dsh-context-keeper

dsh plugin --profile web add dsh-context-keeper

dsh-context-keeper

Two things for a DeepSeek Harness agent:

• A host plugin that teaches it how to reason well — one persistent

system-prompt section, visible on every request.

• An offline analyzer that reads what it actually thought, from the session

files on disk.

It does not cut reasoning short. That was the original goal; measurement

killed it. See [Why this does not reduce thinking](#why-this-does-not-reduce-thinking).

---

What v0.4 adds: a context badge & reminder

A colour dot in every turn's footer (the conversation.chat.turnTail

seat — the same place and shape as dsh-cost-meter's usage chip). It reads the

official contextPressure projection and paints the band — **green (<50%) /

yellow (50–65%) / orange (65–80%) / red (≥80%)** — with the occupancy percent;

the action hint ("建议交接" / "该交接了") only appears from orange up. Hover shows

the full sentence.

A reminder panel under the input (conversation.composer.dock) that appears

at orange/red only. It states the band and offers an 开新会话 button: it

calls the client Remote session.create + session.prompt to make a fresh

session in the same workspace and seed it with "read the latest handoff package

under .context-keeper/handoff and continue". The new session is a full agent,

so it reads the package itself — the button does not inline the package (that

would spend tokens again).

Both are pure presentation plus one explicit user click. They never enter the

model input on their own and cost zero tokens until you press the button.

Honest limits (verified against this build's source):

- DSH's ReasoningRow header (above the thinking block) is hard-wired with no

extension seat, so the footer is the nearest always-visible open spot.

- After creating the new session the button cannot switch you to it — the

slot API has no navigation; open it from the sidebar. The panel says so.

- Command names must match ^[a-z][a-z0-9_-]*$ and third-party commands

render their name (no separate display label), so /handoff and

/context-watch cannot be shown as Handoff/Context-Watch in the menu.

Readability goes into the Chinese one-line description shown next to

each name instead.

The client half is plugin/client.js (declared under dsh.client in

package.json); the host half is unchanged. No config path needed.

---

What v0.3 adds: context budget & handoff

v0.2 taught the agent how to think. v0.3 handles *whether the window can hold

it*. Two human commands, both reading the session file DSH already writes and

calling a model zero times:

• /context-watch — occupancy, band (green/yellow/orange/red), headroom,

growth per turn, and the last compaction's reclaim.

• /handoff — write a portable handoff package plus a full faithful archive

to <workspace>/.context-keeper/handoff/, so a fresh session can continue

without re-deriving anything. It reuses DSH's own compaction/summary

checkpoint as the "early context" (free multi-level distillation) and quotes

the recent tail verbatim.

A short, static context-budget line is added to the system prompt. It holds

no numbers on purpose: a changing number in the system prompt would invalidate

the provider's prefix cache on every request, which costs more than it saves.

The design and the two references it distils are in

[docs/distill-design-v3.md](docs/distill-design-v3.md).

---

Install

As a DSH plugin

dsh plugin --profile <your-profile> add dsh-context-keeper

Then restart the profile. The plugin registers one prompt section named

context-keeper:how-to-reason at order 650, which places it with the other policy

sections — after the deployment persona, before the tool catalog.

To turn it off without uninstalling, either set enabled: false in the config

block, or add a patch row:

- id: context-keeper
  disabled: true

Config options:

Option · Default · Meaning

enabled · true · false registers nothing

text · built-in rule · Replace the rule text entirely

order · 650 · Section position in the assembled prompt

maxChars · 2000 · Truncate at a paragraph boundary

As a CLI

git clone https://github.com/Orliba/dsh-context-keeper
cd dsh-context-keeper
node bin/cli.mjs --help

No build step, no dependencies, Node >= 22 (uses built-in zlib.zstdDecompressSync).

---

The plugin: what it puts in the prompt

The rule is five lines, each naming an observable behaviour rather than a

virtue:

Decide before acting. Before the first tool call, settle what you are

doing, why, and how you will know it worked. Once you state a plan, execute

it; do not reopen the plan mid-execution.

Change a conclusion only with a reason. …

When reasoning stalls, gather evidence instead of thinking harder. …

Match depth to risk. Read-only exploration may be quick. Irreversible

actions deserve a second look. …

Say what you do not know. …

Full text and the reasoning behind each line: [plugin/rule.mjs](plugin/rule.mjs)

and [docs/rule-text.md](docs/rule-text.md).

Why a prompt section and not a stream interceptor

The first design watched the reasoning stream and reacted — lower the effort

tier when a trace looked wasteful, stop a turn that ran away. Three

measurements, on real sessions, removed the target:

Hypothesis · Measured · Result

Looping traces repeat sentences · 0.1% sentence repetition · dead

Nearby steps re-derive earlier steps · 0.3% of step pairs above Jaccard 0.35 · dead

Early commitment + long tail = waste · top candidates read by hand: both productive · dead

It also depended on two fragile places: llm/stream (no in-tree consumer) and

agent/turn-stopping (fires only after the turn already ended).

A prompt section is the opposite kind of intervention. It is declared once,

…(truncated)