Competitive analysis

August 20, 2026 ยท View on GitHub

Research date: 2026-08-20

This review compares product boundaries and public APIs. No third-party source implementation is copied.

DeepSeek Harness ecosystem

ProjectPrimary jobOverlapGap relative to dsh-tool-squeeze
DSH spill policy (official)Store oversized plain text and show a head/tail previewPrevents huge inline resultsContent-agnostic; a critical error in the middle can be absent from the preview
DSH tool-result pruner (official)Prune old tool results during compactionReduces later context pressureActs after results have already entered context; not format-aware
billion-context-dshModel-driven active context pruning as a compaction backendContext reductionConversation/context lifecycle scope, not deterministic pre-context tool-result processing
dsh-contextInspect context composition, history, events, and token costObservabilityObserve/manage rather than transform one tool result before model consumption
dsh-session-auditAnalyze completed session actions, failures, and usageReports tool behaviorPost-session analytics, not inline result compression
dsh-usage-statsUsage trends, heatmaps, model breakdown, exportToken accountingMeasures usage after the fact
dsh-agent-budgetEnforce durable token/deadline budgetsControls total spendAdmission control rather than output transformation
dsh-traceExport turns, model steps, and tool calls to telemetryObservabilityRecords events rather than shrinking content

Public references:

Other agent ecosystems

Headroom

Headroom is a broad compression platform: library, proxy, MCP server, multiple content routers, retrieval, optional learned/ML methods, cache alignment, memory, and cross-agent context. It demonstrates demand for evidence-aware compression and reversible retrieval, but it is much broader than one native Harness hook. The dsh plugin differentiates through a tiny TypeScript-only, DSH-native, deterministic path with no proxy or Python service.

Reference: https://github.com/headroomlabs-ai/headroom (Apache-2.0).

token-saver

token-saver wraps command execution and supplies many command-specific parsers. It has strong CLI specialization and reproducible compression baselines. The MVP deliberately does not compete on parser count: it handles any Harness tool, including MCP and non-shell results, at the official result lifecycle seam.

Reference: https://github.com/ppgranger/token-saver (Apache-2.0).

MCP result compression and context pruning

MCP compression servers generally require an explicit tool call or a proxy layer and may add another service boundary. Session compaction systems operate on accumulated history. Both can be useful, but neither guarantees that the first giant result is transformed before its first model-context insertion.

Product boundary

dsh-tool-squeeze is not another conversation compactor. Its narrow promise is:

Deterministic, evidence-preserving compression of a completed tool result before that large presentation repeatedly consumes model context.

Its defensible value is the combination of:

  • native tools/post-execute integration;
  • preservation of canonical tool values;
  • official spill-store retention of the original presentation;
  • conservative log/JSON/HTML/text processors;
  • visible omission and token-estimate notices;
  • fail-open behavior and per-tool bypass;
  • no LLM, proxy, external service, or core patch.

The project should not claim universal losslessness. Content compression is necessarily lossy; safety comes from conservative activation, explicit notices, evidence rules, and a retrievable original.