DSH HUB
HomePlugin StorePlugin PacksCommunityRankingsResourcesPublish Guide
Plugin source
Back to catalog

LISHUANGXI1412 /

LISHUANGXI1412/dsh-token-trim

Verified

Tool-result trimming for DeepSeek Harness: structural summaries, head/tail caps, repeat deltas and artifact spill before results enter the context, with a measured savings view.

★ 0 Stars0 Forks0 IssuesN/A Community rating0 Confirmed installs
View on GitHub
READMESource: main@3ee33abe

dsh-token-trim

Trim tool results before they enter the model context — structural summaries, head/tail caps, repeat deltas, and an artifact spill you can search back. Ships with a context index and a measured savings view inside the conversation.

Not a proxy, not a middleware you have to trust: every rewrite is reproducible, the original is always on disk, and the model can read it back with guard_query.

Install

dsh plugin add dsh-token-trim

Restart DSH. You get:

  • token-trim (host): rewrites tool results on tools/post-execute;
  • token-trim-index (host): a small system-prompt section listing recent artifacts and touched paths;
  • Savings view tab next to Chat / Trajectory / Stats, plus the guard_query tool.

What it does

rule applies to behaviour
structural summary JSON-shaped results from cordis_inspect_*, plugin_manager, grep, skill, list_agents, CUA window dumps keeps the shape (keys, counts, ids), replaces verbose bodies with pointers
head/tail cap long text from pwsh, job_output, … keeps the first 72% and last 28% of the cap, inserts an artifact pointer + line count
repeat delta any tool in deltaTools if the same tool+args runs again and the diff is < 60% of the full text, send only the diff
unchanged pointer same as above sends [unchanged · same as #N · artifact <id>]

Everything else is left alone: edit, write, todo, sub-agent messages, images, multi-block results, reasoning, and any result under minChars (default 2000).

Measured on the author's machine

19 days of real sessions, 279 rewrites, not a benchmark script:

metric value
characters rewritten 3,493,915 → 876,875 (−74.9%)
tokens not re-sent ≈ 800K
tools affected pwsh 163, cordis_inspect_query 58, plugin_manager 20, grep 9, read 14, …
bill estimate (compaction tuning × this layer) −41.4% (offline replay)
suspected rework deducted 16 reruns, −0.13%
net bill estimate −41.3%

Read those two numbers carefully:

  • −74.9% is the character cut only over the results this plugin actually rewrote. It is not the bill: small results, the system prompt, tool definitions and reasoning are outside the hook.
  • −41.4% is a bill-level model: earlier compaction (−31%) composed with this rule layer (−15% of the bill, measured by replaying 1,518 real tool results), minus rework. It is a replay estimate, not an invoice.
  • The Savings tab shows the same split: gross, suspected-rework deduction, net — so you can see when the plugin starts to hurt instead of help.
  • Measured replay (in the tab). Reads the real session logs and charges each rewrite once at the miss price and once per later request until the next compaction; the threshold side replays the measured per-step deltas under the current policy (0.4 / 0.12) and the shipped default (0.8 / 0.16). On the author's session this came out at −30.6% compaction + −5.3% trimming ≈ −35.8% net; the −41.3% figure is the older corpus-level model kept as a comparison. Rewrites from before session ids existed are counted but not priced, and the tab says so.

Safety model

  1. Fail open. Any exception, any unexpected shape, any non-text result → the original result passes through untouched. A bug cannot block a tool.
  2. Single text block only. Images, structured values and multi-block results are never rewritten.
  3. Originals are always written first, to ~/.dsh/token-trim/artifacts/<sha16>.txt, and the replacement carries that id.
  4. guard_query(id, pattern) searches inside the original (substring or /regex/, with context lines). An artifact can be fetched twice; after that the tool returns the full text capped at 12K chars — because a third fetch costs more context than it saves.
  5. Audit trail. Every transformation appends one line to ~/.dsh/token-trim/manifest.jsonl (tool, mode, chars in/out, artifact id, session id).
  6. State is per agent. Repeat-delta and unchanged detection are keyed by session + tool + args, so a sub-agent never receives "unchanged" for a result it never saw.

What we tried and rejected (kept, so you don't repeat it)

  • Truncating read results. Two real sessions, both truncated reads triggered a follow-up offset/limit read: saved 2.3K tokens, cost ~50K in extra steps. read is now off by default (caps.read: 0).
  • LLM summarization of logs. Gold-recall 77.2% against the required 93.8%. Summaries lose the one line you need. Logs are capped, never summarized.
  • Sending "unchanged" across agents — a real bug, fixed by the agent key above.
  • Model-based trimming (a local 4B). Projected 3–6 points of bill for a resident 4B service; shelved.

Configuration

Patch row token-trim in the DSH profile:

- id: token-trim
  name: dsh-token-trim
  config:
    enabled: true
    dryRun: false       # record what would happen, rewrite nothing
    minChars: 2000
    maxFetches: 2
    caps:
      pwsh: 4000
      cordis_inspect_query: 12000
      read: 0           # 0 disables a cap

dryRun: true is the honest way to try it: the Savings tab fills up, the context does not change.

Savings view

The Savings tab (next to Chat / Trajectory / Stats) shows, per window and per session:

  • net bill estimate with the rework deduction spelled out;
  • measured usage read from dsh-context-kit's session cache when that plugin is installed (hit ×1 / miss ×10 / output ×15);
  • this plugin's own char cut, per tool and per session;
  • the last transformations with artifact ids.

Companion package

dsh-token-trim owns the runtime savings: tool trimming, the context index, the view. dsh-context-kit separately owns compaction-threshold tuning (Settings → Context). Install both for the full effect; either works alone.

License

MIT

DSH HUB

A community index for DSH plugins. Not an official GitHub or DeepSeek AI product.

CommunityResourcesAPIAbout
—/ 5

No ratings yet

Verified DSH bundle

Commit 3ee33abe7092

Community comments

No comments yet. Be the first to write one.