dsh-context-decay

dsh-context-decay

Model-driven, lossy context decay for DeepSeek Harness.

The model decides when and what to compress. Finished spans are replaced by self-written summaries; the current turn is always kept. There is no recovery: the summary is the only surviving record.

Install note: This is a manual-install plugin: it requires a DSH

checkout with the modelMessageDecoration seam and is not a drop-in

plugin-market bundle (see Requirements).

What it does

• Inline position anchors. Every model-addressable message with a visible

text block is prefixed with ⟦p⟧; tool-call-only assistant turns are unanchored by design. Compression ranges use those anchors directly: ⟦p⟧ summary ⟦p⟧. Anchors are presentation, never part of the content.

• Copied anchors removed. If the model starts a reply with one or more

anchors, the leading run is stripped at the request boundary and again before the reply is committed, so the transcript and later requests stay clean.

• Model-selected spans. The model calls compress with one or more

half-open ranges and writes each summary itself. No extra summarizer request. Split around content that must stay live; pass all consumed spans in one call so the prefix is not invalidated repeatedly.

• Lossy by design. Compressed content is gone. There is no decompress, no

original-text search, and no external table. The summary must be self-contained.

• Tool results are compressible. All results of one assistant tool-call

message must stay in the same span. A boundary inside that group is rejected; the plugin never silently widens a span.

• Current turn protection. The active turn and its tool results cannot be

compressed. If the turn starts with unanchored system/runtime messages, a to boundary at its first visible anchor keeps those messages and compresses only the history before the turn; "end" remains the end-of-compressible-history sentinel.

• Tiered re-compression. Compressing a live summary block again produces a

tier-2 summary; larger merges increase the tier. drop removes a block completely with no tombstone.

• Pressure without automation. The plugin reports context pressure and

injects a reminder on each growth step; the reminder level follows the current pressure band, and the critical band uses a shorter step. It never compresses automatically; the model decides.

• Live panel + audit. A sidebar panel shows pressure, blocks, positions,

request counts, and the reminder ledger. An optional JSONL audit records each request and compression.

Requirements

• DeepSeek Harness 0.2.1-rc.2 with the local host patch in

applied. Stock DSH does not expose the decoration seam; there is no runtime fallback. Installation alone is not enough: rebuild the host after patching.

• Node.js >= 22.19.
• A web profile. The client half needs the sidebar/session/locale UI packages

listed in package.json.

• The bundle patch disables official automatic compaction

(compaction-basic.auto: false), keeps the manual /compact command, and disables the in-place surface rewriters (tool-result-pruner, image-offload) when those rows exist. /compact remains an emergency host fallback; its checkpoint is not a context-decay block.

Install

Manual patched install:

# 1. Apply the host patch to a DSH checkout and rebuild the host.
git -C /path/to/deepseek-harness apply /path/to/dsh-context-decay/patches/dsh-model-message-decoration.patch
pnpm -C /path/to/deepseek-harness install
pnpm -C /path/to/deepseek-harness build

# 2. Install this plugin into a profile (checkout or tarball).
dsh plugin --profile web add /path/to/dsh-context-decay
# or: dsh plugin --profile web add ./dsh-context-decay-0.1.0.tgz

# 3. Restart the web server and open the profile.
dsh web --profile web

See docs/INSTALL.md for the full patched-checkout workflow, Windows commands, verification, updating, and rollback.

Tools

Tool · Purpose compress({spans:[{from,to,summary,topic?}]}) · Replace one or more half-open ranges with self-written summaries. from/to are visible anchor texts such as "⟦p12⟧" (bare "p12" and integer 12 also work); to may also be "end". Several non-overlapping spans per call are allowed. Tool-group edges are rejected. drop({from,to}) · Remove exactly one live summary block. Use the block's printed anchor pair; "end" is allowed for a tail block. No tombstone, no recovery.

A live summary block prints its pair inline as ⟦p⟧ summary ⟦p⟧; use that pair for drop. The sidebar panel shows pressure and the block ledger, so no extra status tool is needed.

Examples:

# one span
compress({spans:[{from:"⟦p4⟧", to:"⟦p9⟧", summary:"Read the three requirements files; constraints are ..."}]})

# two non-overlapping spans in one call
compress({spans:[
  {from:"⟦p4⟧", to:"⟦p9⟧", summary:"Read the requirements; constraints are ..."},
  {from:"⟦p9⟧", to:"end", summary:"Implemented the parser and tests; ..."}
]})

# drop one live summary block
drop({from:"⟦p4⟧", to:"⟦p9⟧"})

The anchor ids above are illustrative; use anchors visible in the current session.

Configuration

Key · Default · Meaning enabled · true · Enable the plugin. contextWindowTokens · route value · Override the total context window. reservedOutputTokens · route value · Override the reserved output budget. defaultContextWindowTokens · 128000 · Fallback when the route has no window. growthTokens · 20000 · Periodic reminder step below the critical band. criticalGrowthTokens · 10000 · Shorter periodic reminder step while at the highest warning level. warnRatios · [0.70, 0.81, 0.95] · Warning levels as fractions of the effective window; the reminder level follows the current band. reminderCooldownTurns · 1 · Minimum turns between normal reminders; warnings are not delayed. maxSpansPerCall · 8 · Maximum spans in one compress call. minSummaryChars · 20 · Minimum summary length. maxSummaryChars · 8000 · Maximum summary length. maxMissTokens · null · Optional one-time miss guard. maxPaybackRequests · null · Optional payback guard. audit · false · Write request/compression audit JSONL. debug · false · Verbose plugin logging.

The effective window is total window - reserved output. The model sees pressure as a fraction of the effective window. The panel labels that percentage as effective pressure, shows the total and reservation, and adds a total-window occupancy line for direct comparison with the built-in context meter. Pressure, reminder, and request facts are kept per session, so switching sessions updates the panel.

How it works

The host patch adds a modelMessageDecoration service. The plugin registers a decoration provider that prefixes the messages selected by the replay state; the agent loop, token meter, and request payload all apply the same decoration. Positions come from the replayed surface, not from message text. Compressions append compaction/start, compaction/summary, a replacement user message, and compaction/end; replay rebuilds blocks, tiers, and the free list.

See docs/ARCHITECTURE.md for the state model, invariants, and failure modes.

See docs/PROMPTS.zh-CN.md for a Chinese translation of the model-facing prompts, tool descriptions, reminders, and error copy.

Limitations and non-goals

• No recovery. There is no decompress, search, or spill archive. This is

deliberate; it is also the main trade-off.

• Requires a patched host. The decoration seam is not upstream. Without it

the plugin cannot safely present anchors or replay positions.

• No automatic compression. Reminders are advisory. A model may ignore them;

the budget stays protected by the request guard, not by silent compaction. The official automatic policy is off; manual /compact remains available.

• `/compact` is a manual fallback. It runs the official backend and writes an

official checkpoint, not a context-decay tier block. Use it only when a session is already too large for a normal request.

• Manual install, not a market bundle. A market index cannot express the

host-patch requirement, and engines.dsh cannot distinguish a patched host from a stock one. Distribute the checkout or tarball with the patch instructions until the seam is upstream.

• One compression backend per profile. Do not run another compaction backend

or an in-place surface rewriter alongside it.

• Replay depends on the current event format. Compression replay uses the

current surfaceOp and compaction event shape.

Development

npm install          # if building outside a DSH checkout
npm run build        # src/ -> lib/ (JS + declarations), client/ -> lib/client.js
npm run check        # typecheck only
npm test             # node:test suite against lib/

Local development can reuse a DSH checkout's TypeScript: set DSH_HARNESS_ROOT or place the checkout next to this package.

License

MIT. See LICENSE.