-flow, ruflo 3.57.2. @claude-flow/cli-core 3.7.5 (#4295, #4296) published standalone and pinned exactly. A large community PR batch β€” mostly correctness fixes to error reporting, memory/graph boundary handling, and CLI diagnostics.

Fixed

  • agentdb_graph-query/agentdb_graph-pathfinder resolved the memory DB path ad hoc instead of through the shared resolveDbPath() priority order, so an explicit CLAUDE_FLOW_DB_PATH binding could silently read a different store than the one selected (#4291, #4298).
  • backupMemoryDb() fell back to a raw file copy after any native online-backup failure β€” including ordinary SQLITE_BUSY/disk errors on an unencrypted source β€” and reported backedUp: true regardless; the fallback is now gated on a confirmed-encrypted source with no active WAL, and the result records which method actually completed (#4287, #4297).
  • JsonMemoryBackend.isExpired() used a falsy check on ttlSeconds, so an explicit ttl: 0 never expired (cli-core 3.7.5, #4295, #4296).
  • RvfBackend's native @ruvector/rvf branch could never succeed (wrong open() call) and silently fell back to the pure-TS path; the dead native branch is removed rather than half-wired (#4278, #4279, #4280).
  • ReasoningBank.consolidate() deleted pruned/deduplicated patterns from storage but never called hnswIndex.removePoint(id), so the HNSW index filled with orphans until storePattern() started throwing permanently (#4270, #4271).
  • TopologyManager's queen/coordinator failover never promoted a replacement after death despite failoverEnabled: true, silently falling through to generic mesh-style ranking (#4285, #4286).
  • memory export, memory import, and memory_migrate reported fabricated success text instead of the tool's real error or migrated count (#4204/#4207, #4194/#4209, and the memory-import tool failure fix).
  • hooks worker dispatch printed Status: completed even when no daemon ran anything (#4196/#4208).
  • hooks_intelligence_attention accepted unimplemented modes instead of rejecting them (#4193).
  • init upgrade now refreshes intelligence.cjs/session companions instead of leaving stale copies behind (#4198/#4220).
  • SmartRetrieval collapsed multi-result searches down to one (#4192); the ReasoningBank embedder used a hash fallback instead of the real embedder (#4191); @claude-flow/cli's own package.json wasn't exported for consumers resolving it directly (#4190).
  • ruvocal's MCP server merge dropped a base server's credentials when the browser echoed the server back without headers (#4281).
  • ruflo-x-gateway now advertises offline_access so OAuth clients can refresh silently instead of re-authenticating on every access-token expiry (#4256).
  • workflow list/status/stop/run now read the actual shape and errors the workflow tools return (#4268); stale task owners are released on terminal states (#4272); unregistering a swarm agent now removes its domain-pool membership (#4269); orphaned atomic-write temp files under the policy lock are reaped (#3164/#4273); one-shot CLI runs now flush learned patterns before process.exit(0) instead of losing them while stats.json keeps counting (#4283/#4284).
  • ruflo-console's mission ledger no longer leaks a mission from one project into every other project's cockpit (#4254/#4276).
  • Command examples in the user guide that failed when copied are fixed (#4275); a stray npx invocation referencing a nonexistent unscoped package is corrected to @claude-flow/codex (#4265).
  • scripts/build-codex-mod-hooks.mjs now rebuilds the codex-mod bundle the same way on every OS (#4292).

[3.57.1] - 2026-10-19

Patch release: @claude-flow/cli, claude-flow, ruflo 3.57.1. @claude-flow/cli-core 3.7.4 (#4229, #4230) was published earlier and is pinned exactly.

Security

  • DENYLISTED_ENV_NAMES now blocks the credential/command-hijack and interpreter-flag-injection vars that 2026-09-21's env-sanitizer fix missed: GIT_ASKPASS, GIT_PROXY_COMMAND, GIT_CONFIG_NOSYSTEM, PERL5OPT, RUBYOPT, JAVA_TOOL_OPTIONS, _JAVA_OPTIONS, JDK_JAVA_OPTIONS, PYTHONHOME, CLASSPATH, PYTHONSTARTUP, plus git's numbered GIT_CONFIG_(COUNT|KEY_\d+|VALUE_\d+) family via a new regex (cli-core 3.7.4, #4229, #4230).

Fixed

  • all-plugins-smoke: the adr/ddd/sparc codex-mod native hook bundles are rebuilt, clearing the native-bundle-drift failure that had been hitting every push to main; scripts/build-codex-mod-hooks.mjs also no longer hard-fails on Windows, where execFileSync can't invoke a .cmd shim directly (#4266, #4277, @uyg7x).

[3.57.0] - 2026-10-17

Minor release: @claude-flow/cli, claude-flow, ruflo 3.57.0. A batch of community and dream-cycle fixes (#4210-#4252) plus a policy-ledger integrity fix (#3892). No standalone leaf republish needed this round.

Security

  • ruflo init / init --dual / @claude-flow/codex init no longer write a permissive .codex/config.toml by default. The generated file now uses sandbox_mode = "workspace-write", approval_policy = "on-request" and web_search = "cached" (standard trust); the old danger-full-access / never / live file needs an explicit --codex-trust full (or RUFLO_CODEX_TRUST=full). init prints which level was written, an existing .codex/config.toml is never rewritten (not even with --force), and a kept permissive file is flagged with how to tighten it. Found by the three-host e2e run (ADR-490). @claude-flow/codex 3.0.4 (bundled, ships with the next train).
  • The MCP bridge on loopback no longer accepts tool-call requests from an arbitrary web page: local-only mode now requires the Host to be loopback (blocks DNS rebinding) and the Origin to be loopback-or-allowlisted when no MCP_AUTH_TOKEN is set (#4226, #4243, @kevin9327).
  • The policy ledger now authenticates a retained/pruned ledger against its independent on-disk archive anchor instead of trusting the mutable state.json alone, and streams full audits through fenced writers. Fixes policy-ledger-verification-failed on any install whose ledger has already been pruned (#3892, #4216, @proffesor-for-testing).

Added

  • ruflo doctor reports better-sqlite3 copies compiled against Node 24.19+ headers when running Node 24.19–24.21, where they can abort the process (Assertion failed: (env) != nullptr, nodejs/node#65446), with the documented workarounds. doctor --component native-addon runs it alone (#4055, reported by @ronmikailov).
  • ruflo doctor reports health checks as versioned JSON output (#4228, @bryanbans).

Fixed

  • @metaharness/darwin pin bumped from ~0.10.2 to ~0.12.0, unblocking the metaharness-pin-drift CI gate repo-wide (#3219, #4252).
  • Swarm: subscriber delivery is cancelled cleanly at shutdown, acknowledgements are tracked per recipient, urgent messages survive queue overflow, and failed/cancelled task workers release their slot (#4233, #4234, #4235, #4236, @rudycelekli). Coordinator cancellation stays terminal (#4244, @rudycelekli); domain pools stop creating unregistered agents and release agents after terminal tasks (#4246, #4247, @Tong-bit-art); shared worker reservations are honored across agent pools, fixing a case where that bookkeeping change would have silently defeated the domain-pool-release fix above (#4245, @rudycelekli).
  • Learning stats read-merge-write transactions are serialized across processes, fixing lost concurrent increments (#4217, #4240, @rudycelekli).
  • Claude memories refresh across project and worktree roots (#4210, @rudycelekli); the secret screen no longer treats a hyphen-named memory key as a credential field (#4202, #4211, @akushonkamen).
  • Hook lifecycle events are distinguished during deduplication, fixing the Stop hook claiming the session-end de-dup key so later hooks never ran (#4206, #4212, @dajiaohuang); init omits unimplemented generated hooks (#4200, #4213, @dajiaohuang) and stops granting blanket execution of project helpers (#4221, @xiajiahang).
  • Intelligence: trajectories are forwarded using the ruvllm contract (#4222, @xiajiahang); neural quantization reports unchanged persisted storage instead of a false delta (#4224, @dajiaohuang).
  • Console: Mission Control's prose wraps at 80 columns (#3899, #4225, console 0.44.3, @korjavin); the mission ledger is keyed per project instead of leaking one project's active mission into every other (#4237, #4242, @kevin9327).
  • daemon status reports the running daemon's actual TTL instead of a stale --ttl 0 default (#4238, #4241, @kevin9327).
  • CLI: --no-color is honored for help and version output, and --no-update is honored before the startup update check runs (#4248, #4251, @shuaiyafei).
  • dream(performance): RaftConsensus.awaitConsensus() is event-driven instead of busy-polling (#4214, #4215).
  • Docs: 25 user guide links repaired to v3 packages (#4223, @ketpatil77); ABP-governed SGit memory checkpoints and Ruflo CLI recovery validation documented (#4239, @mondweep).

Not included: #4220 (helper-execution-permission fix) touches a signed helper manifest and needs a re-sign with the private key before merge, held for a follow-up release. #4216's own large diff (ledger integrity) was reviewed in depth separately before merging, given it gates MCP tool-call authorization.

[Unreleased]

Fixed

  • @claude-flow/shared 3.0.4: RVF event log no longer loses appends after a damaged tail (#4031, @rudycelekli). A partial length prefix, a partial payload or a record cut short is truncated on open, so later appends are readable; an unwritable log (EACCES/EROFS/EPERM) keeps its readable history and rejects appends explicitly. A tail whose length prefix is over the 100 MB limit is no longer accepted silently (found by @martinvlad): the bytes are kept and append() rejects until repaired, or set repairOversizedTail: true to truncate it. append() also refuses a record the replay limit would never read back. A fresh install can now import the package root and its tarball ships no test files: zod, express, cors, helmet, ws and @types/ws are declared dependencies, Express 5 bodiless POST and malformed-JSON requests get JSON-RPC 400s (#4091/#4089, @proffesor-for-testing).

Batch of reviewed fixes from @rudycelekli (PRs #4020-#4026, #4028-#4030, #4032, #4033, #4035, #4037; #4027 and #4034 landed earlier):

  • @claude-flow/cli-core 3.7.1: JSON memory backend owns its snapshots, rejects invalid entry containers, measures size in UTF-8 bytes, omits non-matching substring results and lets expired keys be reused; output formatter honours progress controls, empty totals, table padding, coloured header widths, and suppresses progress in quiet or redirected output.
  • @claude-flow/shared 3.0.3: RVF event log honours zero limits, rebuilds indexes on retried initialization and isolates persisted records from caller mutation; circuit breaker returns independent date snapshots and expires rolling requests on completion.
  • ruflo-adr 0.5.5 (see its changelog).
  • Not included: #4031 (RVF truncated-tail recovery) is waiting on the author for a read-only-log fallback.

[3.56.10] - 2026-10-14

Patch release: @claude-flow/cli, claude-flow, ruflo 3.56.10. @claude-flow/memory 3.0.5 (#4183) was published earlier and is pinned exactly. @claude-flow/cli-core 3.7.3 (#3987) was also published earlier and is pinned exactly.

Added

  • ruflo tui draws the console's pictures, looks and motion (console 0.44.0, #4182). The bundled tui.mjs is rebuilt. The TUI draws at the default size when the terminal reports 0 columns (#4160, @martinvlad).

Changed

  • ruflo init: the v3 implementation skills are opt-in, like agents.v3 (#4140, #4139, @z4forzubair).

Fixed

  • The MCP server starts in the session project, CLAUDE_FLOW_CWD naming the home directory or a filesystem root is ignored (cli-core 3.7.3), user-level claims resolve through os.homedir() on Windows, and duplicate or zombie daemons per workspace are stopped (#3987, @socrates6969). Trajectory counts persist across processes and daemon jobs feed learning (#3988, @socrates6969). One node process per MCP session: the launcher runs the resolved local CLI in-process and keeps node:http and the security barrel off the startup path (#3989, @socrates6969; ruflo-core plugin 0.2.10).
  • The console reads the project on Windows: a drive path is absolute, so the cwd is not prefixed twice (#4177, #4175). The neural data directory resolves through the project cwd, and stored worker error text is capped.
  • Hooks and core: failed tool outcomes are recorded, hooks run from the project root, and telemetry stays off the tool path (#4178).
  • Memory: calibrated default search threshold with near-miss hints (#4184, #4129); memory_export reads the CLI store as well as the AgentDB store (#4186, #4148); the AgentDB directory is created before the bridge opens it (#4155, #4132, @martinvlad); TieredMemoryStore recalls multi-word and natural-language queries (memory 3.0.5, #4183, #4152).
  • Intelligence: long memories are recalled for short route prompts (#4172, @rudycelekli); SONA reinforces the nearest pattern for near-identical tasks (#4185, #4134); AIDefence learns missed threats and autopilot learning loads (#4187, #4147, #4146).
  • Workflow: invalid gates and unsupported steps fail closed (#4164, @rudycelekli). Agent health derives from observed execution outcomes (#4167, @rudycelekli).
  • Analyze: diff content and commit subjects drive classification, safe Git revision ranges are accepted, encryption paths are flagged security-sensitive, and the reviewer-role docs are accurate (#4165, #4162, #4169, #4163, @rudycelekli).
  • Security scan: interpolated exec calls after imports are detected (#4166, @rudycelekli); a failed npm audit reports "could not scan" instead of a clean tree (#4154, #4124, @martinvlad).
  • A clear "not installed" message for @ruvector/rvagent-wasm, and only new patterns are counted (#4179, #3979).
  • Skills, plugin contracts and ruvector/neural/kg surfaces (#4181; #4126, #4133, #4135, #4149, #4156-#4159, #4161).

[3.56.9] - 2026-10-12

Patch release: @claude-flow/cli, claude-flow, ruflo 3.56.9, with the bundled leaves @claude-flow/security 3.0.5 and @claude-flow/codex 3.0.5 published standalone and pinned exactly, and @claude-flow/shared 3.0.5 / @claude-flow/cli-core 3.7.2 (published earlier) pinned. Signed helpers changed (hook-handler.cjs, re-signed in #4096).

Fixed

  • Policy envelope (security 3.0.5): explicit envelope ceilings require metering, and unmetered worker ceilings stay opt-in (#3503, @rudycelekli).
  • Codex MCP backend (codex 3.0.5, ruflo wrapper bridge): the opt-in codex backend no longer launches @openai/codex mcp-server, which current Codex CLI dropped, so it is retired without a startup stall (#3522, @rudycelekli; reported in #3509 by @pacphi).
  • CLI parser, retry, rate-limit, monitoring and config fixes: a batch of review findings (#4107; #4000-#4003, #4006-#4011, #4013, #4016, #4017, @rudycelekli and others).
  • analyze diff renders the analyze_diff result shape (#4102, #4101, @z4forzubair).
  • shared 3.0.5 and cli-core 3.7.2: narrow-column truncation, rate-window retry times, structured network error codes (#4014, #4015, #4018, @rudycelekli).
  • ruflo-mods guards (#4096, @proffesor-for-testing): the root-delete guard no longer misses brace, nesting and fork-bomb forms, the screen .env check is fixed, and init-generated hooks carry the changes.
  • Console (marketplace plugin; its tui.mjs is bundled into the CLI): worktree removal runs no fsmonitor or hooks and keeps untracked files (#4092), expired confirm cards are reported by console_state (#4067), pictures draw as SVG on Claude Code Desktop (#4112), all by @proffesor-for-testing; the Skills page pins its skills CLI (#4113, @martinvlad).
  • CI: the v3 root suite runs every test file and a crashed run is no longer accepted as a pass (#4099, @proffesor-for-testing); this does not ship in the package.

[3.56.8] - 2026-10-12

Patch release: @claude-flow/cli, claude-flow, ruflo 3.56.8. @claude-flow/shared 3.0.4 was published earlier and is now pinned exactly (3.56.7 still pinned 3.0.3). No other published package changed since 3.56.7; signed helpers did not change.

Fixed

  • @claude-flow/shared 3.0.4: the RVF event log repairs an incomplete or damaged tail before appending (#4031 by @rudycelekli); a clean install can import ., ./core and ./mcp because zod and express are now declared, and the tarball no longer ships compiled tests (#4089, #4091 by @proffesor-for-testing; the fresh-consumer finding came from @martinvlad, with scripts/smoke-shared-fresh-consumer.mjs).
  • hooks coverage-gaps: files with no executable lines are no longer reported as 0%, overall coverage is line-weighted, the command reads coverage-final.json, and the report size is capped (#4082-#4084, reported by @ronmikailov; #4097). Plugin workflow contracts for ruflo-testgen and ruflo-sparc were corrected in the same change (#4085-#4088; marketplace plugins, not npm).

[3.56.7] - 2026-10-11

Minor-feature patch: @claude-flow/codex 3.0.4 (published standalone; the CLI and root pin it exactly) and @claude-flow/cli, claude-flow, ruflo 3.56.7. Signed helpers changed (#4071, re-signed there).

Added

  • ruflo tui: the ruflo console in a terminal of its own (ADR-489, #4059, #4075, #4076). Six pages, opened with --view or keys 1-6: Overview, Cost, Swarm, Events, Missions (read-only) and an AI page that asks Codex (pinned 0.162.0, read-only) or OpenRouter, each question after a confirm card; --no-ai turns it off and --max-spend-usd (default 0.5) stops sending to OpenRouter once the provider-reported spend reaches it. --plain prints one frame and exits 0; without a terminal it exits 2 with a hint. prepare-publish stages the bundled plugins/ruflo-console/dist/tui.mjs (about 1.27 MB, 446 KB gzipped) into the CLI tarball (about 0.4 MB larger, 3.9 MB packed). Console 0.42.7 is a marketplace plugin, not npm.
  • MCP resources capability on the CLI server, and a three-host integration loop (Claude Code, Codex, OpenRouter) with ADR-490/491 (#4068).
  • doctor flags a better-sqlite3 built against Node 24.19+ headers on Node 24.19-24.21 (#4069, #4074; reported in #4055 by @ronmikailov).
  • ruflo mods: doctor repairs that repair, --strict, atomic install, startup self-check (#4073).

Fixed

  • Auto-memory hooks deliver their subcommand, sync sees learnings, worktrees share the main memory dir, store writes are atomic (#4071, #4058 by @ronmikailov).
  • memory purge keeps the on-disk format on sql.js write-back (#4057); command recording has an off switch and redaction, and memory cleanup --expired-only reaches the bridge store (#4056, #4072; both reported by @ronmikailov).
  • init --dual writes a safe default .codex/config.toml; the previous permissive values now need --codex-trust full (#4070).

Known

  • Nested better-sqlite3 11.x copies under agentdb and agentic-flow still ship; fixing that needs an agentdb release depending on better-sqlite3 ^12. doctor warns on affected Node versions.

[3.56.6] - 2026-10-11

Patch release: @claude-flow/cli, claude-flow, ruflo 3.56.6, with the already-published leaves @claude-flow/cli-core 3.7.1 and @claude-flow/shared 3.0.3 now pinned exactly. Signed helpers changed (hook-handler.cjs) and were re-signed in #4053.

Fixed

  • Windows hooks launch through node -e instead of cmd /c, which started an interactive cmd that executed the hook JSON payload and created stray files (#4045).
  • The settings.json risk scanner now runs on the automatic SessionStart hook; both scanners match encoded PowerShell in linear time (#4052, #4053).
  • Trajectory-end feedback is indexed even when steps were recorded (#3662, #4051).
  • @claude-flow/cli-core 3.7.1 and @claude-flow/shared 3.0.3: JSON memory backend, table/progress output, RVF event log and circuit breaker fixes from a reviewed batch by @rudycelekli (#4061; PRs #4020-#4026, #4028-#4030, #4032, #4033, #4035, #4037).

Plugins (no npm impact)

  • ruflo-cost-tracker: preserve Codex usage ownership (#4048, @Devesh-Maheshwari). ruflo-swarm: host-specific no-op manifest for native Codex hook discovery (#4050). ruflo-adr 0.5.5.

[3.56.5] - 2026-10-11

Patch release: one fix in @claude-flow/cli. No leaf package changed since 3.56.4 (git diff v3.56.4..HEAD -- v3/@claude-flow touches only cli; the integration change drops publishConfig.tag and has no runtime effect).

Fixed

  • The graph-edge-writer encryption-header sniff no longer closes the raw DB file descriptor, which dropped live SQLite POSIX locks; the header is read in a bounded child process (#4044, fixes #4040).

[3.56.4] - 2026-10-10

Patch release: security hardening of the plugin-trust and helper paths, MCP/task fixes, and the Node 24 sqlite fix. Standalone leaves published first: @claude-flow/memory 3.0.4, @claude-flow/integration 3.0.1, @claude-flow/plugins 3.0.2, @claude-flow/mcp 3.1.1 (bundled; republished standalone), @claude-flow/security 3.0.4 (bundled; republished standalone). Then @claude-flow/cli, claude-flow, ruflo 3.56.4.

Security

  • Plugin registry trust: a placeholder (all-zero) trust anchor is a small-order Ed25519 key and no longer vouches for anything; signature verification uses strict (non-ZIP-215) rules; an unsigned registry no longer grants "official" trust (#3948).
  • plugins upgrade no longer runs the new version's postinstall or registers shell:exec hooks without the install-time gate (#3951).
  • Plugin and helper locators stop walking up at node_modules, so a project-local install cannot reach project plugins/ruflo-* code (#3986, replaces #3954).
  • Helpers: session ids and session paths are validated, module roots are no longer project-chosen (#3949); the statusline no longer interpolates HELPER_ROOT into a shell string, and npx runs the helper CLI from the helper root (#3990, replaces #3953).
  • User-level settings pin home helpers (#3952).
  • task_assign rejects __proto__ agent ids that wrote onto Object.prototype (#3967).

Fixed

  • Node 24: better-sqlite3 is routed to a build that does not abort at exit (#3955).
  • Importing the agentic-flow root entry no longer runs its CLI (#3958).
  • MCP resource cache: stale writes are fenced after invalidation (#4019). security scan code patterns no longer report the false positives seen on a real tree (#3999).
  • MCP, task and CLI fixes: #3975, #3974, #3970, #3969, #3968, #3980, #3947; graph path search ~94x faster at n=3200 (#3977).

[3.56.3] - 2026-10-09

Patch release: AgentDB 3.0.0-alpha.20 update. @claude-flow/memory 3.0.3 (published standalone; the CLI pins it exactly) and @claude-flow/cli 3.56.3. neural, shared and cli-core are unchanged.

Changed

  • AgentDB floor raised from ^3.0.0-alpha.17 to ^3.0.0-alpha.20 (memory, cli, root, ruflo). alpha.20 swaps @xenova/transformers for @huggingface/transformers, @ruvector/rvf 0.1.9 -> 0.2.3 and ruvector -> 0.2.x. Semantic search scores shift slightly (same-text cosine ~0.992 against alpha.17 embeddings); an entry scored just under the 0.3 default threshold under alpha.17 can now appear just above it, ranked far below the exact-keyword hit.

Fixed

  • Dev tree only: v3/package.json gains a pnpm.packageExtensions entry declaring onnxruntime-common 1.24.3 for @huggingface/[email protected] (it imports it without declaring it, so pnpm's hoist gave it 1.14.0 and AgentDB silently fell back to mock embeddings in the pnpm workspace; npm installs were not affected).
  • AgentDB alpha.20 refuses a sql.js save when the database changed under an open handle or when <db>.agentdb.lock exists, and a lock left by a crashed writer was never cleared, so every later save failed and the database file was never created. @claude-flow/memory now removes that lock only when it is provably stale (regular file named exactly <db>.agentdb.lock, numeric PID that is dead, older than 10 s, re-verified after an atomic rename-aside), retries once, and otherwise throws AgentdbLockError. A failed persist on shutdown is surfaced (ControllerRegistry, AgentDBBackend, HybridBackend, shutdownBridge), never swallowed. This only affects the sql.js path (no native better-sqlite3).

[3.56.2] - 2026-10-09

Patch release: one bug fix in @claude-flow/cli. No leaf package changed since 3.56.1 (git diff v3.56.1..HEAD -- v3/@claude-flow touches only cli). The ruflo-console fixes merged since 3.56.1 (console 0.40.4-0.40.8, #3933, #3935, #3938, #3941, #3942) and ruflo-swarm 0.3.6 ship through the plugin marketplace, not this npm release.

Fixed

  • task_update accepts only the five task statuses; a task stored as complete is no longer shown as pending or re-dispatched (#3932, fixes #3931).

[3.56.1] - 2026-10-08

Patch release: five bug fixes (four in @claude-flow/cli, one console). No leaf package changed since 3.56.0 (git diff v3.56.0..HEAD -- v3/@claude-flow touches only cli), and no behaviour is removed. The ruflo-console plugin fixes merged since 3.56.0 (console 0.40.2/0.40.3, #3917, #3924) ship through the plugin marketplace, not this npm release.

Fixed

  • The policy trust mirror and key now honour HOME and XDG_CONFIG_HOME instead of a fixed home directory, so a throwaway HOME no longer yields policy-anchor-log-missing (#3922, fixes #3919, reported by @HF-teamdev).
  • ensureSchemaColumns rewrites the store only when a column was actually added; an up-to-date encrypted memory store is no longer rewritten by a read such as memory stats (#3923, fixes #3918, reported by @HF-teamdev).
  • config reset --section <name> resets only that section and removes the matching flat overrides, preserving unrelated configuration (#3901, @rudycelekli).
  • MCP config tools (config_get/set/list/export/import/reset) now work on the plain nested JSON document written by the config CLI command instead of assuming a {values, scopes} envelope; existing envelope stores keep their format (#3902, @rudycelekli). This does not change how the daemon reads config.json (see #3192, #3449, #3239).
  • Console approvals badge counts only rows that have an approve or deny action (#3924, fixes #3920, reported by @HF-teamdev); delivered as ruflo-console 0.40.3 via the plugin marketplace.

[3.56.0] - 2026-10-08

Minor release: a hardening and correctness batch from @rudycelekli, @nicholas-ruest, @martinvlad, @HF-teamdev, @drakeo338 and @stuinfla. Several fixes change behaviour on purpose (see Behaviour changes). Integrated by merging each PR head, so authorship is preserved.

Behaviour changes

  • Unknown ids and value-less options are now errors (#3911, @martinvlad) β€” agent status / task status with an unknown id print not found and exit 1; a declared string/number option with no value (hooks route --task) now reports Option --task needs a value instead of silently becoming true. Applies to every command.
  • session_save captures the persisted task/agent/memory stores by default, and session_import rejects malformed stores (#3489, #3490); explicit false still excludes a store.
  • Default project memory backup snapshots both memory.db and agentdb-memory.db (#3903); explicit --db and a non-blank CLAUDE_FLOW_DB_PATH still select one file.
  • Agent pool scale-to-zero is honored and invalid targets fail before writing (#3488); a zero fallback retry budget is honored (#3496).
  • Project path validators block sensitive directory names anywhere under the project root, not only at the leaf (#3504, @claude-flow/security 3.0.3).
  • The OAuth callback server retains an early callback and ignores unrelated requests (#3507, @claude-flow/security 3.0.3).
  • Provider selection honors an explicit execution provider (#3493) and Anthropic gateway credentials/endpoint (ANTHROPIC_AUTH_TOKEN, ANTHROPIC_BASE_URL; #3494, fixes #3100); provider timeouts now cover reading the response body (#3495).
  • hooks_route consults persisted SONA outcome patterns before local routing (#3904) β€” only a supported agent at confidence >= 0.6 is used; useSemanticRouter: false keeps keyword routing. With the opt-in neural router, selection uses calibrated quality predictions (#3498) so calibration can move the pick across the quality bar.
  • The WAL-sidecar safety gate is liveness-based (#3894, fixes #3161) β€” leftover -wal/-shm files from a closed connection no longer block memory store/list; a genuinely open holder is still refused.
  • ruflo init no longer pins a Claude model in generated .claude/settings.json (#3528, fixes #3527).
  • The ruflo wrapper pins the matching @claude-flow/cli and warns when the resolved CLI version differs (#3438, fixes #3306); it warns and continues, it does not refuse.
  • Claims are stored in one lossless format shared by CLI and MCP; unreadable stores are refused rather than replaced (#3502).
  • Native immutable conditional append for memory store (--append-only, --append-conditions, --require-native, --no-embedding; #3750, @stuinfla) β€” additive, CLI only.

Fixed

  • Shipped .claude/settings.json had unescaped quotes in hook commands and did not parse (#3895, fixes #3888, @nicholas-ruest); a new test checks that every shipped settings/plugin JSON parses.
  • Remaining better-sqlite3 opens go through the shared loader (#3896, fixes #3883's sites, @nicholas-ruest); an RFE1-encrypted store is reported as encrypted, not broken (#3906, fixes #2889, @nicholas-ruest); the demo-registry fallback is labelled as unverified (#3897, @martinvlad).
  • analyze preserves machine-readable JSON (#3910); doctor rejects unsupported component selections (#3907) and loads MetaHarness modules via file URLs on Windows (#3523, fixes #3186); daemon start honors explicit scheduled workers (#3586).
  • Unreadable task/agent records are preserved, not overwritten (#3484); async agent-registry updates do not revive retired agents (#3492); fallback learning is attributed to each attempted model (#3497).
  • Workflow step boundaries are validated (#3491), persisted workflows resume without duplicate executors (#3500) and keep control signals and sibling state across awaits (#3505).
  • Memory JSON import reports rejected writes accurately (#3499); export reads all pages only after successful reads (#3501); concurrent rotating-token refreshes coalesce (#3506).
  • Test fixtures no longer break under pnpm's NODE_PATH (#3543, fixes #3529) and the vitest runner is resolved via package.json.
  • @claude-flow/memory 3.0.2: cache admission accounts for replacement sizes (#3679, fixes #3678) and invalidation matches each key independently (#3687, fixes #3686).
  • Removed an empty .claude/agents/tmp.json that shipped in the CLI tarball.

Not included

#3503 (fail-closed policy envelope: it would deny MCP dispatch for any envelope with a ceiling because dispatch does not supply the metering), #3892, #3831, #3879, #3835, #3751, #3694, #3909 and the draft security PRs: see each PR for the status.

Leaf packages published with this release

@claude-flow/memory 3.0.2, @claude-flow/security 3.0.3.

[3.55.0] - 2026-10-07

Minor release. Contains a security behaviour change: ruflo mcp start -t http on a non-loopback host now refuses to start without a token (see Security and Breaking changes).

Security

  • MCP HTTP transport: refuse unauthenticated non-loopback binds, optional bearer-token auth (#3598, #3599) β€” ruflo mcp start -t http --host 0.0.0.0 (or any non-loopback host) now exits 1 unless a token is set (RUFLO_MCP_HTTP_TOKEN, --auth-token-file, --auth-token) or the operator opts out with RUFLO_MCP_ALLOW_UNAUTHENTICATED_HTTP=1. With a token, /rpc, /mcp and /info need Authorization: Bearer <token> (constant-time compare); /health stays public and minimal. Also fixes a fail-open in @claude-flow/mcp where auth enabled with an empty token list accepted any bearer value. Not closed: loopback with no token is still unauthenticated (any local process can call every tool, and DNS rebinding is not blocked because there is no Host allow-list); set a token whenever the HTTP transport is used. A valid token grants every tool (no per-tool authorization).
  • Hive-mind gating that keeps local users working (ADR-476, #3338, #3339) β€” hive-mind_init no longer returns hiveToken, and spawn, consensus propose, broadcast, shutdown, memory set/delete and optimize-memory (plus the existing join/leave/vote) now require an operator credential from remote callers (HTTP/WebSocket MCP). Local stdio MCP, ruflo mcp exec, the hive-mind CLI and in-process callers need no credential and no extra step. Remote clients set RUFLO_HIVE_BOOTSTRAP_SECRET (or read .claude-flow/hive-mind/bootstrap.secret, created 0600 by the first local hive-mind init) and send it as bootstrapSecret; RUFLO_HIVE_REQUIRE_AUTH=1 applies the same rule to stdio on bridged servers. state.json is now written 0600 atomically and the hive directory 0700. Migration: clients that read hiveToken from the init response must drop that (it is undefined); over stdio they omit it everywhere. This is a speed bump, not a boundary, against a local prompt-injected agent that can read the files.
  • Policy ledger anchor can no longer be deleted and silently re-established (#3602, #3886, ADR-475) β€” policy verify no longer trusts an anchor stored only in state.json. A second, hash-chained anchor log plus a mirror under ~/.config/ruflo/policy-trust/ now detect truncation, and policy verify --establish-anchor (interactive TTY only) is the logged repair path. Limit: this does not defend against an attacker who can rewrite both the project directory and ~/.config/ruflo; stronger evidence needs an external witness. A pre-#3568 ledger with receipts and no anchor now fails policy transactions with policy-ledger-anchor-missing until repaired. Ships in @claude-flow/security 3.0.2.

Fixed

  • Resilience batch (#3885; fixes #3676 #3674 #3668 #3670 #3682 #3672 #3593 #3592; thanks @rudycelekli) β€” @claude-flow/shared 3.0.2: event-store pagination, bulkhead sync-throw handling, retry timeout cleanup, connection-pool reservation (also in @claude-flow/mcp); cli: production retry on non-Error rejections, worker-queue terminal outcomes and cancelled head, bounded worker pool with an already-aborted input.
  • @claude-flow/memory 3.0.1 β€” mmrRerank() caches embedding-cosine max-similarity across rounds (#3516, #3517).
  • @claude-flow/swarm 3.0.1 β€” Byzantine quorums now intersect for every cluster size (#3560, #3587, @rudycelekli); spawnAgent() auto-domain branch registers the agent in its pool (#3538, #3539); MessageBus is event-driven instead of a 10 ms unconditional poll (#3563).
  • @claude-flow/plugin-agent-federation 1.0.1 β€” outbound sends are authorized with the peer's current trust, not a stale snapshot (#3561, #3588, @rudycelekli).
  • CLI string options keep their declared value (#3594, #3601), config cache is isolated per project directory (#3590, #3591), nested config defaults are cloned (#3595, #3600) β€” all @rudycelekli.
  • Hive consensus commands fail when the hive rejects the operation (#3609, #3654, @rudycelekli).
  • daemon start --workers selection reaches the WorkerDaemon (#3547, #3875).
  • Plugins run the installed ruflo CLI before npx @claude-flow/cli@latest (#3558, #3559, @HF-teamdev) β€” ruflo-cost-tracker 0.27.2, ruflo-adr 0.5.4, ruflo-metaharness 0.2.4, ruflo-goals 0.4.3.
  • ruflo-adr edge keys use a separator the memory validator accepts (#3633, #3636, @drakeo338).
  • ruflo-console 0.36.1: Settings lists Claude control and spending first (#3887).

Breaking changes

  • Binding the MCP HTTP transport off loopback (for example Docker with --host 0.0.0.0) now requires RUFLO_MCP_HTTP_TOKEN (and clients must send the header) or RUFLO_MCP_ALLOW_UNAUTHENTICATED_HTTP=1; otherwise mcp start exits with an error. Loopback users are unaffected.
  • hive-mind_init no longer returns hiveToken (ADR-476).

Leaf packages published with this release

@claude-flow/shared 3.0.2, @claude-flow/memory 3.0.1, @claude-flow/swarm 3.0.1, @claude-flow/security 3.0.2, @claude-flow/mcp 3.1.0, @claude-flow/plugin-agent-federation 1.0.1.

[3.34.0] - 2026-07-31

Added

  • AGNTCY/Outshift runtime integration (ADR-378/379/380) β€” optional, removable augmentation per ADR-150's pattern; the kernel stays fully operational with these packages absent. ruflo transport use slim, ruflo agent publish, and ruflo swarm join <namespace> CLI verbs; CASA (Continuous Agentic Semantic Authorization) envelope schema, deterministic compiler, and deny-by-default enforcement gate with Ed25519-signed decision receipts (.swarm/casa-receipts.jsonl); AGNTCY OTel span attributes (coordination.episode, authorization.decision). All verbs exit 0 with a clear message when RUFLO_AGNTCY_SLIM_ENDPOINT is unset β€” no fake success paths. Companion Rust crate v3/crates/ruflo-agntcy mirrors the TS enforcement logic, with a real in-process LocalTransport and a SlimTransport stub behind a non-default slim Cargo feature. Companion package @metaharness/agntcy (build-time half β€” identity, OASF export, Directory publish, semantic observability) ships from the sibling metaharness repo. (v3/@claude-flow/cli/src/commands/agntcy/, plugins/ruflo-agntcy/, v3/crates/ruflo-agntcy/, v3/docs/adr/ADR-378-*.md, ADR-379-*.md, ADR-380-*.md)
  • npm Trusted Publishing (OIDC) release workflow (ADR-378) β€” .github/workflows/stable-npm-release.yml publishes the three-package stable train (@claude-flow/cli, claude-flow, ruflo) from an immutable, tag-pinned checkout with a full test/build/pack/install smoke-test gate before any registry write, verifies published-package integrity against the locally-built archive, and rolls out latest/alpha/v3alpha dist-tags together. Manual workflow_dispatch only, gated to the ruvnet actor.
  • Configurable statusline cost segment via two environment variables (defaults unchanged):
    • RUFLO_STATUSLINE_COST_SYMBOL β€” override the leading $ (e.g. ⚑, €, 🌱); empty string shows the number alone.
    • RUFLO_STATUSLINE_HIDE_COST β€” 1/true/yes/on hides the segment. cost.total_cost_usd is a client-side estimate that may differ from the actual bill and is misleading on subscription plans.

Fixed

  • @agntcy/slim-bindings pinned to the confirmed-working alpha β€” the SLIM maintainers moved off uniffi-bindgen-react-native (which shipped raw, uncompiled TypeScript incompatible with plain Node require/import β€” filed as agntcy/slim#1916, reproduced and confirmed) onto @ubjs/core/@ubjs/node in the 2.0.0-alpha.4+ dist-tag, not yet promoted to latest. v3/@claude-flow/cli/package.json now pins the exact working alpha version (deliberate exact-pin for a pre-release channel, not a caret range) rather than the still-broken latest; verified live end-to-end (server bring-up, client connect, graceful shutdown, zero ERR_UNSUPPORTED_NODE_MODULES_TYPE_STRIPPING). detectAgntcyRuntime() required zero logic changes β€” its existing graceful-degradation design already returned configured: true once the upstream package resolved.
  • security scan failed open on unvalidated --depth / --type / --target β€” an unrecognised --type matched none of the three phase guards, so no phase ran at all and the command still printed "No security issues found!" and exited 0; an unrecognised --depth fell through chained ternaries to the shallowest traversal (so --depth full scanned less than the default standard), which on a tree whose only HIGH finding sat below that budget also flipped the critical/high exit-code gate from 1 to 0; and a non-existent or non-directory --target read nothing, which the swallowed dir-read catches turned into a clean banner, exit 0, and a persisted CLEAN report that getSecurityStatus then surfaced as CLEAN. All three now fail closed before anything is scanned or written. Chained ternaries replaced with exhaustive Record<ScanDepth, number> maps behind real type predicates, and the recursion guard now positive-tests its budget so a bad value stops traversal instead of disabling the limiter. (v3/@claude-flow/cli/src/commands/security.ts)

Changed

  • security scan --depth full is deprecated, not removed β€” full was never a supported depth, but the CLI itself emitted it (statusline insight, announcement, the CLAUDE.md init generates, two shipped agent definitions). It is now normalised to deep with a warning rather than rejected, and those emitters have been updated to --depth deep. (v3/@claude-flow/cli/src/funnel/insights.ts, funnel/messages.ts, commands/announcements.ts, init/claudemd-generator.ts, .claude/agents/v3/security-architect*.md)

Removed

  • security scan --type container is rejected instead of silently reporting clean β€” it had been advertised in --type's help since the command was written, but no phase ever implemented it, so it scanned nothing and printed a clean bill of health. It now exits 1 with an explicit "not implemented" message, and the help text no longer offers it. Breaking for any pipeline passing --type container, which previously exited 0. (v3/@claude-flow/cli/src/commands/security.ts)

[3.32.10] - 2026-07-26

Bug-fix release closing the tracker-fire sweep from 2026-07-24 β†’ 2026-07-26. All fixes are surgical and additive; no API surface change, no schema change, patch semver.

Fixed

  • Statusline promo row blank on new installs β€” restored the cold-start local seed pool that ADR-311 had emptied. The remote Cognitum-served pool (funnel.ruv.io/v1/messages) remains authoritative via eligibleMessagesFromPools (remote wins by id); the seed only renders during the ≀ 60s cold-start window before the first successful remote fetch lands. Nine seed messages ship: one disclosure, seven educational tips (all pointing at cognitum.one docs), one promotional. (v3/@claude-flow/cli/src/funnel/messages.ts)
  • #2777 β€” ruflo init no longer imports the entire ruvnet/ruflo repo (97 MB, 384 SKILL.md) into .agents/skills/ruflo/. Materialization now writes only the single platform SKILL.md, and the idempotency gate detects a "bloated" prior install (Cargo.toml/crates/ present or size > 1 MB) and wipes+re-materializes. (v3/@claude-flow/cli/src/commands/init.ts)
  • #2781 β€” ruflo-adr adr-index no longer silently drops ADR data: status regex accepts the - **Status**: proposed form adr-create emits, single-line and wrapped relation lines parse fully, and CLI_CORE=1 no longer forks writes into an alternate store the default reader can't see (warns and unifies on @claude-flow/cli@latest). Dry-run over the repo's 531 ADRs now captures 608 edges cleanly. (plugins/ruflo-adr/scripts/lib/parse-adrs.mjs, import.mjs, reindex.mjs)
  • #2770 β€” Windows: browser-session MCP tools and two init-flow execFileSync('npx', …) sites now set shell: process.platform === 'win32' so cmd.exe can resolve npx.cmd. POSIX behavior unchanged. Each site carries a shell-injection note for future editors. (v3/@claude-flow/cli/src/mcp-tools/browser-tools.ts, v3/@claude-flow/cli/src/commands/init.ts)
  • #2782 β€” WorkerDaemon.saveState(), autopilot-state.saveState(), and autopilot-state.appendLog() no longer race on a shared .tmp filename under in-process concurrent workers. All three sites now call the existing writeFileAtomic helper (pid + timestamp + random-suffixed temp) so concurrent callers cannot collide; each write is wrapped in try/catch so a losing racer can't crash the daemon. (v3/@claude-flow/cli/src/services/worker-daemon.ts, v3/@claude-flow/cli/src/autopilot-state.ts)
  • #2785 β€” ruflo hooks post-task now accepts --task (short -t) and --store-results flags, matching the CLAUDE.md-documented usage. Routing outcomes finally persist to the namespace hooks_metrics reads, so the "Pattern Learning" / "Agent Routing" numbers become non-zero. (v3/@claude-flow/cli/src/commands/hooks.ts)
  • #2786 β€” AgentDB no longer silently fails to initialize when CLAUDE_FLOW_ENCRYPT_AT_REST=1 is set. Added getAgentDbPath() which returns the same directory as getDbPath() but with basename agentdb-memory.db, so the ControllerRegistry (native better-sqlite3) opens a distinct file from the sql.js CRUD writer's memory.db (which stays encrypted). learningSystem/reasoningBank populate correctly with encryption enabled. (v3/@claude-flow/cli/src/memory/memory-bridge.ts)
  • #2776 β€” Statusline security segment: STALE and IN_PROGRESS states are now reachable via a local overlay (getLocalSecurity) that recomputes freshness on every render from .claude/security-scans/scan-*.json. Configurable via RUFLO_SCAN_STALE_HOURS (default 24) and RUFLO_SCAN_PENDING_CAP_MIN (default 30); STALE renders dim gray so it stops shouting for attention once escalated. (.claude/helpers/statusline.cjs)
  • #2775 β€” Memory store to an existing key no longer dead-ends: bridgeStoreEntry uses INSERT ... ON CONFLICT with tombstone auto-resurrect; UNIQUE returns a typed error instead of null (no more misleading demotion into the #2735 guard); bridgeDeleteEntry runs wal_checkpoint(PASSIVE); CLI memory store --upsert default now applies at the parser layer (root cause: parser.ts:applyDefaults only walked globalOptions); the memory_store MCP tool schema defaults upsert: true for CLI parity. (v3/@claude-flow/cli/src/memory/memory-bridge.ts, commands/memory.ts, parser.ts, mcp-tools/memory-tools.ts)

Investigated

  • #2774 β€” Reporter's diagnosis "Codex MCP generator registers management CLI instead of stdio server" appears incorrect: ruflo mcp start IS a working stdio server per v3/@claude-flow/cli/src/commands/mcp.ts (MCP Server started on stdio), and upstream d20f1323b fix(codex): ship stable Windows-safe Ruflo integration cleanly centralized the Codex MCP config in mcp-config.ts using the same command shape. A proposed swap to claude-flow-mcp was reverted during rebase. Recommend closing the issue unless the reporter can produce a fresh repro against 3.32.9+.

[3.5.0] - 2026-02-27

Ruflo v3.5 β€” First Major Stable Release

This release marks the official rebranding from Claude Flow to Ruflo and represents the first major stable release after 5,800+ commits, 55 alpha iterations, and 10 months of development.

Highlights

  • Rebranding: Claude Flow β†’ Ruflo across all packages (@claude-flow/cli, claude-flow, ruflo)
  • agentic-flow v3.0.0-alpha.1 Integration: Full deep integration with 10 subpath exports (ReasoningBank, Router, Orchestration, Agent Booster, SDK, Security, QUIC transport)
  • AgentDB v3.0.0-alpha.9: 8 new controllers (HierarchicalMemory, MemoryConsolidation, SemanticRouter, GNNService, RVFOptimizer, MutationGuard, AttestationLog, GuardedVectorBackend) + 6 MCP tools
  • 215 MCP Tools: Full Model Context Protocol server with vector memory, neural training, swarm coordination
  • Security Hardening: Command injection fix, TOCTOU race fix, eliminated hardcoded HMAC keys, timing attack fixes
  • Doctor Health Check: New agentic-flow diagnostic (filesystem-based, ESM-compatible)
  • 0 Production Vulnerabilities: Clean npm audit across all packages

Added

  • agentic-flow-bridge.ts β€” Unified lazy-loading bridge for all agentic-flow v3 modules
  • Tiered embedding resolution: ReasoningBank WASM (Tier 1) β†’ @claude-flow/embeddings (Tier 2) β†’ mock fallback (Tier 3)
  • Agent Booster local import with npx fallback
  • checkAgenticFlow() doctor health check
  • 7 TypeScript module declarations for agentic-flow subpath exports
  • ADR-056: agentic-flow v3 Integration Architecture

Fixed

  • Command injection vulnerability in enhanced-model-router.ts (SAFE_LANGUAGES whitelist)
  • TOCTOU race condition in bridge singleton initialization (Promise-based caching)
  • 22 agent/skill files updated from stale v1.5.11/v2.0.0-alpha to v3.0.0-alpha.1
  • ESM compatibility for doctor checks (filesystem-based instead of require.resolve)
  • @ruvector/gnn pinned to 0.1.25 to fix fatal process crash (issue #216)

Changed

  • All 3 packages bumped from 3.1.0-alpha.55 to 3.5.0
  • Publish tags changed from alpha/v3alpha to latest
  • agentic-flow minimum version: 0.1.0 β†’ 3.0.0-alpha.1
  • agentdb minimum version: 2.0.0-alpha.3.4 β†’ 3.0.0-alpha.10

[3.1.0-alpha.55] - 2026-02-27

AgentDB 3.0.0-alpha.9 Integration (ADR-053/ADR-055)

  • Activated 8 AgentDB v3 controllers with MutationGuard proof engine
  • Added 6 new MCP tools: agentdb_hierarchical_*, agentdb_consolidation_*, agentdb_semantic_*
  • Fixed controller registry activation bugs (ADR-055)
  • Statusline fixes for real-time controller status
  • Pinned @ruvector/[email protected] to fix fatal process crash

[3.1.0-alpha.43] - 2026-02-15

Ruflo Branding Fix

  • Fixed CLI branding: show 'ruflo' instead of 'claude-flow' when run via npx ruflo
  • Fixed Windows ESM import crash with pathToFileURL
  • Fixed init hook prompt overflow and description field

[3.1.0-alpha.36] - 2026-02-10

Stability & Compatibility

  • Fixed hooks backward compatibility: --success and --file made optional
  • Fixed Windows npm install crash (404 optional dependencies)
  • Bumped agentdb to 2.0.0-alpha.3.6
  • Fixed V3 build errors (missing helmet, VERSION type, vitest spy)

[3.1.0-alpha.29] - 2026-02-01

Security & Agent Teams

  • Security fixes, backward compatibility, and Agent Teams hooks
  • Added --settings flag to upgrade command for Agent Teams
  • Fixed npm 11 install crash by pinning agentdb

v3.0.0-alpha Series (2025-10 to 2026-02)

v3.0.0-alpha.184 β€” CLI Help & Categorization (2025-12)

  • Fixed CLI help categorization across 26 commands
  • Published install optimizations
  • curl-style installer script
  • SEO-optimized npm packages for discovery

v3.0.0-alpha.170 β€” Plugins & Marketplace (2025-12)

  • Plugin Marketplace: 8 official plugins + IPFS registry via Pinata
  • Gas Town Bridge Plugin: WASM-accelerated orchestrator integration
  • 10 RuVector WASM Plugins: 50 MCP tools for neural computation
  • @claude-flow/teammate-plugin: MCP tools for Agent Teams coordination

v3.0.0-alpha.150 β€” SONA & SemanticRouter (2025-11)

  • SemanticRouter: SONA WASM integration with verified benchmarks
  • Fixed phantom Claude popups on Windows
  • Fixed statusline safe multi-line output for Claude Desktop
  • Fixed MCP tool naming (/ β†’ _) for Claude Desktop compatibility
  • Memory namespace support in delete command

v3.0.0-alpha.100 β€” @claude-flow/guidance (2025-11)

  • @claude-flow/guidance Control Plane: Governance, compliance, and policy enforcement
  • Wave 1: Proof, gateway, memory-gate, coherence, hooks, persistence primitives
  • Wave 2: Conformance kit, capability algebra, evolution pipeline, artifact ledger
  • Wave 3: Civilization-grade primitives (trust, truth, uncertainty, time, authority)
  • Rust WASM Policy Kernel: SIMD128-accelerated policy evaluation
  • ContinueGate: Safety gate for agent continuation decisions
  • 22-benchmark suite with before/after performance reporting
  • CLAUDE.md generators, analyzer, and auto-optimizer
  • Content-aware executor with statistical validation (Spearman ρ, Cohen's d)

v3.0.0-alpha.50 β€” Core V3 Implementation (2025-10)

  • Complete V3 implementation across all ADRs
  • ADR-003: Coordinator consolidation + security tests
  • Complete hooks system with AgentDB, HNSW, tests
  • ReasoningBank guidance system with CLI
  • V2β†’V3 migration documentation
  • MCP memory tools upgraded to sql.js + HNSW backend
  • Claims-based authorization (ADR-016)
  • Node.js worker daemon system
  • Auto-update system for @claude-flow packages (ADR-025)
  • Replaced all mock implementations with real functionality

v3.0.0-alpha.1 β€” Foundation (2025-10)

  • Complete V3 monorepo structure (@claude-flow/cli, shared, memory, hooks, security)
  • 26 CLI commands with 140+ subcommands
  • 215 MCP tools via FastMCP 3.x
  • RuVector intelligence system (SONA, MoE, HNSW, EWC++, Flash Attention)
  • Hive-Mind consensus (Byzantine, Raft, Gossip, CRDT, Quorum)
  • 17 hooks + 12 background workers
  • 60+ specialized agent types
  • Cross-platform helper system

v2.7.x Series (2025-08 to 2025-10)

v2.7.34 β€” PostgreSQL & Neural Persistence

  • PostgreSQL Bridge with attention, GNN, hyperbolic embeddings
  • Neural pattern persistence to disk
  • Hive-mind --claude flag for spawn command
  • Real statusline data, hive-mind shutdown fixes, daemon persistence
  • Multi-platform builds (Linux, macOS, Windows) in CI/CD

v2.7.0 β€” agentic-flow Integration

  • Deep integration with agentic-flow coordination engine
  • SDK architecture analysis and hooks & learning integration
  • Modular installation strategy
  • Optimized v3 migration plan

v2.0.0-alpha Series (2025-05 to 2025-08)

v2.0.0-alpha.128 β€” Maturity

  • Comprehensive hive-mind optimization
  • Database schema robustness (missing columns, optimization errors)
  • Auto-rebuild better-sqlite3 on NODE_MODULE_VERSION mismatch
  • InMemoryStore interval cleanup for clean process exit

v2.0.0-alpha.53 β€” Hook Safety

  • Critical hook safety system
  • Hive-mind optimization command
  • Safety & security features documentation
  • Neural Link System with safety protocols

v2.0.0-alpha.33 β€” Windows & WSL

  • Windows/WSL compatibility fixes
  • Module import error resolution
  • README restructure for v2.0.0 features
  • Comprehensive test suite

v1.x Series (2025-01 to 2025-05)

v1.0.71 β€” Final v1 Release

  • npm publishing compatibility
  • Full CLI command functionality
  • SPARC integration with full prompt loading
  • Cross-platform support

v1.0.50 β€” Swarm & SPARC

  • Parallel execution for swarm tasks
  • Background task management
  • Swarm command with improved error handling
  • Claude Code slash commands integration

v1.0.28 β€” Project Management

  • CLI project management commands
  • System monitoring and SPARC commands
  • Orchestration templates (monitoring, optimization, security review)

v1.0.1 β€” Initial Release (2025-01-01)

  • Complete Claude-Flow AI Agent Orchestration System
  • Configuration guide and comprehensive tests
  • Initial commit

Milestone Summary

Milestone Version Date Key Feature
Initial Release v1.0.1 2025-01 AI agent orchestration system
SPARC Integration v1.0.50 2025-03 Swarm + SPARC methodology
Alpha Foundation v2.0.0-alpha.33 2025-05 V2 alpha with hook safety
agentic-flow v2.7.0 2025-08 agentic-flow coordination engine
V3 Foundation v3.0.0-alpha.1 2025-10 V3 monorepo, 215 MCP tools
Plugin Marketplace v3.0.0-alpha.170 2025-12 8 plugins + IPFS registry
Guidance Control Plane v3.0.0-alpha.100 2026-01 WASM policy kernel, ContinueGate
AgentDB v3 v3.1.0-alpha.55 2026-02 8 controllers, MutationGuard
Ruflo v3.5 v3.5.0 2026-02-27 First stable release, rebranding