@dreb/coding-agent 2.64.6 → 2.65.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -81,7 +81,7 @@ Or use a custom provider (corporate proxy, Bedrock, etc.) — see [Custom provid
81
81
 
82
82
  Then just talk to dreb. All 13 standard built-in tools are enabled by default (unless `backgroundAgents.maxConcurrentSubagents` is `0`, which removes `subagent` from new parent sessions): `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).
83
83
 
84
- **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, unified dismissible session banners, explicit navigation that preserves viewed closed transcripts as read-only snapshots, a TUI-parity rolling TPS indicator with long-term delta, 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 with per-browser light/dark mode and font selection (theme default, Google-hosted IBM Plex Mono, or the bundled self-hosted JetBrains Mono, Fira Code, Iosevka, OpenDyslexic, and Atkinson Hyperlegible), and resilient Tailscale/rotating-code pairing with a configurable 180-day default and advance expiry warnings (`npm install -g @dreb/dashboard`; see [docs/dashboard.md](docs/dashboard.md)). Tool images cross browser-facing transport as content-addressed references; in dashboard mode each unique image crosses the RPC stdout pipe at most once per child process (later occurrences become references), and 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. While drill-in remains mounted, authoritative detail refreshes keep its header current, confirmed model/thinking changes are reconciled without stale snapshot rollback, and post-compaction context uses a conservative estimate until fresh provider usage arrives. 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.
84
+ **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, dismissible session banners confined to the transcript column without shifting the fleet sidebar, a grouped header with back navigation on the left, model/thinking controls in a separate row, and the fleet sidebar toggle in the bottom usage/context-stats row (also available with details collapsed), explicit navigation that preserves viewed closed transcripts as read-only snapshots, a TUI-parity rolling TPS indicator with long-term delta, 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, a fleet sidebar on session/subagent views with the fleet cards' project/status/reasons, activity/latest-assistant preview, subagents, tasks, model/context/cost, and message/activity metadata (deterministic order, persisted desktop collapse and pointer/keyboard-resizable width, highest-priority status border while hidden, safe-area-aware mobile drawer with managed focus and Escape-to-close without aborting the agent), host file browser, dreb memory editor with exact-revision saves and automatic index cleanup on delete, curated appearance themes with per-browser light/dark mode and font selection (theme default, Google-hosted IBM Plex Mono, or the bundled self-hosted JetBrains Mono, Fira Code, Iosevka, OpenDyslexic, and Atkinson Hyperlegible), and resilient Tailscale/rotating-code pairing with a configurable 180-day default and advance expiry warnings (`npm install -g @dreb/dashboard`; see [docs/dashboard.md](docs/dashboard.md)). Tool images cross browser-facing transport as content-addressed references; in dashboard mode each unique image crosses the RPC stdout pipe at most once per child process (later occurrences become references), and 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. Direct sidebar switching, including leaving a closed session, loads the destination with its own screen state and per-session text draft; abandoned hydration cannot overwrite the new view. While drill-in remains mounted, authoritative detail refreshes keep its header current, confirmed model/thinking changes are reconciled without stale snapshot rollback, and post-compaction context uses a conservative estimate until fresh provider usage arrives. 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.
85
85
 
86
86
  **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)
87
87
 
package/docs/dashboard.md CHANGED
@@ -133,19 +133,63 @@ networking window above.
133
133
  | Screen | What it does |
134
134
  |---|---|
135
135
  | **Fleet** | Home. Live-first: one grid of every live session at the top — status chip (● running / ◆ needs-attention / ○ idle / ✕ error), project path, activity line, live subagent lines, tasks progress, ctx%, model, terminal provider-error reason, last activity. Live cards keep a deterministic order by project path, then session start time; needs-attention cards badge the browser tab without jumping around. Below the grid: past sessions grouped by project, three compact rows per group with an "all N on disk" expander, resume and delete. |
136
- | **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, a shared dismissible banner region for model fallback, extension notices, retry/compaction/paused/provider status, and local action results, a controls-only dock line with elapsed time plus ■ stop and explicitly labelled retry/compaction aborts, a persistent session-header live indicator, and an info bar with cwd, branch, session name, token breakdown, cost/(sub)/daily rollup, ctx%, a TUI-parity latest-100 median TPS indicator (`~31 tok/s [100] · 10% ↑ median [10000]`), 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 for the viewed session render in its banner region; other sessions' and app-global notices use the fixed top-center toast stack. |
136
+ | **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, a shared dismissible banner region for model fallback, extension notices, retry/compaction/paused/provider status, and local action results, a controls-only dock line with elapsed time plus ■ stop and explicitly labelled retry/compaction aborts, a persistent session-header live indicator, and an info bar with cwd, branch, session name, token breakdown, cost/(sub)/daily rollup, ctx%, a TUI-parity latest-100 median TPS indicator (`~31 tok/s [100] · 10% ↑ median [10000]`), and a stats popover. A fleet sidebar lists every other live session beside the transcript with the fleet cards' project, status/reasons, activity/latest-assistant preview, running/done subagent summaries, task progress, model, context, cost, message count, and last activity, deterministically ordered by project path then session start time (the fleet page's comparator), so needs-attention/error entries are emphasized — a filled attention chip or outlined error chip plus an entry border — without moving position; clicking an entry navigates to that session, desktop collapse and pointer/keyboard-resizable width persist browser-locally (default expanded, 260px), the hidden toggle border reflects the highest-priority other-session status, and neither sidebar nor toggle renders when no other live sessions exist. The subagent drill-in shows the same sidebar with its parent session excluded. 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 for the viewed session render in its banner region; other sessions' and app-global notices use the fixed top-center toast stack. |
137
137
  | **Subagent view** | 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. While the child is running, a composer sends the user's text unchanged to that specific child as steering input, displays its pending steering queue, and reports its effective `one-at-a-time` or `all` delivery mode. Completed, failed, rehydrated, and unavailable children remain read-only. |
138
138
  | **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. |
139
139
  | **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. |
140
140
  | **Settings** | Persistent defaults (default model, thinking level, steering/follow-up queue modes, auto-compaction, opt-in continuation of pending work after successful automatic compaction, auto-retry) via `get_settings`/`set_settings` — validation errors are shown verbatim. The continuation option is off by default, can keep unattended model turns and costs running indefinitely, does not restart completed answers, and never affects manual `/compact`. The tab-title card exposes the default-enabled generator toggle and an exact authenticated `provider/model` picker; an unset model clearly retains Explore-agent routing, a pinned model can be cleared back to that route, and edits apply to new unnamed sessions. 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, including **Max concurrent subagents** (default 4). Setting it to 0 starts new parents without the subagent tool and tells the parent model to perform normally delegated work itself; positive values cap running children per parent session. 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 plus system/light/dark mode and Theme default/IBM Plex Mono/JetBrains Mono/Fira Code/Iosevka/OpenDyslexic/Atkinson Hyperlegible font selectors, saved per browser. Shows the current rotating pairing code on the host/local dashboard, the 1–3650 day lifetime used only for future pairings (180-day default), and paired-device expiry dates with unpair. |
141
141
  | **Pairing** | Remote first-login: identity echo, rotating-code entry, and the security copy explaining what pairing grants. |
142
142
 
143
+ ### Fleet sidebar controls and session switching
144
+
145
+ The sidebar uses the same display summary as fleet-page cards, but its entire
146
+ card navigates rather than adding a destructive stop-runtime button. Activity
147
+ prefers working text, then a suggested-next command, then the latest nonblank
148
+ assistant text (bounded to 200 characters), with the server's preview as fallback
149
+ for an unvisited transcript. It shows running/done counts and up to three live
150
+ subagent summaries; unavailable optional metadata is omitted.
151
+
152
+ When the desktop sidebar is collapsed or the mobile drawer is closed, the Fleet
153
+ toggle border reflects **error > needs attention > running > idle** across its
154
+ other-session cards, including session-local terminal errors. The viewed session
155
+ (or parent of a viewed subagent) is excluded. Existing theme status colors and
156
+ an accessible textual description communicate the result; card order never changes.
157
+
158
+ On desktop, drag the right-edge separator or focus it and use Left/Right arrows
159
+ (10px steps), Home (minimum), or End (maximum). The initial width is **260px**;
160
+ the preferred range is **240–560px**, constrained by available space to reserve
161
+ **360px** for the transcript plus the separator. The browser saves the preferred
162
+ width under `dreb.dashboard.sessionSidebarWidth`, independently of
163
+ `dreb.dashboard.sessionSidebarCollapsed`. Narrowing the window clamps only the
164
+ rendered width; widening restores the saved choice. Invalid values fall back to
165
+ the default or clamp to the allowed range. Unavailable localStorage leaves the
166
+ controls usable in memory. A cancelled drag does not replace the saved width.
167
+ These preferences are shared by session and subagent screens, not by the server.
168
+
169
+ Direct sidebar navigation, browser back/forward, and subagent identity changes
170
+ load the destination's transcript with fresh screen-local state. Unsent text
171
+ drafts remain associated with each live session for the tab's lifetime;
172
+ attachments, modals, and local errors do not transfer. Leaving a closed session
173
+ releases its retained snapshot as before. Navigation aborts abandoned hydration,
174
+ and late screen actions cannot hydrate or operate on the newly viewed session.
175
+
143
176
  ### Notifications and explicit navigation
144
177
 
145
178
  The session banner region is the single surface for notices belonging to the
146
- session being viewed. Each banner has its own dismiss control, persists until
147
- dismissed or cleared by its source lifecycle, and caps long text with internal
148
- scrolling so its controls remain reachable on mobile. Dismissing a status banner
179
+ session being viewed. It lives inside the transcript column in both session and
180
+ subagent views, aligned with transcript content; showing or dismissing banners
181
+ does not move or shorten the fleet sidebar. Each banner has its own dismiss
182
+ control, persists until dismissed or cleared by its source lifecycle, and caps
183
+ long text with internal scrolling. The stack also has a bounded scroll area so
184
+ multiple notices do not consume the composer. The header keeps back navigation
185
+ on the left, session identity in the middle, and live/details controls on the
186
+ right. Model/thinking controls occupy a separate row. The fleet sidebar toggle
187
+ is on the left of the bottom usage/context-stats row, separate from the back
188
+ link; collapsing details hides the stats but leaves this toggle available.
189
+ Subagent views likewise put the toggle in a bottom header row. On mobile the
190
+ title moves below navigation rather than scattering controls around a long title.
191
+ If a short viewport forces the header to shrink for the composer, the header
192
+ scrolls internally so its bottom controls remain reachable. Dismissing a status banner
149
193
  is presentation-only: provider/error state, Fleet needs-attention state, tab
150
194
  badges, and hidden-page notifications remain accurate until the underlying
151
195
  runtime reports recovery. Genuinely app-global notices and extension notices
@@ -272,9 +316,12 @@ preview to 256 Unicode characters. Internal parent paths and complete searchable
272
316
  transcript text never cross this browser boundary. After creating, resuming,
273
317
  stopping, or deleting a session, the client narrowly refreshes the disk list
274
318
  through `GET /api/sessions` rather than reloading the whole fleet. While the
275
- Fleet screen is visible, it polls each live runtime's
276
- stats no more often than every 30 seconds. That poll is single-flight, retains a
277
- card's last good stats if an update fails, and surfaces failures in the Fleet UI.
319
+ Fleet screen or a session/subagent fleet sidebar is visible, it polls live-runtime
320
+ stats on a shared 30-second cadence. That poll is single-flight, retains a
321
+ card's last good stats if an update fails, and surfaces failures in the visible
322
+ fleet surface. Hiding/unmounting stops that surface's timer. Session switching
323
+ neither accelerates nor restarts the cadence, and showing sidebar summaries
324
+ never hydrates every card's transcript or refetches the entire fleet.
278
325
 
279
326
  For the activity preview, a card prefers the newest assistant text derived from
280
327
  its hydrated client transcript entries. Until those entries exist, the
@@ -452,7 +499,19 @@ status chips, project paths, activity and subagent text, and past-session
452
499
  labels wrap within their cards or rows rather than spilling off-screen. The
453
500
  session view prioritizes read-and-steer (model/thinking switchers collapse into
454
501
  ⋯, and task/subagent panels default collapsed), and the file table shows name +
455
- download only.
502
+ download only. The session fleet sidebar becomes a fixed overlay drawer —
503
+ hidden by default regardless of the desktop collapse preference, opened from
504
+ the session bar, closed by tapping the scrim or pressing Escape, and an entry
505
+ tap navigates and closes — keeping the transcript and composer at full width
506
+ by default. The drawer respects device safe-area insets. Its closed contents are
507
+ hidden from keyboard navigation and assistive technology; opening moves focus
508
+ to its close button, Tab stays within the drawer, and closing returns focus to
509
+ the previous control when it is still available. Escape closes the drawer without
510
+ also stopping an agent waiting for a question response. Breakpoint changes update
511
+ both layout and toggle behavior immediately, close any open mobile drawer, and
512
+ preserve the separate desktop collapse and preferred-width settings. The desktop
513
+ resize handle is absent on mobile; saved desktop widths never change mobile
514
+ drawer geometry.
456
515
  Composer modes, abort, and needs-attention affordances are never reduced away
457
516
  — steering a running agent from a phone is the primary remote use case.
458
517
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@dreb/coding-agent",
3
- "version": "2.64.6",
3
+ "version": "2.65.0",
4
4
  "description": "Coding agent CLI with read, bash, edit, write tools and session management",
5
5
  "type": "module",
6
6
  "drebConfig": {