Introduction¶
In DSH long sessions, dialogue content and tool results continuously accumulate, increasing pressure on the context window. dsh-argp is a third-party context compression engine for DeepSeek Harness (dsh): instead of allowing the model to freely rewrite history, it asks the model to make extract, summary, or false decisions on “atoms,” which are then evaluated by a deterministic guard to decide if the proposal should be applied. Compressed and pruned content is retained in an append-only log, allowing for subsequent recall.
Below is an introduction to its core mechanism, installation method, typical configuration, and usage notes.
What is this¶
dsh-argp is maintained by yoza10635 under the MIT license.
It solves the problem of needing to control context size while avoiding the loss of original historical text when rewritten. dsh-argp works in three parts:
- Stage-1 Atoms compression: The model proposes compression candidates, and the guard evaluates whether to apply them.
- Stage-2 Citation graph pruning: When thresholds are exceeded, whole atoms are removed according to graph rules; this stage performs 0 LLM calls during compression.
append-onlylog: Holds the original text of compressed and pruned content, supporting two-level recall.
Core Mechanism¶
Stage-1 Atoms Compression¶
Stage-1 proposes compression for the atoms of the current turn.
The model can make three types of decisions on atoms:
extract
summary
false
The deterministic guard is responsible for judging whether these proposals can be applied. In other words, the LLM only proposes candidate results; whether they are actually replaced is decided by the guard.
Stage-2 Citation Graph Pruning¶
Stage-2 removes whole atoms in reverse topological order when thresholds are exceeded. This stage performs 0 LLM calls during compression.
CiteDeclarer declares cross-turn citation edges every round and makes them available to Stage-2 via the injectEdges channel.
Log and Recall¶
The append-only log holds the original text of compressed and pruned content.
RecallZoom provides two levels of recall:
recall_summary
recall_detail
There are also specific recalls for pruned atoms:
recall_pruned
list_pruned
Installation and Activation¶
First, add the plugin:
dsh plugin --profile <name> add dsh-argp
This step mounts dsh-argp to the specified profile.
Next, disable the stock summarizer in the profile’s cordis.patch.yml:
- id: compaction-basic
disabled: true
After the above steps, the profile layer only needs to perform configuration overrides.
Mounting is handled by the package’s bundle patch; do not repeat the insert loader entry in the profile layer, otherwise a duplicate loader entry id error may occur.
Typical Configuration¶
If you want to explicitly specify the model backend, you can configure the llm for compressor and declarer:
- id: dsh-argp
config:
compressor:
llm: { provider: deepseek-official, model: deepseek-v4-flash }
declarer:
llm: { provider: deepseek-official, model: deepseek-v4-flash }
When llm is not configured, OpenAI-compatible direct connection can be used based on endpoint/apiKey configuration or environment variables.
Verification Commands¶
The repository provides several types of runnable verification entry points.
Run per-atom soak:
npm run spike36
Run single-transaction zero LLM call verification:
npm run spike8a
Generate per-atom compression/pruning details:
node spike/atom-audit.mjs <产物目录>
Applicable Scenarios and Notes¶
Suitable for dsh plugin scenarios that need to control long-session context while preserving recallable original historical text.
Note the following points before use:
- The plugin runs with the current dsh process permissions; check the source code and license before installation.
- The benefits of Stage-1 depend on the model’s instruction following capability; the guard ensures safety, but compression benefits will vary with the model’s compliance rate.
- The compliance rate for multi-model division in the
litetier has not been tested. - The compression calls in Stage-1 per round are side-channel costs; they do not enter the context but are counted in total cost.
- B-6 window truncation blind spot: Live nodes not replaced by
dsh-argpmay have the oldest parts cut off by the request assembly layer when approachingcontextWindow, leaving no trace, sorecall_prunedmay not be retrieved. - Tombstone two-hop recall: After the placeholder text evolves over multiple rounds, the original sequence may be lost, and
recall_pruned(seq)needs correct numbering. - For DeepSeek series models, when system prompts conflict with user instructions, the
citesdeclaration may be 0; Stage-1 guard compression and Stage-2 deterministic pruning still work as usual.
References¶
GitHub repository:
https://github.com/yoza10635/dsh-argp
The community directory is an independent site with no official affiliation to DeepSeek / Huafan; the specific directory page URL for dsh-argp was not confirmed in this material, so no link is provided here.