Plugins

Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.

High-reliability Feishu/Lark bridge for DeepSeek Harness: QR one-click auth, card-based commands and intent-confirmation cards, at-least-once zero-loss outbox, media in/out, /doctor session-log ZIP, and a reusable DSH Web GUI that lands sessions in the right workspace.

Mobile layout fixes for the Web UI on narrow screens: full-screen settings panel, one-row plugin nav, full-screen sidebar, centered popups, icon-only session-log button.

Unified token quota and usage statistics for dsh: multi-vendor rolling/payg quota with sidebar cards and provider ops, plus session-log token aggregation with trends, heatmap, and per-model breakdown.

Behavior-drift reports for DSH sessions: compares two session logs and reports tool-sequence alignment, tool mix, reasoning volume, timing, retries and file targets, with an optional CI threshold gate. Zero dependencies.

Agent billing and usage observability for dsh web: session-log direct-scan recording (zstd, per-event timestamps, watermark + lastSeq double dedup), multi-account rate profiles per provider and model, per-window live badge reading the window session id via React fiber, full glassmorphism dashboard with 14-day sparkline, budget alerts, relay-station balance queries and a 332-model official price library.

Memory Standard Protocol (mm) for DeepSeek Harness: layered MEMORY.md with hard budgets, frozen snapshots, mm:// URI interop, session-log digestion, mem_* tools and a standalone CLI.

Turn-based time tracking from dsh session logs: totals, per-day/project/provider/source rollups, tool-call counts, failure rates, and time-to-first-token — CLI plus an agent-callable timesheet tool, dsh-timesheet/v1 reports, zero runtime deps.

Disk-usage audit for dsh data directories: total size, per-directory breakdown, largest files, oversized-file warnings (session logs can hit hundreds of MB) and cleanup suggestions — CLI plus an agent-callable disk_audit tool, dsh-disk-audit/v1 reports, zero runtime deps, read-only.

Session repair button in the conversation header: detects & fixes session-log corruption — tool-call id swaps, empty call ids (`message must have tool source`), unknown event types from disabled plugins (marks `ignorable`), torn zstd tails, missing final-frame newlines; ghost-style UI, auto-backup before writes.

Google AI Studio-style floating preview for the Web UI: a draggable/resizable iframe preview with aspect-ratio and resolution presets, plus a VS Code-style code window with direct editing, confirmed writes, and session-log recording.

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

Model-driven context compaction for DeepSeek Harness. The agent decides when and what to compress, commits durable session-log replacements, and ships reversible tool-result compression with byte-exact hash retrieval.

Live change review for DeepSeek Harness: tracks write/edit tool calls per session, lists changed files above the composer and opens each file's line-level diff in a plugin-registered right-sidebar tab, with session-log / initial-version / Git comparison modes, per-change and per-file revert, subagent aggregation and SSE updates. A fork of cirelir/dsh-change-review rebuilt around the right sidebar.

Preventive content policy for DeepSeek Harness tool results: rewrite matched text with regex rules, or drop/truncate unpredictable payloads by field path before they are normalised, rendered, or persisted. The upstream counterpart to dsh-plugin-redact.

DSH session-log repair plugin: scan every stored session, detect a seq collision in the committed region or a torn trailing record, and repair it from a one-click Web UI, model tools, or the /dsh-session-log-repair command. Installing it also registers it

In-place redaction and row-level rollback for session logs, preserving the seq-equals-row-index invariant that makes deleting a middle row corrupt the entire log. Originals are copied to a quarantine sibling before any write, and the reader's own semantics are replayed as a pre-write gate.

Preventive content policy for tool results: rewrites matched text, and drops or truncates whole fields by path before a result is normalised, rendered or persisted, so an unreviewed payload never enters it. Ships inert with no built-in category or domain blocklist.

Real-time DeepSeek API balance (official endpoint) and today-spend estimate (this DSH instance session-log usage x per-model price table) for the DSH web: composer dock strip, always-on floating badge, full settings dashboard (7-day trend, per-model cost, editable price table and polling, history rescan). The API key never leaves the host.

Aborts startup when another live dsh instance holds the same DSH_HOME data directory, preventing the concurrent session-log writes that corrupt transcripts.