docs(wiki): document retrospection (daily transcript replay → memory)
Memory & Knowledge: a Retrospection bullet + the conflict-resolution update under
"Learning from outcomes"; Configuration: memory.retrospect + retrospect_hours.
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
docs(wiki): document memory.resolve_conflicts (opt-in conflict resolver)
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
docs(wiki): document the structural code graph, code_graph tool, RPL fan-in + rollover
- Memory & Knowledge: a "Structural code graph (opt-in)" section (graph.mode +
the code-graph feature + typed edges) and the code_graph agent tool
(callers/callees/impact/implementers).
- Configuration: knowledge.graph { mode, resolve_imports, max_edges_per_symbol,
rpl_impact } and llm.wake_on_rollover.
- RPL-Judgement: a note that file fan-in folds into the blast radius.
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
docs(wiki): GEO/AEO pass across all pages — answer-first intros, FAQs, question headings
Optimize every wiki page for AI answer engines (GEO/AEO) and classic SEO,
additively — all facts, commands, config keys, defaults, and links preserved:
- Answer-first, self-contained intros so each page stands alone if an AI surfaces
it with no other context (each restates what blumi is in one clause).
- TL;DR / "Key facts" blocks of atomic, extractable facts near the top.
- Question-style headings ("What is X?", "How do I Y?") matching natural queries.
- A FAQ (Q&A) section on each substantive page — the most AI-citable format.
- Consistent entity naming + acronyms expanded on first use (RAG, SEDM, RPL,
BYOK, mDNS, FCM, STT/TTS, …).
- Fixed stale version (0.3.0 -> 0.5.0) on Home.
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
docs: Dispatch + FCM push (Mobile-App + Configuration)
- Mobile-App: "Dispatch" section — per-node isolated threads + Broadcast
fan-out + fire-and-forget push, with inbox/thread/broadcast screenshots
and the zero-config FCM service-account drop-in.
- Configuration: "Push notifications (FCM)" section — enabled by file
presence (~/.blumi/fcm-service-account.json, chmod 600), HTTP v1,
token store + auto-prune, graceful no-op, never-commit secrets.
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
docs(config): comprehensive Configuration reference (every section)
Rewrite Configuration.md into a complete, runnable reference so anyone can set up
+ tune blumi from one page:
- Loading/layering (settings.json → project → env BLUMI_*), applying changes
(reload vs restart).
- Providers (preset table + kind/api_key_env/base_url) + full llm.* block.
- Every section with real fields + DEFAULTS + copy-paste JSON, grouped:
agent behavior (permissions, persona/personas, executor, brain, router, heal);
memory & knowledge (embeddings, memory, knowledge, acceleration) incl. the
enable + `blumi knowledge ingest` populate steps; surfaces (web, voice, gateway
telegram/discord/slack/whatsapp, grid, remote, workspaces, git); autonomy
(always_on, notify, hooks); tools (mcp_servers, lsp_servers).
- A realistic "putting it together" settings.json + auto-continue + the
MEMORY.md/USER.md files. Deep-dive cross-links throughout (all verified).
All fields/defaults transcribed from blumi-config structs (accurate, not invented).
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
docs(gateway): gateway.telegram.voice (off by default)
Configuration: document gateway.telegram {token, allowed_chats, voice}.
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
docs(notify): browser Web Push (VAPID) channel
#209d — Self-Management Completion notifications: add Web Push as a server-side
channel (Enable button, ~/.blumi/push.json, secure-context-only caveat).
Configuration: notify bullet now lists web_push.
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
docs(notify): completion notifications (desktop + gateway bot)
#209a — Self-Management: new Completion notifications section (server-side push:
desktop + gateway bot, notify.* config, --notify one-off). Configuration: notify
bullet.
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
docs(hooks): pre_tool_use now wired (tool-blocking)
#208 — Self-Management: split Lifecycle hooks into user_prompt_submit (inject
context) + pre_tool_use (gate tool calls); document non-zero-exit blocks,
matcher scoping, fail-open on infra errors, and reload-to-apply. Configuration:
note pre_tool_use can block a tool call.
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
Document lifecycle hooks (UserPromptSubmit) + config
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
Document cost-aware routing, always-on discovery, white-box memory
- Configuration: add `router` + `always_on` to the config reference (cross-refs).
- CLI-Usage: new TUI commands /route + /discoveries.
- Self-Management: full "Cost-aware routing" + "Always-on discovery" sections
(config blocks, safety, how to drive them).
- Memory-and-Knowledge: a "White-box memory (view/pin/edit/delete)" subsection
+ the /api/memory/* endpoints.
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
Document GPU acceleration, self-healing & evolution, new TUI commands
Refresh the help/wiki for the [Unreleased] features:
- CLI-Usage: new slash commands /open-workspace, /heal, /accel (+ /grid and
/autocontinue) and a `blumi accel` management row.
- Memory-and-Knowledge: a GPU acceleration section (Apple CoreML default, CUDA
opt-in, local-server/Ollama path, grid-embed offload) + acceleration/heal
config; update embeddings.backend="grid" to the real strongest-peer transport.
- Self-Management: a Self-healing & evolution section (reflex recovery, failure
to fix learning, evolution autonomy, cross-step verify, /heal surfacing).
- Grid: a GPU-aware embedding offload section (POST /api/grid/embed).
- Installation: GPU/embeddings build options (BLUMI_CUDA, gpu-cuda, lean default).
- Troubleshooting: GPU/accelerator + self-healing entries.
- Configuration: acceleration/heal/embeddings/memory/knowledge cross-refs.
Co-Authored-By: Blumi <ankur.nairit@gmail.com>
docs: comprehensive help wiki (install, config, CLI, gateway, mobile, grid, voice, self-mgmt, dev, troubleshooting)
Co-Authored-By: Blumi <ankur.nairit@gmail.com>