dsh-plugin-session-cost-pill

dsh plugin --profile web add dsh-plugin-session-cost-pill

💸 Session Cost Pill — DeepSeek Harness

Live session spend, right in the composer dock.


DeepSeek tells you how many tokens you burned. It does not tell you what that cost.

This plugin does — live, per session, without a single line of patched harness source.

---

What you get

The composer dock already tracks turns, speed, tokens, and context. The cost pill joins that row:

Pill · Shows

⏱ activity · turns · steps · decode speed

💾 usage · total tokens · cache-hit rate

💸 cost · estimated spend for this session

🪫 context · context-window pressure

The glyph climbs with the session total, so the row reads at a glance before the number does:

💸 · 💵 · 💰 · 🔥 · 🚨

under $1 · under $5 · under $20 · under $100 · $100 and up

Click it and the breakdown opens: uncached input, cache reads, and output, each priced separately, plus how much

of the total was charged at peak rates and how many steps that covered. It closes on Escape, on a click outside, or on

a second click — the browser's own popover behaviour, so the plugin ships no dialog state, listeners, or positioning

code of its own.

<p align="center">

<img src="https://raw.githubusercontent.com/vegerot/deepseek-harness-session-cost-pill/main/docs/pill-cost.png" alt="The cost pill" width="330">

<img src="https://raw.githubusercontent.com/vegerot/deepseek-harness-session-cost-pill/main/docs/panel.png" alt="The cost breakdown panel open above the pill" width="420">

</p>

---

Install

dsh plugin --profile web     add ~/code/github.com/vegerot/deepseek-harness-session-cost-pill
dsh plugin --profile desktop add ~/code/github.com/vegerot/deepseek-harness-session-cost-pill

That is the whole install. No build, no bundler, no dependencies. Restart the profile and refresh.

---

Why the number is right

Most cost trackers multiply a session's tokens by one flat rate. That is wrong for DeepSeek twice over.

1. DeepSeek has peak pricing

Prices double during peak hours, so a single rate per model cannot price a session.

Model · Tier · Cache hit input · Cache miss input · Output

deepseek-flash · off-peak · 0.003 · 0.15 · 0.60

deepseek-flash · peak · 0.006 · 0.30 · 1.20

deepseek-v4-pro · off-peak · 0.022 · 0.66 · 1.98

deepseek-v4-pro · peak · 0.044 · 1.32 · 3.96

USD per 1M tokens, transcribed from Models & Pricing.

Peak is 01:00–04:00 and 06:00–10:00 UTC, Monday–Friday. Everything else — all weekend — is off-peak.

So this plugin prices every assistant step at the rate in effect for that step's own timestamp. A session that

crosses a peak boundary gets a correctly blended total instead of a guess.

2. Cache hits dominate, and they are ~50× cheaper

A cache hit costs a fraction of a cache miss. A tracker that folds all prompt tokens into one bucket will miss the mark

badly on a long agent session — exactly the kind that reads 96% cache-hit.

Verified against real billing

DeepSeek publishes no pricing API, but its Platform console reports authoritative cost. Checking this plugin's table

against one real account's October deepseek-flash usage:

tokens:  hit 140.56512M   miss 2.828971M   out 0.758458M
published all-off-peak total   = $1.301116
platform's own billed total    = $0.453778 + ¥6.0056894
                               = $1.301116 at FX 7.0877 CNY/USD

A 0.11% match. The table is right, and that month's usage was effectively all off-peak — assuming peak would have

doubled the estimate.

---

How it works

It is an ordinary Cordis client plugin. Nothing in the harness is

patched, forked, or monkey-patched.

ctx.slots.inject('conversation.composer.dock', () => ctx.slots.register({
  name: 'conversation.composer.dock',
  id: 'cost-pill',
  order: 2,            // joins the activity (0) and usage (1) pills
}, CostPill));

The pill reads the chat snapshot through the session standard kit and folds it:

• useChat → every settled assistant step, each carrying its own time and provider usage
• useProjection('modelSelection') → the session's model

total = Σ over steps  costOfUsage(step.usage, model, isPeak(step.time))

isPeak classifies one request from its UTC weekday and hour, so pricing is per-request rather than per-session.

---

Known limits

Honest ones, not footnotes:

• Chinese public holidays are off-peak in full, and this is not modelled. That needs a PRC holiday calendar, so

weekday windows falling inside a holiday week are priced as peak — slightly overstating those days.

• The model is priced at session level. Chat assistant nodes carry time and usage but not the

model, so a session that switched models mid-way prices every step at the most recently used model's rates.

• Account-level spend is not shown. DeepSeek's Platform console does expose real billed cost through private

endpoints that authenticate with x-dsh-auth-token (not Authorization: Bearer), and DSH already

holds that grant via getPlatformSession(). It is deferred here because the browser half of a Remote needs

generated zod code

…(truncated)