Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

feat(web): show durable token usage and context occupancy in the stats line

Browse Source 
The chat stats line took its token totals from the loaded conversation nodes,
so paging changed them and compaction erased the billing behind replaced
content. It also had no way to show context occupancy: the numerator and
capacity never reached the browser.

Both now come from token-meter session projections read through the standard
useProjection seat. Window nodes keep supplying turn and step counts plus LLM
and tool wall times, which are correctly window-scoped facts about what is on
screen; accounting no longer comes from there.

`tokenUsage` supplies billing and cache hit. `contextPressure` supplies
occupancy, pairing the newest provider-reported prompt size with the newest
capacity recorded by `request/context`. Deployments without token-meter drop
the token groups; a route whose adapter advertises no capacity drops the
occupancy group rather than rendering a placeholder.

Occupancy is deliberately approximate: the numerator and capacity are
independent last-wins fields, not one atomic request observation, so switching
models pairs a fresh capacity with the prior route's pressure until the next
request reports usage. It is a user-facing reference figure that nothing in the
harness makes decisions from, and it matches how the TUI status line has always
computed occupancy. The Agent Note and token-meter README state this as a
decision, including why the atomic alternative was implemented and rejected, so
it is not re-litigated as a defect.

Snapshot delta is one added `Context N% of 128K` segment across eight web
goldens; the preceding commit absorbed master's pre-existing golden drift.
This commit is contained in:
Hypatia May
2026-07-30 14:48:19 +08:00
parent 901bd575e1
commit 8a8c1965d7
43 changed files with 535 additions and 159 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
packages/llm/token-meter/README.md
View File

@@ -21,11 +21,23 @@ The fold tracks full request-header snapshots, step boundaries, surface appends
Usage accounting sums disjoint input, cache-read, cache-write, and output buckets; reasoning is not added again. Every successful call records an assistant anchor, including content-less calls. An explicit empty provenance list means a known empty provider stream, while absent legacy provenance conservatively treats the durable assistant output as provider output.
## Session projection
## Session projections
When the composition provides `ctx.sessionProjections`, token-meter registers the `tokenUsage` unit through an optional child fiber. Its client-safe value is the complete durable log's `uncachedInputTokens`, `outputTokens`, `cacheReadTokens`, and `cacheWriteTokens`. Usage chunks are counted even when a request later fails; a final assistant-message usage for the same `(turn, step)` replaces that sample instead of double-counting it. Reasoning remains an output subdivision.
When the composition provides `ctx.sessionProjections`, token-meter registers two units through an optional child fiber.
The unit uses the standard projection baseline, live frame, higher-seq-wins store, and JSON checkpoint paths. Unloading token-meter removes the key. A headless or TUI composition without the projection seam keeps the measurement service's existing behavior.
`tokenUsage` carries the complete durable log's `uncachedInputTokens`, `outputTokens`, `cacheReadTokens`, and `cacheWriteTokens`. Usage chunks are counted even when a request later fails; a final assistant-message usage for the same `(turn, step)` replaces that sample instead of double-counting it. Reasoning remains an output subdivision. The single last-sample slot relies on a session-log ordering property: once a later step reports usage, a legal log never reports usage for an earlier step again.
`contextPressure` carries `pressureTokens` — the newest provider-reported prompt size, summing uncached input plus cache reads and writes — and the optional `contextWindow` from the newest `request/context` record. Output is excluded, so the numerator holds still while a turn streams and steps forward when the next request reports its usage.
Both units use the standard projection baseline, live frame, higher-seq-wins store, and JSON checkpoint paths. Unloading token-meter removes both keys. A headless or TUI composition without the projection seam keeps the measurement service's existing behavior.
### Context occupancy is an approximation, by design
`pressureTokens` and `contextWindow` are independent last-wins fields and are **not** one atomic observation of a single request. Switching models pairs the fresh capacity with the previous route's pressure until the next request reports usage, and `pressureTokens` describes the last request rather than the surface as it stands right now.
This is deliberate. An occupancy percentage is a user-facing reference figure, not a billing record or a gating input — nothing in the harness makes decisions from it, and compaction reads `measure()` instead. The TUI status line has always computed occupancy the same way, dividing a `measure()` total by a separately-resolved capacity for the selected model.
Making the pair atomic was tried and rejected: it required a transient non-replayable wire frame, which needed lifecycle fencing against cross-stream reordering and left occupancy blank after every reconnect. The [Agent Note](../../../.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md) records that comparison. Consumers that need an exact same-boundary figure should call `measure()` at their own request boundary rather than read this projection.
## Composition