dsh-anchored-standard

中文说明

Experimental DeepSeek Harness agent presets — one base mode plus two variants — that anchor a session's first model request on the Minimal condition (real Minimal tool schema, no auto-injected context), then promote to a small resident catalog once the session is durable, unlocking heavier Standard tools on demand.

This is a community project. It is not an official DeepSeek preset and is not affiliated with or endorsed by DeepSeek.

Welcome to submit feedback on the plugin in the form of Issues or PRs. For ideas for new plugins or useful findings, please submit them under the repository.

Modes at a glance

Every mode directory is self-contained and installs alone under whatever id you copy it to (see Install).

Terminology

• trajectory — the style of the model's first reasoning chain. The Minimal condition produces "We need…" first lines; the Standard condition produces "Let me…" ("standard-like") first lines.
• anchor — the first-request conditions that select the trajectory. Issue

  11 isolated three levers: the tool schema, the output budget, and the

  injected reminders.

• bootstrap phase — request #1 of a session: the bootstrap tool pair, no auto-injected context, optional output cap.
• promotion — the durable session event that ends the bootstrap phase. Base mode: first tool/call or assistant/message, whichever comes first. Variants: the anchor reply.
• durable — recorded in the session event log. Phase state is derived from durable events, so resume and reload preserve it.
• resident catalog — the promoted tool set: the bootstrap pair plus the discovery tools plus every tool the model explicitly unlocked.
• discovery tools — dev_tool_search, skill_search, skill_load: the on-demand unlock surface for heavier Standard tools.
• materialized copy — the committed copy of a shared/ plugin inside a mode directory, generated by npm run sync.

How it works

The base mode in one request lifecycle (the variants change only the first turn — see their sections):

user's first message
        │
        ▼
┌ request #1 ─ bootstrap phase ──────────────────────────────┐
│ tools    : bash + str_replace_editor (Minimal's real pair) │
│ context  : no AGENTS.md digest, no skill-catalog reminder  │
│ budget   : adapter default (`bootstrapMaxTokens` optional) │
└─────────────────────────────────────────────────────────────┘
        │ first durable tool/call OR assistant/message
        ▼ PROMOTION — derived from durable events, resume-safe
┌ request #2+ ─ resident phase ──────────────────────────────┐
│ tools    : bootstrap pair + discovery tools + unlocked     │
│ context  : standard injections restored                    │
│ budget   : adapter default (a cap is stripped on promote)  │
└─────────────────────────────────────────────────────────────┘

Three first-request levers decide the trajectory (issue #11):

1. Tool schema — the decisive variable at the adapter-default maxTokens (256000). The real Minimal pair anchored 5/5; every standard-family schema fell standard-like 11/11.
2. Output budget — a 1024 first-request cap also anchored the trajectory (26/32), independent of the tool descriptions. The base mode leaves this lever unset (bootstrapMaxTokens is opt-in).
3. Injected reminders — the AGENTS.md/CLAUDE.md digest and the available-skills reminder. With the skill catalog present the anchor did not reproduce at all (0/9); both are stripped during bootstrap.

Why

DeepSeek V4 Pro conditions strongly on the API-visible tool catalog. In the Project2 evaluation, Standard and PTC produced scores of 91 and 92, while the official Minimal preset produced 99 and 96. Permanently staying on Minimal, however, gives up the Standard preset's broader tool set.

Anchored Standard separates initial trajectory selection from later tool use:

1. Keep the Minimal complete system prompt.
2. Expose the Minimal preset's REAL tool schemas — persistent bash + str_replace_editor, byte-identical to the official Minimal composition — on the first model request (lever 1 above).
3. Strip the auto-injected context on that first request as well — the AGENTS.md/CLAUDE.md workspace digest and the available-skills reminder that true Minimal never mounts (suppressedContextSources in the tool-bootstrap row; lever 3). User-initiated skill gestures are not filtered, and both injections return unchanged from request #2 on.
4. After the session records its first durable promotion signal — a tool/call or the first assistant/message, whichever comes first — promote to the RESIDENT catalog: the bootstrap pair plus the discovery tools plus whatever the model has explicitly unlocked via dev_tool_search. Dumping the full Standard catalog at promotion pulled the trajectory back to standard-like behavior (the post-promotion regression), so heavier tools — web_search, subagent, workflow, … — stay one dev_tool_search call away. Request

   1 always sees the bootstrap catalog; request #2 always sees the resident

   catalog, so a text-only first reply can no longer trap the session in bootstrap. (promoteOn in the tool-bootstrap row selects the trigger: either default, tool-call, or assistant-message.)

5. Derive the phase from durable session events so resume and reload preserve it.

The bootstrap catalog is the same on every platform: the Minimal pair (bash/str_replace_editor). The preset's shell is the persistent PTY bash (the sandboxed Standard bash row is disabled — both register the bash name into the same layer, and the tools registry rejects duplicates; Windows never had the sandboxed bash anyway). pwsh remains available in the promoted catalog on Windows.

Results

Project2 V4.1b, DeepSeek V4 Pro, reasoningEffort=max, Windows native:

Both runs emitted exactly two tool-catalog snapshots: the two-tool Minimal bootstrap, followed by the 25-tool Standard catalog (these runs predate the post-promotion narrowing to the resident set — see How it works). The result is reproducible evidence for this task, not a claim of universal improvement across models or workloads.

Cross-version evidence (issue #11, Windows + official endpoint, first-request trajectory only): at the adapter-default maxTokens the Minimal tool schema anchored 5/5 (We need modify… first lines, we 1.4, let me 0.0), while pwsh/read, pwsh-only, and sandboxed bash/read all produced standard-like first lines 11/11 — the tool schema, not the output cap, is the decisive first-request variable at 256000.

Full methodology and aggregate evidence are in xiaobright/modeltest.

Configuration reference

All knobs are rows in each mode's agent.cordis.yml. Unknown keys fail at preset mount.

tool-bootstrap (in preset/agent.cordis.yml; the row must stay FIRST — waterfall registration order decides the first-request strip):

zero-tool-bootstrap (in zero-anchored-standard/ and whoami-standard/): suppressedContextSources and compactionTools have the same semantics (promotion is always the first assistant/message), plus includeSubagents — whether subagents also take the anchor phase (set true in whoami-standard, false in zero-anchored-standard).

anchor-turn (in both variants): text — the synthetic first user message (default "This round is a test. Tools are not open yet; all tools will open next round." in zero-anchored, "你是谁" in whoami); includeSubagents — whether subagents also take the anchor turn.

eternal-minimal (in eternal-minimal/; the row must stay FIRST):

cot-drip (in combo-anchored/):

toolchoice-adapter (in wire-think-standard/; the row must stay the first LOCAL row):

wire-think (in wire-think-standard/): same mode / suppressedContextSources / includeSubagents / steerText semantics as think-phase, plus provider (must match the toolchoice-adapter row's id) and defaultProvider (the route execute steps restore onto, default deepseek-official).

instruction-hint (all modes): promoteOn matching the mode's promotion semantics (either in the base mode, assistant-message in the variants) — the one-shot "instruction files exist, read them before acting" hint waits for promotion.

Repository layout

preset/                  Anchored Standard — the base mode
zero-anchored-standard/  variant: fixed zero-tool anchor turn
whoami-standard/         variant: "你是谁" anchor turn, subagents inherit
eternal-minimal/         variant: Minimal pair forever + dshx bash gateway
wire-think-standard/     variant: wire-level condition (tools + tool_choice=none)
combo-anchored/          combination package: think split + gate + drip rows
shared/                  single source of truth for plugins used by 2+ modes
scripts/sync-modes.mjs   materializes shared/ plugins into every mode dir
test/                    zero-dependency test suite (npm test)
verify/                  one-shot headless verification runner

Invariants, enforced by npm run check:

• Every mode directory is self-contained: installable by copying it alone; agent.cordis.yml rows may reference only ./local.mjs files, never ../.
• Plugins shared by several modes live once in shared/; the copies in mode directories are generated. Edit shared/, run npm run sync, commit both — never edit a materialized copy.
• The tool-bootstrap row stays the FIRST row of preset/agent.cordis.yml.

This repository deliberately ships no AGENTS.md/CLAUDE.md: the presets' whole mechanism is a clean request #1, stripping exactly those instruction-file digests from it (issue #6: 0/9 anchored with the injection present). Shipping one would only feed later rounds and contradict the mechanism being documented. Everything an assistant needs is in this README.

Compatibility

Developed and tested against:

• DeepSeek Harness 0.1.0-rc.5
• repository commit 47f9438
• Node.js 24 on Windows

On the 0.1.0-rc.5 source checkout, bootstrapMaxTokens reaches the actual first request (the first request/header records the cap, adapterDefaults stays empty), because llm.prepareCall only materializes a default maxTokens when the proposed config has none. One prebuilt profile package observed in issue #11 (CLI launcher reporting 0.1.0-rc.6) overwrote the proposed cap with adapterDefaults.maxTokens; there the cap is a no-op. The default composition therefore relies on the Minimal tool schema alone (which anchors at the adapter default with no cap) and leaves bootstrapMaxTokens as an opt-in for standard-schema bootstraps.

DeepSeek Harness is currently a developer preview and explicitly permits breaking changes. This preset is a full snapshot of the Standard composition, so review upstream changes before using it with a newer release.

Install

Clone this repository, then copy the entire preset directory into the user preset root under the id anchored-standard. Every mode directory in this repository is self-contained: the zero-anchored-standard/, whoami-standard/, eternal-minimal/, wire-think-standard/, and combo-anchored/ variants install the same way, alone or together, with no other directory required (see their sections below).

PowerShell:

$target = Join-Path $env:USERPROFILE '.dsh\.agent-presets\anchored-standard'
if (Test-Path -LiteralPath $target) { throw "Preset already exists: $target" }
New-Item -ItemType Directory -Force -Path (Split-Path -Parent $target) | Out-Null
Copy-Item -Recurse -LiteralPath '.\preset' -Destination $target

Linux/macOS:

dsh_home="${DSH_HOME:-$HOME/.dsh}"
mkdir -p "$dsh_home/.agent-presets"
test ! -e "$dsh_home/.agent-presets/anchored-standard"
cp -R preset "$dsh_home/.agent-presets/anchored-standard"

Fully restart DeepSeek Harness, create a blank session, and select Anchored Standard (experimental). Do not switch an active session from a different preset.

Verify

Export the session JSONL and inspect request/header events. Reproduction checklist (issue #11 asks for the first two explicitly, because both are the variables that decide the anchor):

• First-request config.maxTokens value: with bootstrapMaxTokens unset (the default), the first header records the adapter default (e.g. 256000 with adapterDefaults.maxTokens: true); with a cap configured it records the cap (e.g. 1024 with no maxTokens adapterDefault).
• First-request tool schema source: the first header's tools array must be exactly ["bash", "str_replace_editor"] — the official Minimal preset's real schemas, not Standard's pwsh/read.
• the first request's messages should contain no AGENTS.md/CLAUDE.md digest and no available-skills reminder — only the user message and the minimal persona system prompt;
• after the first tool call or the first assistant reply, the next changed header should contain the promoted resident catalog: the bootstrap pair plus dev_tool_search/skill_search/skill_load plus any tools the model already unlocked;
• subsequent requests should keep that resident set (it grows only through explicit dev_tool_search unlocks) and restore the standard context injections.

Run the local zero-dependency tests with:

npm test

Important behavior

• With the default promoteOn: either, the session promotes after its first durable tool/call OR its first assistant/message, whichever comes first — request #1 sees the bootstrap catalog and every later request sees the resident catalog. A text-only first reply therefore still promotes at request #2; set promoteOn: tool-call to restore the original behavior, where a first response that makes no tool call never promotes.
• A failed tool execution still promotes the session because the durable tool/call already exists.
• The first request's output budget is NOT capped by default: the Minimal tool schema anchors at the adapter-default maxTokens, so bootstrapMaxTokens is opt-in. When set, the first request is capped and the cap is explicitly stripped after promotion (the next request's seed proposal carries the previous header's maxTokens forward).
• The promoted catalog is the RESIDENT set — the bootstrap pair plus the discovery tools plus everything the model unlocked via dev_tool_search — not the full Standard dump. The Standard sandboxed bash row stays disabled in favor of the persistent shell (same tool name, same layer; see Why). When unlocked, the read/write/edit tools keep the sandboxed filesystem while str_replace_editor uses the preset's local fs.
• A missing bootstrap tool degrades to the full catalog with a one-time warning instead of failing requests, so a composition drift cannot brick a session; invalid promoteOn values fail at preset mount instead.
• Promotion decisions are memoized per session for the process lifetime; the durable event scan runs once per session per process.
• While a session is unpromoted, the pre-step filter strips messages whose source.kind is listed in suppressedContextSources (default: agent-instructions and skill-catalog, the two automatic injections Standard adds over Minimal). Set the list to [] to disable the context filter; add other source.kind values to suppress more. A filter failure degrades to keeping every message rather than eating context.
• The tool catalog changes at promotion and again whenever dev_tool_search unlocks a new tool; request-prefix cache continuity breaks at those points.
• The preset has the same trust level as shell access. Review its files before installation.
• The plugin performs no network requests and adds no telemetry.

Zero-Anchored Standard (experimental)

An extra test mode that does not change the Anchored Standard logic above. It uses the same Minimal-aligned system prompt, but instead of exposing two tools on the first request it injects one fixed zero-tool anchor turn:

1. When the user sends their first message, the anchor-turn plugin prepends a fixed user message — "This round is a test. Tools are not open yet; all tools will open next round." — ahead of it.
2. The first real model request carries ZERO tools, so the session's first reasoning chain follows the zero-injection "we" trajectory.
3. Once that anchor response is durable, the resident catalog is exposed and the real message proceeds with it.

Anchoring on the first message — not on session creation — keeps the blank-session preset switcher usable. Subagents always see the resident catalog.

Measured behavior (opencode-go, DeepSeek V4 Pro, reasoningEffort=max): the anchor request is stable "we"-style with zero let me; the following tool-bearing requests return to the "The user wants…/Let me" style. This mode is a comparison point for whether the zero-tool first turn is worth the extra model call — not a claim that tool rounds stay "we"-style.

Install as a separate preset id:

dsh_home="${DSH_HOME:-$HOME/.dsh}"
mkdir -p "$dsh_home/.agent-presets"
test ! -e "$dsh_home/.agent-presets/zero-anchored-standard"
cp -R zero-anchored-standard "$dsh_home/.agent-presets/zero-anchored-standard"

Restart DeepSeek Harness, create a blank session, select Zero-Anchored Standard (experimental), then send your first message.

Whoami Standard (experimental)

A usability-oriented variant of the zero-tool anchor idea: the first turn is a natural self-introduction prompt instead of a fixed test message, and the user's real first message is deferred to the next turn. Whatever the user types first, the session warms up exactly one round and everything is ready when the real message is processed:

1. When the user sends their first message, the anchor-turn plugin prepends a fixed user message — "你是谁" (who are you) — ahead of it in the next-turn inbox queue.
2. dsh claims exactly ONE next-turn message per turn, so the first model request sees only the anchor on an EMPTY tool surface and replies with a self-introduction; that reply is the promotion signal.
3. The real message is claimed by the NEXT turn, with the promoted resident catalog (shells, str_replace_editor, the discovery tools) already unlocked — heavier Standard tools are one dev_tool_search away.

The anchor text is configurable via the anchor-turn row's text option (default "你是谁"). Anchoring on the first message — not session creation — keeps the blank-session preset switcher usable.

Full-powered subagents

Whoami Standard ships with includeSubagents: true on both the zero-tool-bootstrap and anchor-turn rows, so subagents spawned from a session inherit the same anchor flow as top-level sessions:

1. A newly spawned subagent's first model request sees only the "你是谁" anchor on an empty tool catalog.
2. The subagent's self-introduction reply is the promotion signal.
3. The delegated prompt runs on the next turn with the promoted resident catalog (shells, str_replace_editor, and the discovery tools).

Set includeSubagents: false on both rows to restore the plain behavior, where subagents start with the resident catalog immediately. Each subagent costs one extra model call for its anchor turn — a delegation-heavy session pays it per subagent.

zero-anchored-standard keeps subagents plain by default; enabling the same flow there means setting includeSubagents: true on its zero-tool-bootstrap and anchor-turn rows (its anchor text stays the fixed test notice).

The trade-off of the mode itself is one extra model call per session: the anchor turn is always taken, even when the first message is urgent.

The directory is self-contained; install it alone or alongside any other mode.

Install as a separate preset id:

dsh_home="${DSH_HOME:-$HOME/.dsh}"
mkdir -p "$dsh_home/.agent-presets"
test ! -e "$dsh_home/.agent-presets/whoami-standard"
cp -R whoami-standard "$dsh_home/.agent-presets/whoami-standard"

Restart DeepSeek Harness, create a blank session, select Whoami Standard (experimental), then send your first message — the self-introduction round runs first, and your message is answered with the full tooling on the next turn.

Think-Execute Standard (experimental)

Eternal Minimal (experimental)

The "make the model believe it never left Minimal" mode: the model-visible catalog stays EXACTLY the Minimal pair (bash + str_replace_editor) for the WHOLE session — no anchor round, no promotion, no discovery tools, no catalog growth — while the full Standard toolset stays registered and executes FOR REAL behind the dshx bash gateway:

dshx list                           # list every gateway tool
dshx web_search '{"query": "..."}'  # execute the real web_search
dshx read_image '{"path": "..."}'   # execute the real read_image

1. Eternal pair: system-prompt/assemble keeps only the shells + str_replace_editor on every request (think steps, post-compaction, subagents — everything), and auto-injected context is stripped everywhere (there is no promotion boundary to key suppression on).
2. Gateway: a tools/pre-execute listener intercepts bash commands starting with dshx, dispatches them through ctx.tools.execute() (the full registry pipeline — policy, guards, execution, rendering), and returns the rendered output as the command result. The deny channel is the only sanctioned pre-dispatch way to substitute a result, so gateway payloads arrive flagged as errors — every payload states plainly that the tool executed and its output follows, so the model reads it as output. The real tool really ran: the user sees genuine effects (files, searches, subagents) exactly as if it had been called by name.
3. Guide: a short dshx capability guide is appended to the system prompt (guide: false for a byte-pure Minimal persona) so the model knows the gateway exists without a third visible tool.

The gateway refuses to dispatch the shells/str_replace_editor themselves ("invoke them directly"), which also makes recursion impossible. Unknown tools, malformed JSON, and tool failures all come back as readable payloads. Set gateway: false for a bare two-tool session with no interception.

Install as a separate preset id:

dsh_home="${DSH_HOME:-$HOME/.dsh}"
mkdir -p "$dsh_home/.agent-presets"
test ! -e "$dsh_home/.agent-presets/eternal-minimal"
cp -R eternal-minimal "$dsh_home/.agent-presets/eternal-minimal"

Restart DeepSeek Harness, create a blank session, select Eternal Minimal (experimental), then work as usual — the model composes shell commands, and dshx … lines run the heavier Standard tools for real.

Deliberation Gate (experimental)

Wire Think-Execute Standard (experimental)

Combo Anchored (experimental) — the combination package

The everything-is-a-plugin showcase: THREE orthogonal anchoring mechanisms composed as independent rows, each with its own knobs, each removable or retunable by editing one line of agent.cordis.yml. They attack the pre-tool deliberation collapse at different moments of a turn:

With mode: every-turn the think step opens every turn, the gate catches the paths that skip it (steering continuations, resumed sessions, straight-to-tools follow-ups), and the drip sustains deliberation across long tool loops. Defaults are deliberately gentle (minChars: 400, every: 4, one beat per turn); tune per workload. Swapping the think-phase row for wire-think + toolchoice-adapter upgrades the opening to the wire-level condition (see above) at the cost of the sibling route and its prefix-cache churn.

Explored and rejected for this package: pure Code Mode presentation (presentAs('code') collapses the catalog into one run_code tool) — a single-tool surface measurably underperforms the two-tool condition in the sibling project's evaluations; and text-only fake tools or ghost tool-call histories — both proved unreliable anchors in practice.

Official ecosystem guidance

DeepSeek currently asks community plugin authors to publish plugins in their own GitHub projects and add the dsh-plugin repository topic for discovery. The official repository does not currently accept external pull requests and does not mandate a community repository template. See the official CONTRIBUTING.md.

License

MIT. preset/agent.cordis.yml is derived from the DeepSeek Harness Standard preset; the original DeepSeek copyright and MIT notice are retained in NOTICE.