PerryLink/dsh-observe

📊 dsh-observe

• 1024 store channel: npm i -g dsh1024 once, then dsh1024 plugin --profile web add dsh-observe (counts toward the deepseek1024.com install ranking).

OpenTelemetry and Langfuse observability exporter for DeepSeek Harness.

*Turn session events into OTLP traces and Langfuse observations — sanitized, buffered, off by default.*

English · 简体中文 · Español · Português · हिन्दी

dsh plugin --profile <name> add dsh-observe

📖 Ecosystem knowledge base — measured data, not marketing: plugin development guide · plugin-selection data · maintenance criteria.

Install & uninstall

• git channel (latest main): dsh plugin --profile web add github:PerryLink/dsh-observe — the prepare script builds with production dependencies only.
• npm channel (published releases): dsh plugin --profile web add dsh-observe.
• tarball channel: pnpm pack in this repo, then dsh plugin --profile web add ./dsh-observe-.tgz.
• uninstall: dsh plugin --profile web remove dsh-observe (or remove the row from the profile patch).

If pnpm reports ERR_PNPM_IGNORED_BUILDS for this package (esbuild's harmless platform-binary validation), add allowBuilds: { esbuild: true } to your pnpm-workspace.yaml — the dsh CLI prints the exact snippet.

⭐ 如果它帮到了你

这个插件是 DSH 插件家族的一员（95 个，全部 Apache-2.0）。如果你在用，给个 star —— 它不会解锁任何功能，但会让下一个人在搜索里更容易找到它。

*English:* part of a 95 plugin family for DeepSeek Harness. If it is useful, a star helps the next person find it — nothing is gated behind it.

What is dsh-observe?

OpenTelemetry and Langfuse observability exporter for DeepSeek Harness.

Turn session events into OTLP traces and Langfuse observations — sanitized, buffered, off by default.

*Workflow overview: install → open panel → act. The examples below use the real command surface.*

Compatibility

Surface · Status Harness · DeepSeek Harness dsh-v0.2.1-alpha.1 (adapted 2026-10-04): session format V4 represents a tool result as a first-class role: 'tool' message carrying top-level toolCallId + content + optional isError — the V3 tool-result content block is gone from the host's ContentBlockMap, and this plugin reads only the V4 shape (a pre-upgrade V3 log still projects through a read-only compatibility path). Session format V3's other traits carry over: the assistant stream is embedded in assistant/message / assistant/attempt, and the system prompt is surface node 0 (system/message); the plugin consumes only the live event stream and never reads session log files. The peer range >=0.1.2-rc.1 =0.1.5-alpha.1 =0.1.6-0 =0.1.7-0 =24.0.0 Backends · OpenTelemetry OTLP/HTTP (traces + metrics, JSON encoding) and Langfuse (LLM observability) — either or both Model · Model-agnostic: it exports the session/event stream; no model calls are made

What you get

dsh-observe turns the harness's session/event stream into standard observability protocols:

• Spans — turn, step, tool-call (duration, status, retry derivation), and LLM generation spans, linked into per-turn traces with deterministic ids.
• Metrics — per-provider/model token counters, USD cost counters (configurable pricing table), and the optional context-pressure gauge from ctx.tokenMeter.
• Sanitized capture — prompt and completion bodies are redacted (structural key names + built-in secret patterns + your patterns) and truncated before anything is queued or sent.
• Reliability — async batching (size- and timer-triggered), a bounded durable offline buffer (storage-domain) with oldest-first eviction, and deterministic exponential-backoff retries; undeliverable batches survive restarts.
• Runtime kill switch — the optional Typert remote (observe/status, observe/setEnabled) lets a settings page stop and resume exporting without unmounting.
• Off by default — enabled: true plus at least one backend is an explicit opt-in; nothing is captured or exported otherwise.

session/event stream
   │ collector (turn/step/tool/llm spans, metrics)
   │ sanitize (keys, secrets, budgets)
   ├──▶ pipeline "otlp"  ── queue ── flush ──▶ OTLP /v1/traces + /v1/metrics
   │         └─ retry/backoff ─┐
   ├──▶ pipeline "langfuse" ── queue ── flush ──▶ Langfuse ingestion
   │         └─ retry/backoff ─┤
   └────────── durable spool (offline buffer, bounded) ◀┘

Quick start

dsh plugin --profile web add github:PerryLink/dsh-observe

# 1. install the bundle into your profile
dsh plugin --profile web add github:PerryLink/dsh-observe

# or from npm (published releases)
dsh plugin --profile web add dsh-observe

# 2. configure a backend in your profile patch (cordis.yml) and restart
dsh --profile web

Minimal OTLP configuration (the row ships commented out in cordis.patch.yml):

- insert:
    - id: dsh-observe
      name: dsh-observe
      config:
        enabled: true
        otlp:
          endpoint: http://localhost:4318

Then verify the row mounts:

dsh --profile web --dump-config | grep -A2 'id: dsh-observe'

Examples

No user-facing command is registered; this plugin runs as a background exporter, configured through its settings.

Configuration

All tunables are Schemastery Config fields (changeable from cordis.yml). An id-targeted override replaces the whole row — restate every key you need. cordis.patch.yml documents each key inline.

Key · Default · Meaning enabled · false · Master switch; true plus at least one backend is the explicit opt-in otlp · null · OTLP backend config, or null to disable it otlp.endpoint · *(required)* · OTLP base URL; /v1/traces and /v1/metrics are appended otlp.serviceName · deepseek-harness · service.name resource attribute otlp.serviceVersion · *(none)* · service.version resource attribute otlp.headers · {} · Extra headers merged into every export request otlp.timeoutMs · 10000 · Per-request timeout langfuse · null · Langfuse backend config, or null to disable it langfuse.baseUrl · https://cloud.langfuse.com · Langfuse base URL langfuse.publicKey · *(required)* · Project public key langfuse.secretKey · *(required)* · Project secret key langfuse.release · *(none)* · Release tag stamped onto traces langfuse.traceName · session {session} turn {turn} · Trace-name template; {session}/{turn} interpolate per trace langfuse.tags · [] · Static tags stamped onto every trace langfuse.timeoutMs · 10000 · Per-request timeout capture.turns · true · Turn lifecycle spans capture.steps · true · Step lifecycle spans capture.tools · true · Tool-call spans with sanitized arguments/results capture.llm · true · LLM generation spans llm.prompt · true · Capture the sanitized request prompt (false = sizes only) llm.completion · true · Capture the sanitized completion (false = sizes only) metadata.sessionId · true · Session id attribute metadata.cwd · false · Session working directory (a local path — off by default) metadata.agentPreset · true · Agent preset id attribute metadata.model · true · Provider/model attributes metrics.tokens · true · Per-provider/model token counters metrics.cost · true · USD cost counters (need pricing rules to match) metrics.contextTokens · true · Context-pressure gauge (needs ctx.tokenMeter) pricing · [] · Pricing table, first match wins: { provider?, model, inputPerToken, outputPerToken, cacheReadPerToken?, cacheWritePerToken? } sanitize.enabled · true · Redaction master switch (false disables redaction, never truncation) sanitize.redactKeys · [] · Extra key-name substrings (key/token/secret/password/authorization/credential/apiKey are always included) sanitize.redactPatterns · [] · Extra secret regular expressions sanitize.truncatePromptChars · 4000 · Prompt character budget sanitize.truncateCompletionChars · 4000 · Completion character budget sanitize.truncateToolInputChars · 2000 · Tool argument character budget sanitize.truncateToolOutputChars · 2000 · Tool result character budget sanitize.truncateAttributeChars · 512 · Span attribute string budget batch.maxRecords · 256 · Flush once the queue holds this many records batch.flushIntervalMs · 5000 · Timer flush interval batch.maxQueueRecords · 2000 · In-memory queue bound; excess spills to the buffer batch.maxBufferRecords · 10000 · Durable offline buffer bound; oldest records drop first batch.bufferRetryIntervalMs · 30000 · Offline buffer retry interval retry.maxAttempts · 5 · Attempts per batch, including the first try retry.baseDelayMs · 1000 · First backoff delay retry.factor · 2 · Backoff multiplier per consecutive failure retry.maxDelayMs · 60000 · Backoff ceiling remote.enabled · false · Mount the observe Typert remote (kill switch)

Tools & surfaces

This plugin registers no model tools — it is a background exporter. Its surfaces:

• Consumes session/event (span/metric collection), session/flush (best-effort export kick — the durability checkpoint never waits on a remote backend), and session/disposed.
• Optional remote service observe — observe/status returns the kill-switch state, configured backends, queue depths, and buffer occupancy; observe/setEnabled stops and resumes exporting at runtime.

Permissions & data

• Permissions: network:outbound to the endpoints you configure, session:read for the event stream, storage:write for the offline buffer; no native code, no filesystem access.
• Data: everything sent is derived from the session log and sanitized (redaction + truncation) before it is queued, buffered, or transmitted. The offline buffer stores only sanitized records, re-validated when read back.
• Credentials: Langfuse public/secret keys travel only to the configured Langfuse endpoint; OTLP headers only to the configured OTLP endpoint. The plugin stores no credentials itself — keep them in credential references or environment-injected values.

Security boundaries

• Off by default — nothing is captured or exported unless you opt in explicitly.
• Sanitize before send — structural key redaction, built-in secret patterns (API keys, GitHub tokens, AWS keys, bearer credentials, private keys), your patterns, and character budgets all apply before any record leaves memory.
• Durable boundary re-validation — records read back from storage are checked again before a sink can see them.
• Failure loud, failure contained — export failures warn, count, retry, and finally spool; a failing session handler is caught and logged so observability can never break the harness hot path.
• Model-visible ⟺ logged — prompt/completion exports project only the session surface (whose node 0 is the system prompt) and the logged header (call config and tools); the exporter invents no content.

Known limitations

• npm 0.1.7-rc.2 — the plugin is developed and tested against @deepseek-ai/dsh@0.1.7-rc.2 (devDeps and CI's primary ruler); the peer range >=0.1.2-rc.1 =0.1.5-alpha.1 =0.1.6-0 =0.1.7-0 <0.2.0 keeps every published line installable, and the second ruler (typecheck:ci) plus the compat workflow cover the older baselines.
• Audit events are not persisted — the exporter's own observe/* records are audit-only: on the current host line the session append gate admits surface events, so no observe/* event is written to the session log, and the plugin does not fake one with an unmarked append (that would make sessions unreadable). Treat /observe status output and the OTLP/Langfuse backends as the audit surface.
• Metrics bypass the retry/spool path — OTLP metrics are aggregated cumulatively, so a lost flush self-heals on the next one (by design, not a bug).
• No sampling — every enabled span family is exported; set capture.* switches and batch.maxBufferRecords for high-volume sessions.

Development

pnpm install        # node ^22.19 || >=24
pnpm run typecheck  # tsc: src + tests against the 0.1.7-rc.2 devDeps (no tsconfig paths)
pnpm run typecheck:ci  # tsc against the published line (no paths)
pnpm run check:ruler-live  # canary: must fail to compile, proving the ruler is live
pnpm test           # vitest: 126 tests, 18 suites (real Context/Session/storage seam)
pnpm run test:coverage  # coverage gate (90/80/90/90)
pnpm run build      # tsdown bundle + tsc declarations (lib/)
pnpm run verify:self-contained  # dependency specs resolve from the registry
pnpm run verify:artifacts       # built ESM face + bundle patch present
node scripts/check-readme-sync.mjs  # five-language README sync gate
pnpm pack           # the published tarball

Topics

dsh, dsh-plugin, deepseek-harness, deepseek, cordis, observability, opentelemetry, otlp, langfuse, tracing

Contributors

• @PerryLink — creator and maintainer: collector, pipelines, spool, OTLP/Langfuse sinks, sanitization, and the five-language docs.

PerryLink DSH Plugin Family

This project is part of the DeepSeek Harness plugin family from PerryLink. The roster stays collapsed below so every README keeps a short first screen; expand it to see every row and its status.

Expand all plugins

Plugin · Status dsh-aqua-input-check · dsh-archive-check · dsh-auto-review · dsh-autotier · dsh-bid-ca-precheck · dsh-bid-qual-check · dsh-cert-mcp · dsh-checkpoint-rewind · dsh-click · dsh-composer-history · dsh-contract-stance · dsh-customs-doc-check · dsh-data-quality · dsh-demurrage-ledger · dsh-doublecheck · dsh-drill-script-check · dsh-eia-guide-check · dsh-emergency-plan · dsh-essay-rubric-check · dsh-evidence-check · dsh-export-ctl-check · dsh-fast · dsh-fmea-table-check · dsh-forecast-penalty · dsh-fund-research · dsh-github · dsh-gongwen-flow-check · dsh-gongwen-word-check · dsh-guard-plan-qc · dsh-hazchem-check · dsh-hazplan-check · dsh-hidden-risk-map · dsh-hs-classify · dsh-icd-rule-check · dsh-industry-research · dsh-lawcite-adapter · dsh-laya · dsh-lc-doc-check · dsh-learning-gap-check · dsh-library · dsh-local-ai · dsh-lsp-actions · dsh-mask · dsh-mcp-panel · dsh-medrec-qc · dsh-memento · dsh-nsfc-form-check · dsh-nurse-record-check · dsh-observe · dsh-origin-rvc-check · dsh-ota-review-check · dsh-output-styles · dsh-paper-doc-adapter · dsh-permission-rules · dsh-permit-report-check · dsh-pipeline-check · dsh-pleading-draft · dsh-plugin-doctor · dsh-plugin-guide · dsh-plugin-kit · dsh-plugin-upgrade · dsh-policy-brief-draft · dsh-power-loss-split · dsh-power-ticket-check · dsh-ppap-check · dsh-protest-deadline · dsh-railway-window · dsh-repair-order-qc · dsh-research-report · dsh-review-reply-check · dsh-rulefile-check · dsh-safety-brief-check · dsh-score · dsh-session-sync · dsh-site-log-check · dsh-skill-pack-security · dsh-soe-decision-check · dsh-soilwater-check · dsh-sop-sync-check · dsh-spc-gbt-adapter · dsh-talk · dsh-tender-extract · dsh-tender-matrix · dsh-test-drive · dsh-ticktick · dsh-translate · dsh-warranty-calc · dsh-budget · 🧊 FROZEN — see the repo README dsh-claude-move · 🧊 FROZEN — see the repo README dsh-defend · 🧊 FROZEN — see the repo README dsh-draw · 🧊 FROZEN — see the repo README dsh-reach · 🧊 FROZEN — see the repo README dsh-background-agents · 🚫 RETIRED — see the repo README dsh-session-pin · 🚫 RETIRED — see the repo README dsh-team-rooms · 🚫 RETIRED — see the repo README

License

Apache License 2.0 © 2026 dsh-observe contributors