v0.36.0

0.36.0 (2026-04-18)

Features

• abstraction: archive escape hatch for chronically-demoted abstractions (18ec2c5)
• abstraction: archive escape hatch for chronically-demoted abstractions (45b61a9)
• abstraction: gate synthesis on substrate-change fingerprint (2b92ead)
• abstraction: gate synthesis on substrate-change fingerprint (209020b)
• abstraction: streak-based archive supersedes age-based decay exit (917edb3)
• abstraction: streak-based archive supersedes age-based decay exit (083d0c1)
• add Gemma 4 E2B spoke inference server (6a3c409)
• consolidation: resurrect archived patterns on re-emergence (24c9943)
• consolidation: resurrect archived patterns on re-emergence (0c27890)
• continuous learning Phase B — curriculum generation (#391) (e5a5d59)
• continuous learning Phase C — training trigger & orchestration (#391) (5bb0094)
• continuous learning Phases B+C — curriculum generation & training trigger (#391) (28860cf)
• dreaming: INFO logs for four silent-drop gates (865a71d)
• dreaming: INFO logs for four silent-drop gates (c9f40bd)
• dreaming: rotate replay sample via recent-ID ring buffer (1a97250)
• dreaming: rotate replay sample via recent-ID ring buffer (b8ae0a7)
• enable continuous learning by default (#391) (ac2bf1b)
• Gemma 4 E2B spoke training — 25/25 schema compliance (ab6ba40)
• SetSpokeTensorF32 — push F32 weights with auto-quantization to native type (780808f)
• SPLICE API for CRISPR-LM (edit/status/tensor/complete) + Gemma 4 template fix (c77f749)
• SPLICE API for CRISPR-LM + Gemma 4 chat template fix (79289a6)
• training data assembly for continuous learning (#391) (99d3c28)

Bug Fixes

• abstraction: bump MaxTokens 200 -> 500 for principle/axiom synthesis (252d14c)
• abstraction: bump MaxTokens 200→500 for principle/axiom synthesis (ef0ffd4)
• abstraction: concept-overlap gate on findSimilarAbstraction (604bf33)
• abstraction: concept-overlap gate on findSimilarAbstraction (cbabbbd)
• abstraction: lower MinStrength default 0.7 → 0.5 to unblock principle synthesis (d89fa4a)
• abstraction: lower MinStrength default 0.7 → 0.5 to unblock principle synthesis (98a8408)
• add GBNF grammar for episode synthesis (588f802)
• add GBNF grammar for episode synthesis to fix "Untitled session" failures (151296c)
• address all PR #397 review items from Caleb (e52ee2a)
• agents: axiom grounding, pattern dedup, forum transition reporting (1b7ba03)
• agents: axiom grounding, pattern dedup, forum transition reporting (0cff8b5)
• consolidation: bound salience with a 1.0 ceiling in decay (d80e297)
• consolidation: bound salience with a 1.0 ceiling in decay (daff51e)
• consolidation: break pattern-dedup super-attractor via concept-overlap gate (c1a3a39)
• consolidation: break pattern-dedup super-attractor via concept-overlap gate (d50c860)
• consolidation: concept-overlap gate on second-stage dedup (3372dc9)
• consolidation: concept-overlap gate on second-stage dedup (f9135fd)
• consolidation: sample large clusters + raise MaxTokens for identifyPattern (cfae847)
• consolidation: sample large clusters + raise MaxTokens for identifyPattern (cbb5434)
• correct bool array type in Gemma GGUF export + update EXP-30 verdict (45515b2)
• curriculum_runs stored time.Time.String() output, unparseable on read (1266e46)
• curriculum_runs stored time.Time.String() output, unparseable on read (f1eec70)
• Gemma 4 spoke training produces garbage due to use_cache=False (b1eaa8e)
• llm: drop misleading "busy" prefix on embedded provider cancel (48b3b19)
• llm: drop misleading "busy" prefix on embedded provider cancel (450c886)
• move advisory board personas from local memory to .claude/skills/ (2dd06b0), closes #398
• move advisory board personas into repo (5c4e5bb)
• prevent MCP processes from loading GPU models into VRAM (8bd86a8)
• prevent MCP processes from loading GPU models into VRAM (a575622)
• store: age-bound training breaker so stale failures expire (0198153)
• store: age-bound training circuit breaker so stale failures expire (6e76dc2)
• Task Scheduler is logon-only, manual start uses PID-file daemon (07a605f)
• training crash loop safety + episode synthesis quality (f0a8a95)
• training crash loop safety + episode synthesis quality (#391) ([75dc713](h...

v0.35.0

0.35.0 (2026-04-10)

Features

• 210 mnemonic-specific scenarios, bespoke generator, fix encoding token limit (3ebecc1)
• add conciseness guidance for structured_concepts encoding (dc6dabe)
• add Gemma 4 E2B spoke GGUF export script (f96dbbb)
• add serve_spokes.py for OpenAI-compatible spoke model serving (26613ab)
• add thinking-mode support to bake-off harness (665082b)
• backfill verification metrics + fix chart dot visibility (1b78795)
• continuous learning Phase A — runtime verification & experience collection (#391) (82140a1)
• dashboard encoding quality metrics (EPR, TED, experience buffer) (2545de1)
• dashboard narrative + lifecycle chart overhaul (5ce22bf)
• distribution balance data gen, fix batch_encode source preservation (b1bfd96)
• EXP-15 through EXP-19, Gemma 4 adapter, data pipeline, quality testing (e4b94e7)
• EXP-15-19 training research, Gemma 4 adapter, data pipeline (f6ce427)
• EXP-20 data quality pipeline, targeted data generation, MI300X prep (6d75333)
• EXP-25 faithfulness probe — confirmed at seq_len 2375 (d3b6f3a), closes #381
• EXP-25 faithfulness probe, encoding fixes, MCP HTTP transport (45a7cd5)
• EXP-29 candidate model evaluation — bake-off tooling and research designs (e4a8b01)
• EXP-29 candidate model evaluation + faithful prompt (5d470a9)
• faithful prompt format for encoding — rules-first design (EXP-29) (cfb9dc1)
• fix spoke GGUF export, gist merge bug, bump token limits to 4096 (e9fbfaa)
• Gemma chat template support for embedded provider (e647578)
• Gemma E2B spoke training + continuous learning Phase A + dashboard overhaul (6d0d0eb)
• Gemma E2B spoke training setup (EXP-30) (fc54802)
• layer importance profiling script for structured pruning (f6c1a62)
• MI300X Gemma 4 E2B training infrastructure, wandb logging (dc42349)
• Model Control Center with embedded LLM and runtime switching (d2aec19)
• Model Control Center with embedded LLM inference (ad2a86b)
• procedural generator + 96 handwritten mnemonic scenarios v2 (79ed030)
• prompt ablation reveals faithful variant as best encoding approach (f5bd07c)
• research analytics dashboard overhaul (f7e1e56)
• RotorQ RQ4 quantizer + benchmark scripts (ba8e66d)
• RQ4 GPU inference, RQ3 experiment, spoke fusion, fused GGUF export (b603dbc)
• RQ4 GPU inference, spoke fusion, handoff recall fixes (de1efd5)
• serve MCP over HTTP transport from daemon (65fe6cf)
• serve MCP over HTTP transport from daemon (#384) (47a093f)
• spoke routing infrastructure, llama.cpp inference, TurboQuant reference (f51db44)
• TurboQuant prompt cache compression, EXP-22 registration (f8ccf51)
• update EXP-20 config, pre-register EXP-21 (bottleneck rotation) (040c596)
• v6 smoke test 7/7 stress, add advisory board rule (304d884)
• v7 diverse input generation pipeline (8c30d06)

Bug Fixes

• encoding faithfulness + amend raw_id + dashboard timeline bugs (9e874ab)
• encoding faithfulness, amend raw_id, dashboard timeline (671b1b6)
• FR metric now measures content fields only, not concepts (3b12bde)
• GBNF grammar via chat completions payload, not server-level flag (87ec76a)
• gist merge FK violation, ambiguous column in FTS concept search (042a1e3)
• handoff recall, type-filtered search, consolidation exclusions (0ca58bf)
• inline migration 016 for continuous learning tables (3bc78ab)
• preserve full content in handoff-type memories (831a9fe)
• preserve full content in handoff-type memories (ac17492)
• sparse templates with proper gist mapping, dedup to 51 unique (27a400b)
• SQL flagged_rate query handles legacy "null" string values. (2545de1)
• stress test --checkpoint arg, batch_encode model upgrade, misc fixes (0c1c5d1)
• stress test Gemma support, batched generation, JSON parser (cd9e6c7)
• update TestFormatPrompt for ChatML format (d959878)
• use theme-neutral grey dots for EPR chart (053fff8)
• write SQL NULL for empty flags (not JSON "null" string). (2545de1)

What's Changed

• Remove images from README.md by @CalebisGross in #368
• fix: preserve full content in handoff-type memories by @CalebisGross in #375
• feat: EXP-15-19 training research, Gemma 4 adapter, data pipeline by @CalebisGross in #377
• feat: RQ4 GPU inference, spoke fusion, handoff recall fixes by @CalebisGross in #379
• feat: Model Control Center with embedded LLM inference by @CalebisGross in #380
• fix: encoding faithfulness, amend raw_id, dashboard timeline by @CalebisGross in https://github.c...

v0.34.1

0.34.1 (2026-03-29)

Bug Fixes

• add cancellation to HeuristicFilter cleanup goroutine (c8848cd)
• cancel constructor context in encoding agent Start() (6a77042)
• remediate all 9 yield audit findings (issue #355) (0af0268)

What's Changed

• docs: post-v0.34.0 documentation audit + darken Parchment theme by @CalebisGross in #364
• fix: remediate all 9 yield audit findings (issue #355) by @CalebisGross in #365
• chore(main): release 0.34.1 by @appsprout-release-please[bot] in #366

Full Changelog: v0.34.0...v0.34.1

v0.34.0

0.34.0 (2026-03-29)

Features

• add CGo llama.cpp backend and wire into EmbeddedProvider (ed71564)
• add DB pair extraction, fix data loading, prep for EXP-14 (2ff222f)
• add deploy pipeline, embedding fine-tune script, and pre-register EXP-9 (bf534bc)
• add dismiss_abstraction tool, recall filtering, IDs in output (5279493)
• add embedding extraction via mean-pooled hidden states (6da2d0d)
• add lightweight D3 shim replacing CDN dependency (Phase 4) (9491930)
• add llama.cpp submodule and fix GGUF export for Felix architecture (93f1766)
• add llama.cpp submodule, CGo bridge, and Qwen spoke training docs (6c9e1d2)
• add LoRA support, gradient checkpointing fix, and EXP runner scripts (9ba9738)
• add per-token logit validation for embedded LLM quality gating (96775a2)
• add Phase 3 data pipeline scripts and pre-register EXP-6/7/8 (640123b)
• add Phase 3 fine-tuning pipeline (9c7df1c)
• add Phase 3 fine-tuning pipeline (498dd28)
• add Q8_0 quantization support and prefer quantized models (b7a2488)
• add Qwen spoke adapter, re-tokenization pipeline, and pre-register EXP-11-14 (371464a)
• add ROCm HIP link flags and encoding comparison script (8ae61c0)
• add server-side episode_id filter to /memories endpoint (934b6a6)
• add standalone command center dashboard for GitHub tracking (e750f60)
• add thread view, restyle SDK/LLM/Tools headers (Phase 3/7) (0651281)
• add training script and evaluation hooks for Qwen spoke experiments (36d8bdb)
• agent identity system — sources become forum users (20ba192)
• breadcrumbs update on every view switch (afe0d62)
• clickable live feed posts — navigate to relevant views (eb47ac2)
• clickable memory/pattern/abstraction rows — expand to show detail (9b9e757)
• complete Epic #339 dashboard cleanup — digest threads, associations, D3 removal (0939956)
• complete EXP-9 mixed fine-tune, fix embedding script, add v2 model (5bb94dc)
• complete structural rewrite — all views use phpBB patterns (26cf76c)
• episode-aware @mentions — agents know which episode you're asking about (7984ba9)
• extract CSS sections and add forum component library (Phase 2) (746e636)
• extract CSS tokens, remove D3 CDN, archive mockups (Phase 1) (354570d)
• fix instrumented model label for embedded provider, add nomic BERT test (f5e0c24)
• forum categories — sub-forum index page with phpBB layout (c2b3197)
• forum communication layer — posts, threads, agent personality, @mentions, internalization (fe7445d)
• forum UX — @mention autocomplete, quote button, @tag names, blank reply fix (d1b662b)
• forum-style dashboard redesign (Epic #339) (66ae0cd)
• functional depth — clickable memory sections, project routing, episode project tagging (05303c7)
• improve recall quality for LLM agents, fix Windows self-update (7a8bfa6)
• improve recall quality for LLM agents, fix Windows self-update (aa07982)
• live activity feed — agents post to forum in real-time (fb96d78)
• MCP agent UX — dismiss_abstraction, recall filtering, hook fixes (d747591)
• nested forum navigation — index > group > sub-forum > thread > post (fb9ca12)
• Phase 3-4 autoresearch — fine-tuning pipeline, CGo backend, experiments (49ad590)
• populate welcome panel with stats + last visit tracking (ef88f51)
• project auto-detection, data-aware agents, agent-to-agent chat, thread subscriptions (1354424)
• Qwen 3.5 2B + Felix spoke training infrastructure (21facd3)
• remove Mind/Graph view entirely (Phase 3 partial) (94056ca)
• render quoted text as styled blockquote boxes (a6147a9)
• restyle SDK, LLM, Tools views to forum aesthetic (#349) (ec8ce1a)
• rewrite Explore and Recall renderers to forum style (Phase 3-5) (2c05b8d)
• rewrite Timeline renderer to forum rows (Phase 6) (fb4e78f)
• run spoke gate analysis (EXP-8) and fix synthesis data generation (c43587c)
• scaffold modular dashboard structure (Phase 0) (6145e9a)
• standalone command center dashboard (ea0536e)
• strip coaching prompts from training data, tune LR to 3e-4 (68c2725)
• structural rewrite — phpBB-inspired dl/dt/dd forum layout (cca709a)
• thread view shows Episoding Agent post when no encoded memories (49f6b14)
• transform nav to forum top bar + navbar + footer (Phase 2-3) (ef1c48a)
• unified forum index — merge welcome+live feed, add Memory System section ([ad634b3](ad634b3...

v0.33.0

0.33.0 (2026-03-21)

Features

• add Mind page to dashboard — force-directed memory graph visualization (a8ae051)
• live cognitive metrics, system analysis, and embedding backfill (442e999)
• Mind graph page, live cognitive metrics, and system analysis (aca26f7)
• redesign tools page research analytics and session activity (1fb5018)

Bug Fixes

• NULL raw_id crash, feedback bloat, and runtime metrics (470e207)
• NULL raw_id crash, feedback bloat, and runtime metrics (#332, #333, #334) (ecc6f94)

What's Changed

• fix: NULL raw_id crash, feedback bloat, and runtime metrics by @CalebisGross in #336
• feat: Mind graph page, live cognitive metrics, and system analysis by @CalebisGross in #335
• chore(main): release 0.33.0 by @appsprout-release-please[bot] in #337

Full Changelog: v0.32.0...v0.33.0

v0.32.0

0.32.0 (2026-03-21)

Features

• dynamic tool count, associate_with validation, session timeline polish (c318dd2)
• dynamic tool count, associate_with validation, session timeline polish (95e59f7)
• make agent constants configurable via config.yaml (5d709ff)
• make agent constants configurable via config.yaml (87e87e1)
• make MCP/API salience and feedback weights configurable (d51c88a)
• make MCP/API salience and feedback weights configurable (d66b349)
• make perception scoring weights configurable (2b7e4d8)
• make perception scoring weights configurable via config.yaml (8d1fc7e)
• make reactor cooldowns and startup delays configurable (de7f166)
• make reactor cooldowns and startup delays configurable (0504c06)

Bug Fixes

• prevent consolidation from reactivating dismissed patterns, filter exclude_concepts on patterns/principles (7a583a7)
• prevent dismissed pattern reactivation + filter exclude_concepts on patterns (7d1255b)

What's Changed

• fix: prevent dismissed pattern reactivation + filter exclude_concepts on patterns by @CalebisGross in #324
• feat: dynamic tool count, associate_with validation, session timeline polish by @CalebisGross in #325
• feat: make agent constants configurable via config.yaml by @CalebisGross in #327
• feat: make perception scoring weights configurable by @CalebisGross in #328
• feat: make reactor cooldowns and startup delays configurable by @CalebisGross in #329
• docs: fix outdated tool counts and missing git watcher by @CalebisGross in #331
• feat: make MCP/API salience and feedback weights configurable by @CalebisGross in #330
• chore(main): release 0.32.0 by @appsprout-release-please[bot] in #326

Full Changelog: v0.31.0...v0.32.0

v0.31.0

0.31.0 (2026-03-21)

Features

• dashboard session timeline, encoding pipeline, salience histogram (1cee5d2)
• dashboard session timeline, encoding pipeline, salience histogram (6e7e5ef), closes #309

Bug Fixes

• add --resume-step and restore _orig_mod prefix stripping (cb1be55)

What's Changed

• feat: dashboard session timeline, encoding pipeline, salience histogram by @CalebisGross in #316
• chore(main): release 0.31.0 by @appsprout-release-please[bot] in #317

Full Changelog: v0.30.0...v0.31.0

v0.30.0

0.30.0 (2026-03-21)

Features

• add --resume support to training script (71c72b9)
• add --resume support to training script (fbdf2f1)
• bulk forget and exclude_concepts for recall (86c6768)
• bulk forget and exclude_concepts for recall (912306d), closes #307
• dashboard activity tracker and pattern management (57d17b9)
• dashboard activity tracker and pattern management (7b63565)
• explicit associations on remember and create_handoff tool (4b8f929)
• explicit associations on remember and create_handoff tool (ff7ff79), closes #308

Bug Fixes

• correct docs images and remove unused 192x192 icon (3c58802)
• correct docs images and remove unused 192x192 icon (5f53534)
• correct mnemonic.png and remove unused 512x512 icon (11d3c44)
• filter binary asset paths and numeric segments from concept extraction (63fa4ef)
• filter binary asset paths and numeric segments from concept extraction (7d82ec4), closes #305
• pattern project scoping, decay, and dismiss_pattern tool (f050a36)
• pattern project scoping, decay, and dismiss_pattern tool (43a0f96), closes #306
• use correct mnemonic.png and remove unused 512x512 icon (daaae33)

What's Changed

• ci: add workflow_dispatch trigger to release workflow by @CalebisGross in #300
• chore: update docs images and gitignore artifacts by @CalebisGross in #301
• fix: correct docs images and remove unused 192x192 icon by @CalebisGross in #302
• fix: correct mnemonic.png and remove unused 512x512 icon by @CalebisGross in #304
• fix: filter binary asset paths and numeric segments from concept extraction by @CalebisGross in #310
• fix: pattern project scoping, decay, and dismiss_pattern tool by @CalebisGross in #311
• feat: bulk forget and exclude_concepts for recall by @CalebisGross in #312
• feat: explicit associations on remember and create_handoff tool by @CalebisGross in #313
• feat: dashboard activity tracker and pattern management by @CalebisGross in #314
• feat: add --resume support to training script by @CalebisGross in #315
• chore(main): release 0.30.0 by @appsprout-release-please[bot] in #303

Full Changelog: v0.29.1...v0.30.0

v0.29.1

0.29.1 (2026-03-21)

Bug Fixes

• publish WatcherEvent to bus so retrieval agent receives activity (#296) (c7fddc2)
• sync daemon activity to MCP and filter path noise from themes (#298) (739d39b)

v0.29.0

0.29.0 (2026-03-20)

Features

• add pipeline observability metrics to get_context (c566a60)
• add pipeline observability metrics to get_context MCP tool (aebdaec)
• boost recall scores from recent watcher activity (108af2e)
• boost recall scores from recent watcher activity (#277) (110762a)
• enrich get_context themes with event types and terminal commands (86c6a52)
• enrich get_context themes with event types and terminal commands (b0257e9)