Add dashboard memory management

README.md

@@ -6,7 +6,7 @@ Use dreb if you want a coding agent that can run against direct APIs, coding sub
 
 ## Why choose dreb?
 
-- **Every session, on every device.** The [web dashboard](#web-dashboard) is a first-party browser UI for the same sessions the terminal runs: a fleet overview of all live and past sessions across projects, full chat with steering, live subagent observability, host file access, and settings — one synchronized state on desktop and mobile. Local-only by default; remote access is Tailscale-gated with device pairing.
+- **Every session, on every device.** The [web dashboard](#web-dashboard) is a first-party browser UI for the same sessions the terminal runs: a fleet overview of all live and past sessions across projects, full chat with steering, live subagent observability, host file access, dreb memory management, and settings — one synchronized state on desktop and mobile. Local-only by default; remote access is Tailscale-gated with device pairing.
 - **Model and provider freedom.** Authenticate with API keys or `/login` subscriptions, switch models at runtime with `/model`, scope model sets, tune thinking levels, route built-in providers through proxies, use cloud providers such as Bedrock/Vertex/Azure, or add local/proxy/custom models through [Custom Models](packages/coding-agent/docs/models.md) and [Custom Providers](packages/coding-agent/docs/custom-provider.md). See [Providers](packages/coding-agent/docs/providers.md) for the current setup list.
 - **A real development workflow.** [mach6](packages/coding-agent/docs/mach6.md) is a built-in issue-to-merge workflow: assess issues, plan work, open draft PRs, implement, push progress, run multi-agent reviews, independently assess findings, fix CI or review items, and publish. Plans, reviews, and progress live on GitHub as shared memory.
 - **Composable agent building blocks.** [Skills](packages/coding-agent/docs/skills.md) are markdown workflows loaded on demand; [extensions](packages/coding-agent/docs/extensions.md) are TypeScript modules for custom tools, commands, event hooks, UI components, renderers, keybindings, provider registration, permission gates, and workflow automation; [packages](packages/coding-agent/docs/packages.md) bundle skills, extensions, prompts, and themes for npm, git, or local sharing.
@@ -116,7 +116,7 @@ The same agent runtime powers multiple surfaces:
 - **RPC mode** — strict [JSONL stdin/stdout protocol](packages/coding-agent/docs/rpc.md) for non-Node clients and custom UIs.
 - **SDK** — import `@dreb/coding-agent` and create agent sessions directly in TypeScript.
 - **Telegram** — `@dreb/telegram` runs dreb as a bot with sessions, model controls, file upload/download, live tool status, and visible results for user-facing tools.
-- **Web dashboard** — `dreb dashboard` serves a browser UI (fleet overview of all sessions, full chat with steering, subagent observability, host file browser); local-only by default, remote via Tailscale + rotating pairing code. See [dashboard docs](packages/coding-agent/docs/dashboard.md).
+- **Web dashboard** — `dreb dashboard` serves a browser UI (fleet overview of all sessions, full chat with steering, subagent observability, host file browser, dreb memory editor); local-only by default, remote via Tailscale + rotating pairing code. See [dashboard docs](packages/coding-agent/docs/dashboard.md).
 
 ### Web dashboard
 
@@ -143,6 +143,8 @@ The dashboard is the visual face of dreb: every agent session on the host, live
 
 **Host files, explicitly.** Browse the host filesystem, upload/download, create folders, and start a new session in any directory — every file operation logged server-side.
 
+**Memories, repairable.** The Memories screen edits dreb memory scopes only: global `~/.dreb/memory` plus populated `.dreb/memory` directories for active/disk project roots (empty projects are omitted because entry creation is outside this screen). It shows the complete `MEMORY.md` index (with a warning when it exceeds the 200-line prompt convention), opens local index links in the current scope, provides visible loading feedback, displays existing entry metadata or parse errors and sanitized Markdown previews, preserves drafts on exact-revision conflicts, and synchronously cleans matching index links before deleting an entry. It does not create/rename entries or expose Claude memory paths.
+
 **Curated appearance themes.** A theme gallery in settings offers eight dashboard-native themes (entropist.ca, Dim, Solarized, Gruvbox, Caves of Qud, Van Gogh, plus the colorblind-safe Okabe-Ito and Paul Tol palettes), each with its own light and dark palette, plus a system/light/dark mode toggle. Choices are saved per browser and are independent of your TUI theme.
 
 Launch locally:

package.json

@@ -39,7 +39,7 @@
 		"node": "22.x"
 	},
 	"packageManager": "npm@11.5.1",
-	"version": "2.54.0",
+	"version": "2.55.0",
 	"dependencies": {
 		"@dreb/coding-agent": "*",
 		"@mariozechner/jiti": "^2.6.5",

packages/agent/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@dreb/agent-core",
-	"version": "2.54.0",
+	"version": "2.55.0",
 	"description": "General-purpose agent with transport abstraction, state management, and attachment support",
 	"type": "module",
 	"main": "./dist/index.js",

packages/ai/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@dreb/ai",
-	"version": "2.54.0",
+	"version": "2.55.0",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"type": "module",
 	"main": "./dist/index.js",

packages/coding-agent/README.md

@@ -81,7 +81,7 @@ Or use a custom provider (corporate proxy, Bedrock, etc.) — see [Custom provid
 
 Then just talk to dreb. All 13 standard built-in tools are enabled by default: `read`, `write`, `edit`, `bash`, `grep`, `find`, `ls`, `web_search`, `web_fetch`, `subagent`, `wait`, `watch_github_ci`, and `ask_user`. Use `--tools` to restrict to a subset (e.g., `--tools read,grep,find,ls` for read-only). Three additional tools — `search`, `skill`, and `tasks_update` — are always active regardless of `--tools`. `suggest_next` is active by default but excluded when `--tools` is specified. The model uses these to fulfill your requests. Add capabilities via [skills](#skills), [prompt templates](#prompt-templates), [extensions](#extensions), or [packages](#packages).
 
-**Also available:** [`@dreb/telegram`](https://www.npmjs.com/package/@dreb/telegram) — run dreb as a Telegram bot with live tool status and visible results for user-facing tools (`npm install -g @dreb/telegram`). [`@dreb/dashboard`](https://www.npmjs.com/package/@dreb/dashboard) — run `dreb dashboard` for a browser UI with fleet overview, full chat steering, generic fail-closed built-in slash-command discovery and execution, inline provider/API failures with partial output preserved, sanitized raster tool images plus sent user uploads retained as bounded transcript previews by default, a bounded all-agent subagent panel with drill-in, host file browser, curated appearance themes (per-browser light/dark), and Tailscale/rotating-code pairing (`npm install -g @dreb/dashboard`; see [docs/dashboard.md](docs/dashboard.md)). Tool images cross browser-facing transport as content-addressed references; browser-local Settings offers placeholders, bounded previews, or informed-opt-in originals, with size disclosure and confirmation above 1 MiB. Full-resolution HTML export remains self-contained. Compact SSE snapshots update live fleet cards without repeatedly fetching the cross-project inventory, and session drill-in hydrates state, messages, and background agents through one ordered snapshot request. Terminal provider failures show their reason on fleet cards, while transient failures clear terminal state when automatic retry begins and remain recorded inline on the failed attempt. Its top bar and persistent session header indicators report connecting, connected, retrying, resyncing, disconnected, or auth failed; bounded SSE replay plus an explicit snapshot barrier restores session state, tasks, and image references after a reload, restart, gap, backpressure disconnect, or stalled stream, while authenticated image routes recover bytes separately from authoritative transcripts.
+**Also available:** [`@dreb/telegram`](https://www.npmjs.com/package/@dreb/telegram) — run dreb as a Telegram bot with live tool status and visible results for user-facing tools (`npm install -g @dreb/telegram`). [`@dreb/dashboard`](https://www.npmjs.com/package/@dreb/dashboard) — run `dreb dashboard` for a browser UI with fleet overview, full chat steering, generic fail-closed built-in slash-command discovery and execution, inline provider/API failures with partial output preserved, sanitized raster tool images plus sent user uploads retained as bounded transcript previews by default, a bounded all-agent subagent panel with drill-in, host file browser, dreb memory editor with exact-revision saves and automatic index cleanup on delete, curated appearance themes (per-browser light/dark), and Tailscale/rotating-code pairing (`npm install -g @dreb/dashboard`; see [docs/dashboard.md](docs/dashboard.md)). Tool images cross browser-facing transport as content-addressed references; browser-local Settings offers placeholders, bounded previews, or informed-opt-in originals, with size disclosure and confirmation above 1 MiB. Full-resolution HTML export remains self-contained. The Memories screen is dreb-only (`~/.dreb/memory` and populated active/on-disk-session project `.dreb/memory`; empty projects are omitted), shows complete indexes with a >200-line warning, opens local index links within the selected scope, replaces stale editor content with visible loading feedback, surfaces malformed entry frontmatter for repair, preserves drafts on conflicts, and does not create/rename entries or expose Claude paths. Compact SSE snapshots update live fleet cards without repeatedly fetching the cross-project inventory, and session drill-in hydrates state, messages, and background agents through one ordered snapshot request. Terminal provider failures show their reason on fleet cards, while transient failures clear terminal state when automatic retry begins and remain recorded inline on the failed attempt. Its top bar and persistent session header indicators report connecting, connected, retrying, resyncing, disconnected, or auth failed; bounded SSE replay plus an explicit snapshot barrier restores session state, tasks, and image references after a reload, restart, gap, backpressure disconnect, or stalled stream, while authenticated image routes recover bytes separately from authoritative transcripts.
 
 **Platform notes:** [Windows](docs/windows.md) | [Termux (Android)](docs/termux.md) | [tmux](docs/tmux.md) | [Terminal setup](docs/terminal-setup.md) | [Shell aliases](docs/shell-aliases.md)
 

packages/coding-agent/docs/dashboard.md

@@ -10,6 +10,10 @@ over [RPC mode](rpc.md): the server maintains a pool of `dreb --mode rpc`
 child processes, one per live session. The server uses dreb's public session
 APIs for on-disk inventory/delete and serves its own host file API.
 
+## Memories
+
+The Memories tab keeps the global dreb scope visible and lists only populated project `.dreb/memory` directories discovered from active and on-disk sessions. Empty or missing project scopes are omitted because the dashboard edits and deletes existing documents but does not create entries. The complete `MEMORY.md` index and direct-child entries are editable with revision conflicts, sanitized previews, and synchronized index cleanup on delete. Local direct-child links in the rendered index open the entry within the current scope; external links retain normal safe link behavior. Scope and document changes immediately hide stale editor content and show loading feedback while fresh data is read.
+
 ## Launching
 
 ```bash
@@ -123,6 +127,7 @@ networking window above.
 | **Session view** | Full chat drill-in. Markdown streaming transcript (text, thinking blocks with expand preference, inline provider/API failures with partial output preserved, agent-result cards, tool cards with bespoke read/write/edit/bash bodies plus full expandable inputs, markdown-rendered results for markdown-contract tools like subagent/skill/web_fetch/suggest_next, and inline tool-result images, compaction/branch summaries, custom messages), per-message copy, tasks panel, a bounded scrollable subagent panel that lists every retained agent newest-first with full running/done counts, status line with elapsed time plus ■ stop and compaction/retry aborts, a persistent session-header live indicator, and an info bar with cwd, branch, session name, token breakdown, cost/(sub)/daily rollup, ctx%, median tok/s, and a stats popover. Composer supports auto-grow, history, `/` autocomplete from `get_commands`, image attach/paste with sent images retained as user-message previews, queued-message chips with restore-all, steer/follow-up modes, and suggest-next. Registered built-in slash commands are discovered generically, deduplicated ahead of colliding resource commands, and intercepted before prompting: dashboard actions cover settings, model, scoped-models, export/import, name/session stats, fork/tree, new/compact/dream, resume/reload, and quit. `/scoped-models` deep-links to the Settings editor with the session's current cwd as project context; login/logout show an explicit not-yet-implemented notice, while copy/hotkeys/buddy give terminal-only guidance. Future built-ins are intercepted automatically. The RPC prompt boundary rejects any built-in that reaches it during command-loading races or failures, so slash text cannot leak to the model. Attachments are retained and the command is visibly rejected rather than silently discarded. The ⋯ menu covers export HTML, compact, rename, fork-from-message, loaded context, and tool expand/collapse. Session names update live from manual rename or auto-naming. Extension UI requests for select/confirm/input/editor render as modals; a rich `ask`/`ask_user` request renders inline as a single wizard that presents all its questions together — each with Markdown-formatted question text, choices, optional free text — plus an in-card Stop agent action, Escape-to-stop, and the authoritative auto-stop countdown, and is answered as one batch submit. Pending questions set needs-attention state and use the existing hidden-page notification path. Extension notifications render as toasts. |
 | **Subagent view** | Read-only transcript of a background agent: live events via the RPC relay, hydrated from the agent's on-disk session log (`/subagents/:agentId/messages`) so the transcript survives browser reloads. Shows the task, streaming output, tool activity, and any safe Dispatch Arbiter changed/unchanged/failure records with the final agent/model/thinking. No raw arbiter output is displayed or transported. No composer — subagents can't be steered yet; the parent session controls them. |
 | **Files** | Host-wide browser with places shortcuts (home, /tmp, project roots), breadcrumbs to `/`, new-folder, download, drop-zone/picker upload with explicit collision prompts, and "new session here" on any directory. It also shows the **effective global nested-context trust** for the displayed canonical directory: untrusted, trusted by that root, inherited from a granting root, or global expert trust-all. You can trust the displayed folder and descendants, or untrust the actual granting root; untrusting an inherited folder removes that root's trust for all descendants. |
+| **Memories** | Dreb-only memory management for `~/.dreb/memory` and `.dreb/memory` under active/disk project roots. It lists existing `MEMORY.md` indexes and direct child `.md` entries only (no Claude paths, create, or rename), shows entry frontmatter or metadata errors so malformed files can be repaired, renders sanitized Markdown preview beside a raw editor, and uses exact SHA-256 revisions so stale saves/deletes return conflicts while preserving drafts. The index view is complete, not truncated, and warns when it exceeds the 200-line memory-index convention. Entry deletion requires both entry and index revisions, removes only matching safe Markdown-link index lines (`file.md` / `./file.md`), writes the cleaned index atomically before unlinking the entry, and rolls back loudly if the unlink fails. |
 | **Settings** | Persistent defaults (default model, thinking level, steering/follow-up queue modes, auto-compaction, auto-retry) via `get_settings`/`set_settings` — validation errors are shown verbatim. The scoped-models editor controls model cycling for new sessions only: grouped search, model/provider/all toggles, responsive controls, accessible up/down partial-scope ordering, and save/reset. An absent `enabledModels` is future-inclusive all models in registry order and cannot be reordered; a partial scope is a non-empty ordered list of canonical `provider/model` references. Editing legacy glob, fuzzy, or thinking-suffix values saves normalized exact references. The selected context reads effective global + project settings but writes global; a project-level `enabledModels` shadow is warned. The global-only Dispatch Arbiter card exposes enable/disable, exact authenticated model selection, thinking, guide path, and readiness guidance; model-less enablement is blocked and RPC/runtime validation remains fail-closed. Entering Settings flushes pending writes and reloads durable global + project settings, so external edits appear; read, parse, or write failures fail loudly instead of showing stale settings. The global-only nested-context policy lists every explicit trusted root for audit and revoke, offers a simple add-by-path control, and includes a prominently warned expert trust-all toggle; the Files view remains the primary place to grant trust while browsing. Most defaults seed new sessions; context-trust changes are observed by active main/subagent processes for future lazy loads, but cannot remove already injected content. Dashboard-local preferences (always expand thinking, transcript image display mode, needs-attention notification permission) live in the browser, alongside an appearance section: a theme gallery of eight curated themes (entropist.ca, Dim, Solarized, Gruvbox, Caves of Qud, Van Gogh, and the colorblind-safe Okabe-Ito and Paul Tol) with live preview cards and a system/light/dark mode selector, saved per browser. Shows the current rotating pairing code on the host/local dashboard, plus the paired-devices list with unpair. |
 | **Pairing** | Remote first-login: identity echo, rotating-code entry, and the security copy explaining what pairing grants. |