dream: 2026-06-22 17:56, 6 change(s)

[MEMORY] Wiki current state: ~21 nodes, ~130+ edges (was 17 nodes, 125 edges) after ingesting LEGO MINDSTORMS source with 3 entities and 2 concepts
[MEMORY] New wiki source ingested: source-lego-mindstorms-continued-use (LEGO MINDSTORMS discontinuation, Pybricks alternative, SPIKE Prime successor)
[MEMORY] New wiki entities: product-lego-mindstorms, product-pybricks, product-spike-prime
[MEMORY] New wiki concepts: digital-preservation, alternative-firmware
[USER-REMOVE] "U destruktivních / nevratných akcí (smazání, restarty produkčních služeb, push --force) si nejdřív vyžádej potvrzení" — duplicates SOUL.md rule "U nevratných akcí (smazání, přepis, odeslání) raději počkej na potvrzení"; SOUL.md is canonical location for bot behavior rules
[MEMORY-REMOVE] "User wants deterministic IRC-bot-style command dispatch in nanobot where !command text invokes a registered Python function or external app and returns output without LLM agent involvement" ← 16d — overlaps with two related entries below; consolidate into one
[MEMORY-REMOVE] "Zájem o :skillname prefix pro deterministické vyvolání skillu bez LLM deliberace — varianta navrhovaného custom command patche s ! prefixem" ← 15d — overlaps with above and below; consolidate
[MEMORY-REMOVE] "GLM-5.2 does not exist as of June 2026; Z.AI has made no official announcement" ← 15d — negative/time-sensitive fact that becomes stale the moment GLM-5.2 is announced; low ongoing value
[MEMORY-REMOVE] "nemotron-3-ultra:cloud released 2026-06-04 and is too new for real-world nanobot agent validation" ← 15d — time-sensitive assessment now 18+ days old; superseded by actual experience if any

USER.md

@@ -33,7 +33,6 @@
 - Preferuje root cause analysis před opakovaným spouštěním toolů — nelíbí se mu re-run bez diagnózy proč selhalo
 - Preferuje konkrétní úpravy (edity) nad research/planning smyčkami — uvíznuté workflow často pramení z „research mode" místo provedení změny
 - Pro research a srovnávání se nespoléhá na jediný zdroj — vždy ověřit přes více zdrojů; chybí-li data, říct to nahlas
-- U destruktivních / nevratných akcí (mazání, restarty produkčních služeb, push --force) si nejdřív vyžádej potvrzení
 - Připomínky: stručné, přirozené zprávy v češtině mluvené přímo uživateli; bez průběžného komentáře, shrnutí, user ID nebo statusových štítků jako „Hotovo“/„Připomenuto“
 - Preferovaný pager pro markdown v konzoli: `glow -p`
 

memory/.dream_cursor

@@ -1 +1 @@
-369
+370

memory/MEMORY.md

@@ -41,9 +41,7 @@ This file stores important information that should persist across sessions.
 - Session files are stored in `/home/nanobot/.nanobot/workspace/sessions/` (confirmed after failed attempts at root `.nanobot/sessions/`)
 - User explicitly rejected unified/Mega session approach; prefers connecting to older existing sessions instead
 - Telegram slash commands (e.g., `/skills`) are filtered out by `& ~filters.COMMAND` in telegram.py:384; workaround: invoke skills without slash prefix (e.g., `skills` not `/skills`); alternative fix: remove the filter from MessageHandler
-- User wants deterministic IRC-bot-style command dispatch in nanobot where `!command text` invokes a registered Python function or external app and returns output without LLM agent involvement
+- User wants deterministic command dispatch in nanobot (`!command text` → registered Python function/external app, no LLM involvement); expects native implementation from nanobot creators, considers existing workarounds unsatisfactory
-- User expects nanobot creators to implement custom command registration natively and considers existing workaround solutions unsatisfactory
-- Zájem o `:skillname` prefix pro deterministické vyvolání skillu bez LLM deliberace — varianta navrhovaného custom command patche s `!` prefixem
 - User wants nanobot use-case analysis framed as personal project relevance, not generic use case lists
 - User is interested in litellm proxy for Ollama
 - User considers Raspberry Pi good for testing
@@ -69,9 +67,7 @@ This file stores important information that should persist across sessions.
 - deepseek-v4-flash:cloud is a viable nanobot agent alternative with 1M ctx, MIT license, and ~30-50 tok/s speed
 - qwen3.5:397b-cloud is a viable nanobot agent alternative with multimodal support, 1M ctx, 201 languages including Czech, but has speed and accuracy tradeoffs
 - devstral-2:123b-cloud is a viable nanobot agent alternative with Terminal-Bench 77.3%, coding-only focus, and 128K ctx limit
-- GLM-5.2 does not exist as of June 2026; Z.AI has made no official announcement
 - User is interested in switching to GLM-5.2:cloud as primary nanobot agent model if/when it becomes available on Ollama Cloud
-- nemotron-3-ultra:cloud released 2026-06-04 and is too new for real-world nanobot agent validation
 - GLM-5.1:cloud achieves ~198 tok/s on Ollama Cloud
 - Agent model comparison report saved to `results/2026-06-07_ollama-cloud-agent-model-comparison.md`
 - User prefers Qwen model for deep research tasks (not currently in presets)
@@ -89,7 +85,10 @@ This file stores important information that should persist across sessions.
 - Wiki graph regeneration: run `wiki_graph_lint.py` + `wiki_graph_extract.py` after each ingest batch that adds graph metadata
 - Wiki source pages need explicit `slug` field (e.g. `slug: source-flash-attention`) and `graph.node_id` + `canonical: true` to avoid UNIQUE constraint collision with concept/entity pages sharing the same filename stem
 - `wiki_graph_extract.py` patched: skip duplicate slugs (first wins) instead of crashing on `nodes.slug` UNIQUE constraint
-- Wiki current state: 17 nodes, 125 edges, 1 broken ref (concept:llm — page not yet created, report-only)
+- Wiki current state: ~21 nodes, ~130+ edges (was 17 nodes, 125 edges after initial build)
+- Wiki source ingested: source-lego-mindstorms-continued-use (LEGO MINDSTORMS discontinuation, Pybricks alternative, SPIKE Prime successor)
+- Wiki entities: product-lego-mindstorms, product-pybricks, product-spike-prime
+- Wiki concepts: digital-preservation, alternative-firmware
 
 ## Reminder System