@dreb/coding-agent 2.66.0 → 2.66.2

package/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 (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).
 
-**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.
+**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. Persisted sessions whose recorded working directory is missing remain visible and resumable: Dashboard asks for an existing runtime directory, validates it before starting the child, shows both historical and effective paths, and leaves the original session header unchanged.
 
 **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)
 
@@ -131,6 +131,8 @@ See [docs/providers.md](docs/providers.md) for detailed setup instructions, incl
 
 **Custom providers & models:** Add providers via `~/.dreb/agent/models.json` if they speak a supported API (OpenAI, Anthropic, Google), including Bearer-only Anthropic-compatible endpoints. For custom APIs or OAuth, use extensions. See [docs/models.md](docs/models.md) and [docs/custom-provider.md](docs/custom-provider.md).
 
+**Output limits and retries:** `maxTokens` is the ordinary request maximum, including model overrides; explicit bounded internal calls may use less. Responses truncated at the model's configured output limit retry at that same limit. After exhaustion, genuine output-budget failures fail loudly, while possible full-context truncation enters one compact-and-retry recovery. The ChatGPT-backed `openai-codex` protocol rejects client-supplied output limits, so its built-in maximum remains server-controlled and dreb rejects `maxTokens` overrides for that provider.
+
 **Reasoning across model switches:** Exact-model signed, encrypted, or redacted reasoning state is replayed unchanged. Structured reasoning is portable only between models that share a provider and the `openai-completions` API when the destination accepts the source's recognized plain field (`reasoning_content`, `reasoning`, or `reasoning_text`). Other readable reasoning is retained as labelled plaintext in `<reformatted-pre-switch-reasoning>` markers with incompatible protocol metadata removed; opaque redacted or encrypted-only state is omitted for incompatible targets. This outbound conversion does not change session history, so switching back can replay the original state unless it was compacted or pruned. Custom models must also share provider identity and compatible API/signature behavior.
 
 ---

package/dist/core/agent-session.d.ts

@@ -372,6 +372,8 @@ export declare class AgentSession {
     dispose(): void;
     /** Full agent state */
     get state(): AgentState;
+    /** Effective runtime working directory used by tools, resources, and project discovery. */
+    get cwd(): string;
     /** Current session task list (read-only) */
     get tasks(): readonly SessionTask[];
     /** Current model (may be undefined if not yet selected) */