dsh-llm-call-inspector

English | 中文

A local, session-scoped LLM request and response inspector for DeepSeek Harness Web. It adds an LLM Calls view beside Chat and Trajectory so developers can inspect each session-associated normalized llm/stream call without changing what the model receives or what the caller receives.

This is a community plugin, not an official DeepSeek Harness release. Version 0.1.x is verified against the 0.1.0-rc.8 API surface.

[!WARNING] Request and response bodies can contain prompts, source code, tool arguments, tool results, personal data, or secrets embedded in content. Installing this plugin opts the Host into body capture by default. Read Privacy and data handling before using it with sensitive sessions.

What it shows

• A newest-first list of calls for the active DSH session.
• Provider, model, purpose, status, start time, duration, chunk count, and body-capture state.
• Search plus status and purpose filters.
• A master/detail layout with separate request and response tabs, expandable JSON, and copy actions.
• Live polling, explicit refresh, session-local clear, error and empty states, keyboard focus, responsive layout, and English/Chinese labels.
• Calls made for assistant work, compaction, session-title generation, or another normalized purpose when the call carries a sessionId.

The captured normalized request allowlist is:

provider, model, reasoningEffort, messages, system, tools, temperature, maxTokens, stop, sessionId, and purpose.

The captured response is the ordered array of DSH StreamChunk values observed at llm/stream. The observer delegates exactly once, yields the original chunk objects in the original order, and preserves downstream throws. Whole-chunk capture also preserves JSON-compatible adapter replay metadata, including finish.replayState when an adapter emits it.

Scope boundary

This plugin inspects the DSH-normalized LLM boundary. It is not a provider wire proxy.

It does not capture:

• provider-native HTTP request or response bodies;
• HTTP headers, top-level API keys, abort signals, or undeclared adapter-private fields on the request object;
• raw SSE frames, transport retries hidden inside an adapter, or provider-side processing;
• sessionless llm/stream calls; or
• hidden reasoning that the provider does not return as a normalized chunk.

Top-level structural exclusion is not content redaction. A key pasted into a prompt or returned by a tool can still be captured. Response chunks are preserved whole, so adapter-private JSON inside finish.replayState can also be captured and must be treated as sensitive content.

Why a separate view instead of merging with Trajectory

DeepSeek Harness 0.1.0-rc.8 exposes conversation.view as the public additive UI seam. The built-in Trajectory uses that seam but does not expose a supported inner row or panel extension point.

Trajectory and this inspector also answer different questions:

• Trajectory explains the durable session story: user/assistant/tool events, steps, timing, usage, and outcomes.
• LLM Calls exposes each normalized invocation boundary: the exact captured request snapshot and ordered response chunks observed for that invocation.

The plugin therefore registers an adjacent view at order 20 instead of copying, patching, or depending on Trajectory internals. If Trajectory later publishes a stable cross-link or inner-extension seam, the two views can be connected without changing capture ownership.

Architecture

session-associated GenerateOptions
              |
              v
      llm/stream observer
              |
              v
 bounded per-session memory store
              |
              v
 Connection RPC /dsh-llm-call-inspector (loopback only)
              |
              v
 conversation.view / LLM Calls

One package contains both runtime faces:

• Host injects llm and connection, prepends a transparent llm/stream observer, owns bounded memory, and registers one loopback-only Connection RPC channel.
• Client injects connection, slots, and locale, then registers one conversation.view entry. It polls body-free summaries and fetches the full body only for the selected call.
• Bundle declares dsh.bundle.patch and a Web client export, so dsh plugin adds both faces through the supported profile mechanism.

The store never writes captured bodies to disk. Records disappear when you clear the current session in the UI, the configured per-session/session/global-body bounds evict them, the plugin reloads, or DSH restarts.

Install

Prerequisites:

• DeepSeek Harness 0.1.0-rc.8;
• Node.js 22.19 or newer supported by the package engine; and
• pnpm on PATH, as required by dsh plugin.

Install the GitHub repository into the Web profile:

dsh plugin --profile web add github:striveh/dsh-llm-call-inspector
dsh --profile web --dump-config
dsh web

Restart a running Web profile after adding, updating, or removing a bundle. The config dump should contain a # == dsh-llm-call-inspector layer.

For reproducible use, pin a reviewed commit:

dsh plugin --profile web add github:striveh/dsh-llm-call-inspector#<commit-sha>

The repository ships checked-in lib/ artifacts and deliberately has no prepare or install lifecycle script. A GitHub install therefore does not need pnpm allowBuilds permission.

Configuration

The bundle defaults are:

Field	Default	Meaning
captureBodies	true	Capture allowlisted request fields and ordered response chunks. false keeps call metadata but marks both bodies omitted.
maxCallsPerSession	100	Maximum retained calls in one session; oldest calls are evicted first.
maxSessions	32	Maximum retained session buckets; least-recently-used buckets are evicted.
maxRequestBytes	524288	UTF-8 JSON byte ceiling for one request snapshot.
maxResponseBytes	1048576	UTF-8 JSON byte ceiling for one response chunk array.
maxTotalBodyBytes	67108864	Global retained captured-JSON budget across all sessions; settled calls are evicted before running calls, then oldest creation order first.
pollIntervalMs	750	Interval advertised to the mounted browser view.

To override them, add a later row to $DSH_HOME/profiles/web/cordis.patch.yml. A DSH patch replaces the row's complete config, so this example restates every field:

- id: dsh-llm-call-inspector
  config:
    captureBodies: true
    maxCallsPerSession: 50
    maxSessions: 16
    maxRequestBytes: 262144
    maxResponseBytes: 524288
    maxTotalBodyBytes: 33554432
    pollIntervalMs: 1000

If a body exceeds its limit, the plugin drops the whole body and exposes an explicit size-limit omission with measured bytes. Non-JSON-compatible values and disabled capture also produce explicit omission states; metadata and chunk counts remain available.

Metadata-only mode

Set captureBodies: false when provider/model, status, timing, and chunk counts are sufficient:

- id: dsh-llm-call-inspector
  config:
    captureBodies: false
    maxCallsPerSession: 100
    maxSessions: 32
    maxRequestBytes: 524288
    maxResponseBytes: 1048576
    maxTotalBodyBytes: 67108864
    pollIntervalMs: 750

Changing this configuration reloads the plugin and discards its current in-memory records.

Disable or uninstall

To keep the dependency installed but disable the plugin, add this later profile patch and restart Web:

- id: dsh-llm-call-inspector
  disabled: true

To remove the dependency and its bundle layer:

dsh plugin --profile web remove dsh-llm-call-inspector

Restart the profile after removal. Uninstalling or disabling the plugin cannot recover already-evicted in-memory records; none are persisted by this plugin.

Existing options and when to use them

This landscape changes quickly; follow each linked project's current documentation before choosing one.

Option	Primary data and UI	Better fit when
Built-in Trajectory	Durable session events in the native UI	You need the agent/session narrative, tool flow, usage, and outcomes rather than call bodies.
dsh-devtools	Metadata-first runtime profiler in a Web view; intentionally omits prompts and tool bodies	You need performance and runtime diagnostics with a smaller content-privacy surface.
dsh-llm-inspector	Reasoning controls, traffic statistics, a think workflow, and optional audit files; no native request/detail Web UI documented	You explicitly want those behavior-changing or file-audit features.
dsh-plugin-langfuse	Session events exported as OpenTelemetry traces to Langfuse	You need centralized, cross-session observability and accept/configure external export.
dsh-llm-call-inspector	Local native master/detail UI over normalized call bodies; bounded process memory only	You need focused trace, debug, teaching, or research inspection on the local Web surface.

GitHub topics are discovery metadata, not a security review or official endorsement.

Development

pnpm install --frozen-lockfile
pnpm verify
pnpm pack --dry-run

pnpm verify runs host and client typechecks, automated tests, a clean build, and read-only package checks. The package verifier checks the public exports, committed build artifacts, Web loader identity, bundle patch, DSH client declaration, documentation install command, and absence of install-time lifecycle scripts.

To test a local checkout after building it:

dsh plugin --profile web add .
dsh --profile web --dump-config
dsh web

See CONTRIBUTING.md for change constraints and SECURITY.md for private vulnerability reporting.

Compatibility

DeepSeek Harness is in developer preview and does not promise plugin compatibility across prereleases. This release's source, peer dependencies, tests, and package verification use @deepseek-ai/dsh-* 0.1.0-rc.8. No other DSH version is claimed as verified until it passes the same gates.

License

MIT