dsh-auto-continue

dsh-auto-continue

Recover interrupted DSH sessions automatically, with an optional loop to continue after successful turns.

English · 中文

What It Does

Automatic recovery for DeepSeek Harness, in the Web UI and desktop app. When a recoverable failure interrupts a session, the plugin sends your configured continuation prompt through DSH. The engine runs inside the host process, so it keeps watching while browser tabs are closed; all tabs share that engine. Recovery is enabled by default. Continuing after successful turns is a separate, opt-in autonomous loop.

Smart recovery (all configurable):

• Error classification — transient failures (network / timeout / 5xx / 429…) are auto-resumed; permanent ones are skipped and notified, because retrying them never helps. A failure counts as permanent when its HTTP status is 401/403 or its code/message matches auth, credential/API-key, balance/quota, unknown-model, or context-length/overflow keywords. Provider-specific exceptions can be opted into with literal custom retryable patterns; turn classification off to resume everything
• Adaptive backoff — consecutive failures wait longer each time (cooldown × factor: 20s → 40s → 80s…), capped at the max backoff, instead of hammering a broken upstream
• English / Chinese localization — the settings card, built-in resume / guard / loop text, and browser notifications follow DSH's active UI language (initially selected from the browser language). Only en and zh are supported; other languages fall back to Chinese. Switching languages updates built-in defaults without overwriting custom text
• Templated continue text — continueText supports {code} {message} {status} {tool} {turn} {errorCount} {sessionTitle} {elapsed} placeholders, so the resume message can carry the failure context ("Continue ({tool} failed: {code})"); a separate template fires on max-tokens (e.g. "Continue the output without repeating anything already generated")
• Idempotency guard — before resuming, the plugin inspects the last tool call: if its result is unconfirmed (the turn died mid-tool, e.g. a git push that may have gone through), the resume message tells the model to check state first and not to rerun; if the tool is confirmed done, it says so and asks not to repeat it; a failed tool gets no guard (retrying it is the point). Both guard texts are configurable ({tool} / {result} placeholders)
• Silent turn resume — recover an observed model step or reasoning-only response that completes without visible output. A no-op turn with no model activity is left alone. Text, tool calls, images and extension blocks count as visible, including streamed output. Unobserved turns are not guessed to be silent. Explicit no-visible-output markers also recover after restart. Disabling Resume silent turns cancels queued silent sends; silent turns never reset the retry cap, even while the option is off.
• Autonomous loop — off by default (resumeCompletedTurns). When enabled, normally completed turns continue after the grace period, without the recovery cooldown or attempt cap. Reasoning-only turns and explicit no-visible-output endings still consume the recovery budget and obey backoff. Global pause, session pause, manual Stop and disabling the option stop the loop. Its prompt is separate from the loop guard’s prompt (continueTextLoop, default Continue).
• Pause — a global Pause auto-continue toggle in the settings card stops automatic sends from live events and startup scanning; per-session pauses (e.g. via a notification button) suspend only one session until they expire. The Resume now notification button is the one explicit exception: pressing it is the user asking for exactly one send, pause or not
• Notification buttons — notifications carry Resume now (send immediately, ignoring cooldown, the consecutive cap and any pause) and Pause this session 1h actions
• Loop guard — watches running turns too. Four signals trip the guard, which cancels the turn and restarts it with a configurable loop text ("stop repeating, try another way"): the model repeating the exact same message several times (any length — e.g. "Let me test variants of the regex…" ×7), repeated near-duplicate paragraphs inside one streamed assistant message, many short messages inside a short time window with no tool call in between (the "Let me read…" spin), or the same tool called repeatedly with the same arguments and the same results (a changed argument or result counts as progress). The cancel carries an internal marker so it is never confused with a user stop — the restart only happens for guard-initiated cancels. Thresholds, the time window and the loop text are configurable
• Stats panel — the settings card shows today's auto-continue count, recoveries, failures, permanent skips, give-ups and loop breaks, broken down by error code, with a one-click reset
• Browser notifications — optional alerts when auto-continue fires, gives up, or hits a permanent error; the browser asks for permission on first use, and nothing is shown again after a denial

It watches the live event streams and reacts to:

Recovery stops for: manual Stop, policy rejection (blocked), paused sessions, subagent sessions and the consecutive-attempt cap. A new turn or manual user message cancels a queued continuation. Live interrupted markers are left to the startup recovery scan. Recoverable failures during cooldown are deferred, not discarded. If an interrupted session already has queued turns, the continuation runs first and the existing turns retain their order behind it. The loop guard can separately cancel and restart a running turn that is repeating itself.

How It Works

The host-side engine subscribes to the session event firehose inside the dsh host process — one engine shared by every browser tab. On an interruption it waits a grace period (default 3 s) — if the host starts a new turn by itself (turn/start), the auto-continue is cancelled — then sends the configured text through the agent registry (agent.followup, the same queue the Send button uses). When that queue already contains turns, the engine promotes only its newly inserted continuation before the host wakes the agent; it does not remove or reorder the queued user turns.

On host boot it also scans the live sessions: a session whose last turn ended with a non-human reason within the scan window (default 15 minutes), with no later turn/start or user message, gets resumed automatically too (e.g. the host crashed while the browser was closed — the agent-loop resumes the session and the engine picks it up).

The browser half is a thin shell: the settings card, plus a status bridge that shows notifications (with Resume now / Pause this session 1h buttons, routed back to the host engine) and feeds the card's stats / paused-sessions panels.

Recovery workflow

The diagram summarizes the automatic recovery path, the loop-guard restart path, and the exit to human intervention. Click it to open the full-size version.

Quick Start

DSH plugins install into a profile (dsh web → web profile). The commands below install into the web profile; restart dsh web after installation. In the desktop app, install through its Plugins page instead.

Compatibility

DSH 0.1.0-rc.6 and earlier are unsupported. Automated runtime checks cover 0.1.7-rc.2 and 0.2.0-rc.1. Desktop app versions and embedded DSH runtime versions are different; use the runtime version when checking compatibility. For the CLI, run dsh --version; see official DSH releases for available versions.

Plugins 0.11.9 and 0.12.0 are rejected by DSH 0.2.0-rc.1’s version check. Upgrade the plugin to 0.12.1 or newer; its existing configuration-form integration works on this runtime. See #50.

On current DSH, Settings → Built-in plugins is a component inventory, not the configuration editor. Use the main Plugins page. The screenshots below use DSH 0.2.0-rc.1 + plugin 0.12.1. If you previously installed with a symlink or hand-written loader entry, see Migrating an older installation.

From npm (recommended)

Published as dsh-client-auto-continue:

dsh plugin --profile web add dsh-client-auto-continue@latest
dsh web

Updating an installed plugin

Let active work finish and stop DSH. Run the npm command above again to replace the installed version with @latest, then restart DSH and reload the browser. Existing configuration overrides remain in the profile. For a desktop installation, update the plugin from that app’s Plugins page and restart the app; updating the CLI’s web profile does not update the desktop profile.

Directly from GitHub (no clone needed)

Installs straight from the repository's default branch — built artifacts are committed, so no local clone or build step:

dsh plugin --profile web add github:HsiangNianian/dsh-auto-continue
dsh web

This tracks the main branch rather than released tags — great for trying the latest changes, while the npm method above is the stable choice. Switching between install sources is just re-running dsh plugin --profile web add <other-spec>; the profile dependency is replaced in place.

From this repository

Use Node.js 22, the version used by CI.

git clone https://github.com/HsiangNianian/dsh-auto-continue.git
cd dsh-auto-continue
npm ci
npm run build

# the package carries its own cordis.patch.yml (dsh.bundle.patch),
# so the plugin row registers itself
dsh plugin --profile web add "link:$(pwd)"

dsh web

Migrating an older installation

A manual loader entry can start the engine without registering a bundle in the Plugins page. Use the profile's package manager to install the bundle; a symlink and insert entry alone are no longer the recommended setup.

1. Let active work finish, then stop dsh web. Back up package.json, cordis.patch.yml and pnpm-lock.yaml in ~/.dsh/profiles/web/, plus ~/.dsh/settings.yaml if it exists. If you set DSH_HOME, use that directory instead of ~/.dsh.

2. Keep your existing auto-continue values. Remove only the manually added auto-continue row inside an insert list (and the list if it becomes empty). The installed bundle supplies that row. A top-level - id: auto-continue with config: is a configuration override: keep it.

3. Install with either the npm or GitHub command above. In the profile's package.json, dsh.profile.bundles should now include dsh-client-auto-continue, alongside the existing DSH bundles. If it already does and the plugin appears in Plugins, this part is already complete.

4. On DSH 0.1.7 / 0.2, merge any saved values from the old settings.yaml → auto-continue section or the removed row's config into the profile's cordis.patch.yml. For example, a custom cooldown becomes:

   - id: auto-continue
     config:
       cooldownMs: 45000 # example: preserve your own saved value
   

   Merge into an existing override instead of adding another one. Keep unrelated settings intact. DSH 0.1.7 / 0.2 reads this entry config; editing the old settings.yaml section will not update the new form.

5. Start dsh web again and reload the browser. Open Plugins → dsh-client-auto-continue, expand Auto continue, and check that your values are present. Save a change and reload to confirm it persists.

The include:auto-continue label in Built-in plugins is a normal loader prefix. It does not, by itself, indicate a legacy install or a duplicate engine.

Verify & uninstall

dsh --profile web --dump-config | grep -A 4 'id: auto-continue'

The composed config should contain one id: auto-continue entry. In Plugins → dsh-client-auto-continue, check that the component is Running and that expanding Auto continue shows editable fields. With verbose logging enabled, engine activity appears in the terminal running DSH.

dsh plugin --profile web remove dsh-client-auto-continue   # npm / repo install
# also remove this plugin's config override from cordis.patch.yml, if present
dsh web

Troubleshooting

• “Skipping profile bundle” / “incompatible with dsh 0.2.0-rc.1”: update to plugin 0.12.1 or newer in the profile the app actually uses, then restart it. A version exemption is not needed for this fix.
• Enabled, but no configuration fields: open the main Plugins page, select the package and expand Auto continue. The Built-in plugins status page has no editable fields.
• /api/auto-continue-bridge returns 404: check the DSH startup log and composed config to confirm the host component loaded. Refreshing the settings card cannot start a missing host component.

Configuration

On DSH 0.1.7 / 0.2, open Plugins from the main sidebar, choose dsh-client-auto-continue, then expand the Auto continue card. This is separate from Settings → Built-in plugins, which only lists component status. Older DSH versions use Settings → Plugins → Plugin configuration.

Click the card header or its right-hand chevron to show the fields. The expanded card also contains a live stats panel (today's activity with a reset button) and paused sessions (each with a resume button).

The settings card groups controls by handoff, safety, recovery, loop breaking, and live status. Its header also keeps the open-source repository and a Star on GitHub shortcut within reach.

DSH 0.1.7 / 0.2 stores these values in the auto-continue entry's config in the active profile patch (~/.dsh/profiles/web/cordis.patch.yml for the default web profile). Save applies changes live without restarting the engine. Omitted fields use the defaults below.

Startup recovery polls every three seconds for sessions that load late, up to freshMs after the engine starts. Each settled session history is inspected once. scanLimit limits eligible recoveries per pass, so healthy or permanent-error sessions cannot crowd out interrupted ones. Pausing suspends recovery within the same window; unloading cancels the poller.

The browser mirrors DSH's active language into the internal locale field. Leave the seven localized text fields empty or omit them to follow that language automatically; any non-empty value is treated as your own template and is never rewritten when the language changes:

- id: auto-continue
  config:
    locale: 'en' # normally managed by the browser
    paused: false
    continueText: ''
    resumeSilentTurns: true
    resumeCompletedTurns: false
    continueTextSilent: ''
    continueTextLoop: ''
    continueTextMaxTokens: ''
    guardTools: true
    guardPendingText: ''
    guardDoneText: ''
    graceMs: 3000
    cooldownMs: 20000
    maxConsecutive: 3
    scanOnBoot: true
    scanLimit: 8
    freshMs: 900000
    verbose: true
    classify: true
    retryableErrorPatterns: ''
    backoffFactor: 2
    backoffMaxMs: 300000
    notify: false
    loopGuard: true
    loopShortChars: 40
    loopWindowMs: 30000
    loopShortCount: 12
    loopRepeatText: 4
    loopToolRepeat: 5
    loopText: ''

auto-continue:
  cooldownMs: 45000

How the card works:

• Edits are staged — nothing reaches the disk until you hit Save; an unsaved badge marks the card while drafts are pending, and Discard drops them
• A field you changed shows an Overridden badge with a per-field Reset to default button that removes the override and restores the inherited value (normally the built-in default)
• Boolean fields are tri-state: Inherit (use the default) / On / Off
• Invalid drafts (non-numbers, values below the minimum) block the save with a hint
• In a read-only deployment the card shows the stored values but disables every control
• Changes apply immediately after Save and persist in the active profile config (or ~/.dsh/settings.yaml on older hosts)

For a provider-specific error that is safe to resume (confirm first that manually sending "continue" recovers), add a narrow, stable fragment rather than disabling classification globally:

- id: auto-continue
  config:
    retryableErrorPatterns: |-
      Upstream rejected the request as invalid

Patterns are literal substrings, not regular expressions. Blank lines are ignored; any matching line wins before the built-in permanent-error rules. Cooldown and consecutive-attempt limits still apply.

continueText (and continueTextMaxTokens, continueTextSilent, continueTextLoop) accept the placeholders {code}, {message}, {status}, {tool} (last tool call before the failure), {turn}, {errorCount} (consecutive failures including this one), {sessionTitle} (from the session list) and {elapsed} (time since the failure, e.g. 1m5s) — e.g. Continue ({tool}: {code}) becomes Continue (git push: UPSTREAM). The guard texts accept {tool} and {result} (a truncated excerpt of the last tool output).

Privacy & permissions

The recovery engine runs inside the DSH host. The browser provides the configuration card, live status and optional notifications:

• The engine reads session events and history through DSH's services. The browser talks to that host; the plugin adds no third-party service or credential store
• Recovery sends your configured text through agent.followup. The loop guard can cancel a looping turn through agent.cancel before sending its recovery prompt. Resumed agents continue with the session's existing tools and permissions
• Saving configuration uses DSH's settings API: the active profile patch on DSH 0.1.7 / 0.2, or ~/.dsh/settings.yaml on older hosts
• Retry counters, cooldown timestamps, per-session pauses and stats stay in host process memory and reset when the engine restarts. The global paused setting is saved with your other configuration
• Browser notifications are opt-in (notify setting) and permission is requested on first use only

Development

Use Node.js 22. Install both pinned runtime fixtures to reproduce CI locally:

npm ci
npm ci --prefix tests/fixtures/dsh-0.1.7
npm ci --prefix tests/fixtures/dsh-0.2.0
npm run typecheck
npm run build
npm test
npm run test:runtime

npm test covers recovery, autonomous-loop limits and toggles, startup scanning, queue ordering, statistics, localization and settings UI lifecycle. npm run test:runtime uses published DSH 0.1.7-rc.2 and 0.2.0-rc.1 Settings, Loader and HTTP services. It also runs the actual 0.2 profile compatibility gate and checks client activation with Cordis 4.0.4 when one settings provider is absent. The runtime harness controls agent events; it does not send requests to a model provider.

After editing a linked checkout, run npm run build to write the updated lib/ files, then restart DSH and refresh the browser. Hosts with client HMR enabled can reload a rebuilt client bundle automatically.

CI typechecks, rebuilds, runs both test suites, verifies committed lib/ artifacts and runs dsh-plugin-check. The same checks gate releases. See screenshot capture notes when updating the UI documentation.

Activity

Links

• Repository: github.com/HsiangNianian/dsh-auto-continue
• LINUX DO: linux.do
• DeepSeek Harness: github.com/deepseek-ai/deepseek-harness
• dsh-plugin-check: github.com/omdsh-dev/dsh-plugin-check — health-check your own DSH plugin repos

License

MIT © Hsiang Nianian