No breaking changes, drop-in upgrade.

Added

• Cursor plugin: 7 auto-capture hooks + 17 skills + MCP, IDE and cursor-agent CLI
• Devin support: connect devin --with-hooks (6 native hooks) and a Devin plugin manifest for /agentmemory:<skill> commands
• DeepSeek Harness connector (connect dsh), with --with-hooks for full auto-capture
• connect pi now actually installs the extension; capture reaches parity with the Claude Code plugin
• Two new skills, 15 → 17: memory-discipline (when to recall and save) and /lesson (corrections become confidence-weighted rules)
• Write-time provenance on every record: origin channel stamped at capture, save, and import
• Keyless graph extraction: the knowledge graph now populates without an LLM key
• AGENTMEMORY_LLM_NOTHINK=1 to skip the hidden thinking pass during graph extraction
• Viewer clarity pass: two-pane session explorer, expandable records, honest zero states

Fixed

• MCP initialize now negotiates the client's protocol version instead of hardcoding 2024-11-05 (#908)
• Hybrid BM25 + vector + graph ranking reaches memory_recall, not just smart-search
• Superseded memory versions leave the search indexes; recall stops returning stale facts as current
• Lesson recall runs off a real index instead of scanning the whole corpus per query
• agentId threads through every save path (#1159, #1160, #1197)
• Prompt dedup no longer swallows prompts after the first in a TTL window (#1173)
• Stop hook no longer summarizes twice (#1203)
• Per-session project attribution in the OpenCode plugin (#1188)
• Safe agentmemory stop in Docker mode (#1151)
• ~/.agentmemory/.env now applies to every module at boot

Changed

• Provider default models bumped to current generations (OpenAI, Anthropic, Gemini, MiniMax, OpenRouter); explicit *_MODEL overrides unaffected

Full changelog: v0.9.28...v0.9.29

No breaking changes, drop-in upgrade.

Security

• Closed cross-agent memory leak via /agentmemory/context under AGENTMEMORY_AGENT_SCOPE=isolated (#1057)

Fixed

• Hooks no longer crash ("hook exited with code 1") on a null payload from Codex CLI / Claude Code (#1047)
• Engine conflict no longer hangs in a WS reconnect loop; clean recovery and pinned-engine guidance (#984)
• Onboarding stat drift and over-strict engine version gate (#852)

Added

• agentmemory demo --serve: one-command seed and recall demo, no second terminal (#852)
• opencode connect adapter; onboarding agent picker single-sourced from adapters (#883)
• Session summaries now returned by GET /agentmemory/sessions (#882)
• 15 detailed, self-updating skills covering the whole system (#854)
• Agent-driven install runbook (INSTALL_FOR_AGENTS.md) and Windows/WSL2 clarity (#853)
• Colored CLI output and quieter boot (#984)

Full changelog: v0.9.27...v0.9.28

Wave release closing several breaking regressions reported against v0.9.26, plus an agent-scope isolation security fix, an iii version-pin audit fix, and a benchmark scorecard correction. No breaking changes; drop-in upgrade.

Security

• AGENTMEMORY_AGENT_SCOPE=isolated not enforced on mem::search / POST /agentmemory/search / memory_recall / recall_context (#817). PR #654's isolation work covered smart-search, /memories, /observations, and /sessions but missed the BM25-only recall path. An isolated worker booted with AGENT_ID=B could read agent A's memories via the standard MCP memory_recall tool. Fail-closed: if isolated mode is on and no agent id resolves, the call throws rather than dropping the filter.

Fixed

• /graph/query and /graph/stats timed out with "Invocation stopped" on large existing corpora (#814, PR #816). Refactored mem::graph-extract to maintain three side-indexes (graphNameIndex, graphEdgeKey, graphNodeDegree) so every extract path is O(1), never O(n). Hot path reads exclusively from a precomputed top-degree snapshot updated inline on every extract.
• All data lost on agentmemory stop followed by restart (#843). Stop order inverted: worker first with a 5s SIGTERM grace so index flush can land, engine second.
• mem::graph-snapshot-rebuild and mem::graph-reset heartbeat-crashed on legacy >25K-node corpora (#825). Rebuild now refuses pre-flight when no prior snapshot exists. Reset is now enumeration-free: writes empty snapshot with resetAt epoch marker. Future extracts treat any pre-resetAt row as orphan.
• Multi-instance port collisions on one host (#750, PR #815). --port N now drags streams + engine. New --instance N shortcut picks a 100-port block.
• iii console install pulled latest engine instead of the pinned v0.11.2 (audit). Install command now passes VERSION=${IIPINNED_VERSION}. Render path is platform-aware: Windows users get a PowerShell hint.

Added

• POST /agentmemory/graph/snapshot-rebuild (≤25K nodes, force: true to bypass).
• POST /agentmemory/graph/reset enumeration-free clean-restart.
• --instance N CLI flag for multi-daemon (max N=50).
• GraphSnapshot.topDegrees, GraphSnapshot.resetAt, GraphQueryResult.fromSnapshot, GraphQueryResult.warning.

Changed

• REST endpoint count: 126 → 128.
• mem::graph-stats reads exclusively from snapshot.
• mem::graph-query empty-body / nodeType path reads exclusively from snapshot.
• mem::search over-fetch triggers on agentId filter too.

Docs

• Corrected coding-agent-life-v1 P@5 numbers (#796).
• README refresh: stats 174 files / 1,390+ tests / 258 functions; "New in vX.Y.Z" callout removed.
• import-jsonl users warned about Claude Code's cleanupPeriodDays 30-day default.

Full changelog: CHANGELOG.md

Hotfix on top of v0.9.25. Closes #797.

Fixed

• First boot crash: TypeError: Cannot read properties of undefined (reading 'v') (#797). The sharded index load path checked manifest.value !== null before forwarding, but some iii-state adapters return undefined (not null) for a missing key. loadManifestData(undefined) then crashed on undefined.v. Now treats both null + undefined + non-object values as 'no manifest' and falls through to the legacy load path.

Self-healing was already in place — the next debounced save rebuilt a fresh manifest — but the crash on first boot scared every fresh upgrader.

Upgrade

npm install -g @agentmemory/agentmemory@0.9.26

If you already saw the warning on v0.9.25 and the daemon kept running, you're fine — the index was already rebuilt. v0.9.26 just makes the first-run boot quiet.

Verified

• 125 test files / 1381 tests pass
• Build clean

Bug-fix wave closing every breaking 0.9.24 regression, plus a feature lane. Eleven issues closed. No breaking changes; drop-in upgrade.

Fixed

• Cross-provider fallback always 404'd and tripped the circuit breaker (#778). Fallback resolved each provider's own env-driven default model instead of inheriting the primary's.
• import-jsonl aborted entire batch on legacy session row missing id (#775). Re-keys on parsed.sessionId, backfills missing existing.id.
• parseSummaryXml silently dropped summaries wrapped in markdown fences (#783). New stripXmlWrappers() peels fences + pre/postamble; final-merge parse retries once.
• sdk.triggerVoid is not a function on iii-sdk 0.11.2 (#758 / #726). All 9 call sites migrated to trigger({ action: TriggerAction.Void() }).
• pi integration recorded every observation as "No content provided" (#759). Field-name fix: tool_input / tool_output.
• Fresh global install refused to boot when PATH iii didn't match the runtime pin (#752). Private install at ~/.agentmemory/bin/ + auto-fallback. Existing user iii stays untouched.
• mem::obsidian-export HTTP 500 [object Object] on any record missing id (#729). Four-layer hardening + outer try/catch.
• Concurrent agent-sdk summarize chunks failed with too_many_chunks_skipped (#781). AsyncLocalStorage recursion guard + reference-counted env marker.
• Viewer #graph tab blank on large graphs (#753). graph/query pagination + degree-ranked default cap + viewer error banner with Retry.

Upgrade

npm install -g @agentmemory/agentmemory@0.9.25

iii-sdk and iii-engine pins stay at v0.11.2.

Full changelog: https://github.com/rohitg00/agentmemory/blob/main/CHANGELOG.md

0.9.24 — 2026-05-29

Hotfix

0.9.23 — 2026-05-28

Bug-fix + integration wave. GitHub Copilot CLI joins the supported agent matrix with plugin + hooks + MCP coverage. Three silent DX bugs fixed end-to-end: graph extraction never fired on session end, agentmemory status reported zero memories, consolidation defaulted off even with an LLM provider configured. Five additional adapters and a clearer local-LLM story for Ollama / LM Studio users. agentmemory connect now points users at npx skills add for the native-skills install path (50+ agents).

Added

• GitHub Copilot CLI (PR #534). Full first-class support: plugin/plugin.json manifest, hooks.copilot.json lifecycle hooks for all 11 Copilot events with camelCase payload normalization, agentmemory connect copilot-cli MCP path, first-run onboarding default-select via COPILOT_CLI / COPILOT_AGENT_SESSION_ID env detection, Windows-safe cmd.exe /d /s /c npx wrapper. Standalone MCP transport now speaks LSP-style Content-Length framed JSON-RPC alongside the existing newline-delimited form so Copilot's stdio init handshake works.
• Five new MCP adapters (PR #677). Warp, Cline, Continue, Zed, and Droid. createJsonMcpAdapter extended with wrapperKey (Zed uses context_servers instead of mcpServers) and extraEntryFields (Droid requires type: "stdio"). ADAPTERS count: 11 → 17.
• /agentmemory/graph/build endpoint (PR #698). Backfills the knowledge graph from existing compressed observations across every session in configurable batches. Wires up the viewer's "Build Graph" button that previously returned 404.
• 11 README translations + language picker (PR #675). zh-CN, zh-TW, ja-JP, ko-KR, es-ES, pt-BR, fr-FR, de-DE, ru-RU, tr-TR, hi-IN.
• npx skills add hint in connect output (PR #709). After a successful agentmemory connect <agent>, the CLI now prints the matching npx skills add rohitg00/agentmemory -y command so users get the native-skills install alongside MCP wiring. The skills CLI covers 50+ agents including the 5 added in PR #677. README "Other agents" section gains a dedicated subsection explaining the two-step pattern (connect writes MCP config, skills add installs the 8 SKILL.md files into the agent's native skill directory).

Changed

• Consolidation auto-enables when an LLM provider is configured (PR #696, closes #612). CONSOLIDATION_ENABLED defaulted to false, so users with a working provider got compression + summarization but zero graph nodes / crystals / lessons. Now defaults true whenever any of ANTHROPIC_API_KEY / OPENAI_API_KEY / OPENROUTER_API_KEY / GEMINI_API_KEY / GOOGLE_API_KEY / MINIMAX_API_KEY / OPENAI_BASE_URL is set, or AGENTMEMORY_PROVIDER=agent-sdk. Explicit =false / AGENTMEMORY_PROVIDER=noop still opt out. OPENAI_API_KEY_FOR_LLM=false honored (key scoped to embeddings).
• Fire-and-forget telemetry hooks (PR #688, closes #573). Nine telemetry-only hooks (notification, post-tool-failure, post-tool-use, prompt-submit, stop, session-end, subagent-start, subagent-stop, task-completed) switched to unawaited fetch(...).catch(() => {}) paired with setTimeout(() => process.exit(0), 500).unref() (1500ms for the multi-fetch stop + session-end hooks). No longer blocks Claude Code's next-prompt boundary on every assistant turn.
• Observability defaults tamed (PR #686, closes #519). iii-config.yaml defaults: sampling_ratio: 0.1, logs_console_output: false. findIiiConfig() precedence reversed so AGENTMEMORY_III_CONFIG env > cwd > ~/.agentmemory/iii-config.yaml > bundled.

Fixed

• Graph extraction never fires automatically (PR #698, closes #666). event::session::stopped listens on agentmemory.session.stopped but nothing in the codebase ever published that topic. api::session::end now directly calls sdk.triggerVoid("event::session::stopped", { sessionId }) (try/catch guarded so a fan-out error doesn't fail the HTTP response). Knowledge graphs now materialize automatically when sessions end.
• agentmemory status shows Memories/Observations = 0 (PR #698, closes #666). CLI fetched /agentmemory/export for counts but that endpoint times out (>5s) on iii-engine's file-based KV under concurrent kv.list(). Switched to /memories?count=true (count-only, constant-time) + sum of sessions[].observationCount.
• Hooks send full filesystem path as project instead of repo basename (PR #687, closes #474). Native sessions, replay-import, and memory_lesson_save all use repo basename — the path/basename mismatch silently filtered out the bulk of relevant lessons from auto-injected context. New resolveProject(cwd?) helper: AGENTMEMORY_PROJECT_NAME env > git rev-parse --show-toplevel basename > basename(cwd). Applied to 9 hooks.
• Cross-project memory leakage (PR #662). Memories created in one project leaking into recall on another. Wildcard guard pattern (!project || !m.project || m.project === project) preserves backward-compat for legacy unscoped memories while scoping new ones strictly.
• Graph parser tolerates reordered XML attributes (PR #685, closes #635). Order-dependent regex replaced with order-independent parseAttrs helper. Self-closing trailing-/ handling preserved.
• Defensive null guards on Memory.sessionIds (PR #684). Older exports + hand-edited dumps can omit this field; now treated as empty array on read.
• Vector index Buffer slice metadata round-trip (PR #683, closes #587, #584). byteOffset + byteLength preserved on Buffer.from and Float32Array construction so base64 round-trips don't corrupt vectors stored as slices.
• Slots HTTP triggers return 503 not 500 (PR #682, closes #678). Feature-flag-disabled responses now use the documented 503 shape with enableHow + docsHref. .env propagation fixed (now reads via getEnvVar() not raw process.env).
• agentmemory doctor points to correct iii install URL (PR #681).
• Separate OPENAI_EMBEDDING_BASE_URL + OPENAI_EMBEDDING_API_KEY (PR #503). Lets users route embeddings and LLM calls to different OpenAI-compatible endpoints (e.g. cloud OpenAI for embeddings + local LM Studio for LLM, or vice versa).
• Viewer Memories tab sorts newest first (PR #701, closes #674). Memories list rendered in KV-insertion order, hiding just-saved entries at the bottom of long lists. loadMemories() now sorts on createdAt desc (fallback updatedAt) before items reach state — matches the localeCompare pattern Sessions / Metrics tabs already use.

Docs

• Local-LLM section in README (PR #697, closes #671). Dedicated "Local models (Ollama / LM Studio / vLLM)" subsection with copy-paste configs, model-pick table (qwen2.5-coder:7b, llama3.2:3b, mistral:7b-instruct, deepseek-r1:7b), and reasoning-model empty-content callout. Existing OpenAI-compatible support was buried in a one-line env comment.
• Three pipeline layers, not three primitives (PR #690). Website + README copy: the three primitives are worker / function / trigger (iii). HOOKS / RECALL / CONSOLIDATE are pipeline layers. Section anchor renamed #primitives → #stack to match the nav label.

Infrastructure

• Hook scripts now bundle per-entry instead of sharing chunks, so plugin/scripts/_project-*.mjs hashed artifacts no longer churn the diff on every build.
• AGENTS.md "Hook Scripts" section documents the two patterns (context-injecting vs telemetry-only) and the 500ms / 1500ms exit-delay rule for single vs multi-fetch hooks.
• Test suite: 1271 → 1291 (+20 new tests covering project basename resolver, fire-and-forget wiring, consolidation default behavior, session-end → graph extraction, the graph-build endpoint, and the viewer memories sort).

Stability + ecosystem wave. Three install-broken bugs (npm install ERESOLVE, non-OpenAI base URLs, broken Claude bridge path) closed. Six runtime bugs from active users fixed end-to-end. Three new agent integrations (Qwen Code, Antigravity, Kiro). New AGENT_ID scope for multi-agent setups. Port mapping documented.

Fixed

• npm install ERESOLVE on fresh install (PR #649, closes #631). @anthropic-ai/sdk bumped from ^0.39.0 to ^0.93.0 so claude-agent-sdk's peer is satisfied. Verified clean install with only the published dependencies block.

• Non-OpenAI base URLs silent-404 (PR #649, closes #646, #628). buildChatUrl + buildEmbeddingUrl no longer blindly prepend /v1/. DeepSeek, SiliconFlow, Zhipu (/api/paas/v4), vLLM, LM Studio, Ollama all resolve correctly.

• CLAUDE_MEMORY_BRIDGE writes to a path Claude Code reads (PR #649, closes #625). Slug now preserves the leading - on POSIX absolute paths and drops the spurious /memory/ subdir, matching ~/.claude/projects/<slug>/MEMORY.md.

• OpenAI provider reads reasoning_content for thinking models (PR #648, closes #627). DeepSeek V4 / Qwen3 / GLM / Kimi return message.reasoning_content. Previously only message.reasoning was checked — compress silently failed every call and tripped the circuit breaker.

• agentmemory stop reaps the worker process (PR #648, closes #640, #474). Worker pid is written to ~/.agentmemory/worker.pid on boot; stop signals both engine + worker.

• OpenCode plugin implicit-creates the session on first observation (PR #648, closes #638). mem::observe creates the session row when one doesn't exist. No more orphan observations or Session not found for summarize.

• OpenCode plugin zero-config auto-context injection (PR #648, closes #431). POST /session/start context is cached per-session; the existing experimental.chat.system.transform hook reads from the cache.

• Viewer graph settles on 1000+ node graphs (PR #648, closes #563). Tick-decayed damping, per-node velocity cap, raf park on quiescence. Mousedown / wheel / zoom / recenter re-wake the parked loop.

• /memories + /export paginate (PR #648, closes #544). New ?count=true and ?limit=N&offset=M on /memories. /export forwards ?maxSessions + ?offset. Stops large corpora (8K+ memories) from timing out at the iii-engine invocation boundary.

• Claude Code drops the MCP server silently (PR #650, closes #510). plugin/.mcp.json env block uses ${VAR:-default} form. Unset required vars no longer fail config parse.

• Full 51-tool MCP surface by default (PR #650, closes #553). getVisibleTools() default flipped from core (8) to all (51) to match what every plugin manifest advertises. AGENTMEMORY_TOOLS=core still gives the lean set.

• Connect adapters write ${VAR:-default} env block (PR #650). agentmemory connect for Claude Code / Cursor / Gemini CLI / Windsurf writes the same default form.

• Hermes memory status no longer reports the plugin as Missing (PR #643, closes #520). Hermes plugin seeds AGENTMEMORY_URL to http://localhost:3111 at import. Works for systemd-managed agentmemory where the env file is loaded via EnvironmentFile= and never reaches the interactive shell.

• Deleted memories cleared from BM25 + vector indices (PR #636 by @abhinav-m22, closes #632). SearchIndex.remove() added and called from every delete path. Snapshot flushed synchronously so a SIGKILL between mutation + debounce can't resurrect deleted entries.

• PostToolUse hook reads tool_response, falls back to tool_output (PR #561 by @faraz152, closes #539). Claude Code's PostToolUse payload uses tool_response. Now reads tool_response ?? tool_output so legacy integrations keep working.

• iii-sdk pinned to exact 0.11.2 (PR #567, closes #555). iii-sdk@0.11.6 introduced a routing regression where every /agentmemory/* route returned 404. Pin removes the caret.

• OpenAI provider sends explicit stream: false (PR #526 by @Ptah-CT). Some OpenAI-compatible proxies default to text/event-stream when stream is absent.

• Viewer search uses NFKC normalisation for CJK / fullwidth input (PR #542 by @kaushalrog).

• Viewer splash shows actual bound viewer port (PR #560 by @Tanmay-008, closes #521). /agentmemory/livez now returns viewerPort + viewerSkipped.

• Viewer tab bar height stable across tab switches (PR #325 by @hungtd119, closes #324).

• Graph parser accepts self-closing <entity .../> tags (PR #494 by @Rex57, closes #492).

• Plugin MCP server inherits remote/auth env (PR #386 by @LaplaceYoung, closes #375).

• @agentmemory/mcp rejects literal ${VAR} placeholders. Any AGENTMEMORY_URL / AGENTMEMORY_SECRET value of the form ${...} is treated as unset and falls back to http://localhost:3111.

• Codex stop hook closes session (PR #579, closes #493). Stop was missing from the Codex bundle; session never got marked completed.

• Claude Code --with-hooks works for MCP-standalone users (PR #581, closes #508).

Added

• AGENT_ID multi-agent memory isolation (PR #654, closes #554). Optional AGENT_ID env tags every Session / RawObservation / CompressedObservation / Memory. AGENTMEMORY_AGENT_SCOPE=isolated (opt-in; shared default) also filters every recall path (mem::smart-search, /memories, /observations, /sessions). Per-call overrides via request body + ?agentId=<role> / ?agentId=* query params. ?includeOrphans=true surfaces pre-tag rows.

• Qwen Code connect adapter (PR #651, closes #647). agentmemory connect qwen writes the standard mcpServers block to ~/.qwen/settings.json.

• Antigravity connect adapter (PR #651, closes #614). Replacement for Gemini CLI (sunset 2026-06-18). Writes mcp_config.json to the platform-specific User dir.

• Kiro connect adapter (PR #651, closes #618). Writes user-level ~/.kiro/settings/mcp.json.

• Cost-aware model selection (PR #654, closes #613). Runtime warning when OPENROUTER_MODEL matches the premium pattern. README cost-tier table with measured workload data. Suppress via AGENTMEMORY_SUPPRESS_COST_WARNING=1.

• Pluggable benchmark harness (PR #562). New eval/ directory with the coding-agent-life-v1 corpus (15 sessions + 15 graded queries) and three adapters (grep, OpenAI embeddings + cosine, agentmemory hybrid). LongMemEval support. Sandboxed agentmemory + iii-engine on alt ports via eval/scripts/sandbox.sh. Dev-only — no runtime impact.

• agentmemory connect codex --with-hooks opt-in flag (PR #564, closes #509). Workaround for openai/codex#16430.

• Cross-platform CI matrix (PR #556). Ubuntu + macOS × Node 20 + 22, paths-ignore, per-branch concurrency cancellation.

Docs

• Port mapping table (PR #651, closes #629). 3111 REST / 3112 streams / 3113 viewer / 49134 engine WS + env overrides + stale-process cleanup recipe.

• Pairings recipe (PR #641). docs/recipes/pairings.md covers stacking agentmemory with codegraph, Understand Anything, and Graphify.

• Multi-agent README section (PR #654). AGENT_ID + AGENTMEMORY_AGENT_SCOPE semantics, per-endpoint behavior table.

• Supply-chain policy in SECURITY.md (PR #654, closes #540). Explains why no lockfile is committed (dist/ ships pre-built) and what monitoring exists.

• README "Config File" section + Windows path (PR #321 by @aqilaziz, closes #293).

• README sudo install hint for EACCES (PR #454 by @kedar-1).

Infrastructure

• 108 test files, 1171 tests pass.
• Agent count: 8 → 11 (claude-code, codex, cursor, gemini-cli, qwen, antigravity, kiro, openclaw, hermes, pi, openhuman).

0.9.21 — 2026-05-19

Quality + integration wave. Headline: native OpenCode plugin with full Claude Code hook parity (#237 by @cl0ckt0wer). Ten more PRs alongside: memory_recall returning the wrong shape, env-file AGENTMEMORY_DROP_STALE_INDEX silently ignored, hook scripts crashing on Windows usernames with spaces, viewer search inputs interrupting CJK IME composition, large sessions silently failing at the LLM context limit, lessons invisible to smart-search, Hermes plugin manifest missing hooks, cli onboarding crashing in non-TTY contexts, rebuildIndex blocking boot on large corpora, 25h embed-loop bottleneck during rebuild, and the v0.9.19 iii-console installer workaround can come out now that upstream is fixed.

Added

• OpenCode plugin with 22 auto-capture hooks (PR #237 by @cl0ckt0wer, closes #236 + #244). Complete OpenCode plugin in plugin/opencode/ matching Claude Code hook parity. Covers session lifecycle (8 hooks), messages (3), tool lifecycle (2), part tracking, permissions, task tracking, plus a two-layer enrichment pipeline (memory context on first turn, file enrichment on subsequent turns) and two slash commands (/recall, /remember). Full gap analysis in plugin/opencode/README.md.

Fixed

• memory_recall endpoint + format/token_budget forwarding (PR #516 by @serhiizghama, closes #507 + #440). MCP memory_recall always returned compact mode and dropped format + token_budget params. Two root causes fixed: standalone shim routed through /agentmemory/smart-search instead of /agentmemory/search, and the local-fallback path didn't read either param. Now routes correctly, forwards both params end-to-end, defaults format to "full" matching the MCP schema.

• env-file AGENTMEMORY_DROP_STALE_INDEX flag now honored (PR #461 by @honor2030, closes #456). Setting the flag in ~/.agentmemory/.env was silently ignored because the boot path read process.env directly. New isDropStaleIndexEnabled() helper reads merged env. Combined with #455 + #469 reports, this is the unblock path for the stale-index server-crash recovery loop.

• Windows hook scripts quote plugin paths correctly (PR #487 by @honor2030, closes #477). Hook command strings referenced ${CLAUDE_PLUGIN_ROOT}/scripts/*.mjs without quotes — Windows users with spaces in their username had every hook crash. Quotes added + regression test.

• Viewer search inputs honor IME composition (PR #517 by @jonathanzhan1975). CJK users typing in the viewer's search inputs hit mid-character interruption — every keystroke fired the oninput= re-render handler, breaking IME composition mid-syllable. New bindImeSafeSearch helper defers re-render until compositionend.

• Chunk large sessions to fit LLM context window (PR #472 by @efenex). Sessions with >7000 observations silently failed at the LLM provider's context limit — the consolidation pipeline silently skipped the session. New chunking splits oversized sessions across multiple compress calls + restitches the narrative via a REDUCE_SYSTEM prompt. Legacy single-call path preserved when obs count is under the chunk size. Backfill script under scripts/ for users hitting the pre-fix bug.

• Surface lessons in smart-search + diagnose tally (PR #473 by @efenex). Closes the lesson round-trip with #458 (lessons auto-injected into mem::context): lessons are now also returned alongside hybrid search results in a separate lessons field on smart-search, and the diagnose health surface tallies per-store counts so the trust-shock pattern (save succeeds, recall empty, diagnose says 0) goes away.

• Declare all Hermes plugin hooks (PR #486 by @honor2030). The Hermes plugin.yaml manifest only declared 3 of the 6 implemented hooks. All 6 now declared (prefetch, sync_turn, on_session_end, on_pre_compress, on_memory_write, system_prompt_block).

• rebuildIndex non-blocking on boot (PR #500 by @efenex). Boot path previously await-ed rebuildIndex(kv), so the viewer + later boot steps stalled — on large corpora this was 25h+ of blocked startup. Replaced with void rebuildIndex(kv).then(...).catch(...) so the rebuild runs in the background.

• Batched embed calls in rebuildIndex (25h → 3h on large corpora) (PR #504 by @efenex). The rebuild loop made one embed call per observation, paying full HTTP RTT per item. New vectorIndexAddBatchGuarded helper batches embeds (default 32, configurable via REBUILD_EMBED_BATCH_SIZE) and try/catches per-item failures. Measured 25h → 3h on a 250k-observation corpus.

• CLI skips onboarding prompts without a tty (PR #491 by @honor2030). Onboarding prompts crashed in non-interactive contexts (CI, docker run -d, piped input). New guard short-circuits with sensible defaults when stdin/stdout aren't TTYs or CI=1.

Changed

• Drop iii-console installer --next workaround (PR #546). v0.9.19 routed first-run iii-console install through bash -s -- --next to dodge an upstream tag-prefix bug at iii-hq/iii#1652. Upstream iii-hq/iii#1660 shipped 2026-05-19; install.iii.dev/console/main/install.sh is a CDN proxy serving upstream main HEAD so the fix is live without an iii release tag. Reverted to canonical bare curl ... | sh.

Infrastructure

• 95 test files (was 92), 1067 tests pass (was 1038) on chore(release): v0.9.21.
• Bundles 11 PRs: 1 contributor feature + 9 bug fixes across MCP / hooks / viewer / summarize / lessons / Hermes / rebuildIndex / CLI + 1 upstream-installer revert.
• New contributors landing first PRs this release: @cl0ckt0wer, @serhiizghama, @jonathanzhan1975.

0.9.20 — 2026-05-18

Hotfix: revert the Codex Stop → session-end chain shipped in v0.9.19.

Fixed

• Revert Codex Stop hook session-end chain (PR #501 by @Rex57, reverts v0.9.19's #495, re-opens #493). Post-merge field-testing surfaced the underlying issue: Codex Stop fires before the overall conversation is truly finished — multiple Stops bracket each assistant turn within one session. Chaining session-end.mjs from Stop marked sessions completed too early, with later observations still arriving against an endedAt-stamped record. Restored to summarize-only Stop; the SessionEnd-shaped solution stays open as #493.