pine-of-glass
Observability extensions for the Pi coding agent
Package details
Install pine-of-glass from npm and Pi will load the resources declared by the package manifest.
$ pi install npm:pine-of-glass- Package
pine-of-glass- Version
0.10.2- Published
- Aug 22, 2026
- Downloads
- 4,006/mo · 1,300/wk
- Author
- tmustier
- License
- MIT
- Types
- extension
- Size
- 2.6 MB
- Dependencies
- 0 dependencies · 3 peers
Pi manifest JSON
{
"extensions": [
"./extensions/pi-contextimate",
"./extensions/pi-traceline",
"./extensions/pi-cachemire",
"./extensions/pi-meantime"
]
}Security note
Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.
README
pine-of-glass
Small observability and context management tools for Pi in the terminal.
contextimatebreaks down what is filling your context window: sysprompt, AGENTS.md, Skill frontmatter, Tool schemas, and session material. Toggle with ctrl+o on start and /reload.tracelinecollapses tool calls to one trace line each, so you can see the full arc of what Pi did (path taken, context read, bloated tool results). Toggle with ctrl+t (expands/collapses both thinking blocks and tools).cachemireshows you what's happening to your cache and warns you about eventsmeantime(work-in-progress, feature flagged) understand latency from inference speed (TTFT, TPS) and potentially diagnose other things slowing down your agent like orcehstration or CI
See each extension's own README.md for details and docs/ for deeper reference.
Installation
- From GitHub:
pi install git:github.com/tmustier/pine-of-glass - From npm (installs
contextimate,traceline, and experimentalcachemireandmeantime):pi install npm:pine-of-glass. Meantime stays inert until its config sets"enabled": true.
Screenshots
Traceline
ctrl+t now collapses each tool call and thinking summary to a single line, and you can expand everything back to see per-item details.

Contextimate
Each new session and /reload now lists what's in your context window before you type a word. Toggle level of detail with ctrl+o.
Summary mode:

Compact mode, one aligned line per skill and tool:

Expanded mode, with per-section sources and a schema field tree for every active tool (excerpt):

Cachemire
You see cache-related warnings inline and above the editor only when the cache needs attention. /cache gives you a full session review by turn.


Meantime
Feature-flagged off by default. Once its config sets "enabled": true, a tempo line above the editor decomposes the current wait (waiting / thinking / writing / tools), slow calls earn a notice with a named cause, and /pace shows the per-call tempo ledger:


call ttft think write tools total out tok/s
1 1.9s 42s 8.0s 31s 1m22s 2.1k 48
2 1.7s 3.0s 12s 4.2s 17s 0.8k 41
3 14s 6.1s 5.0s 22s 26s 0.7k 35 slow start (median 1.9s)
totals: 3 calls · waiting 18s · thinking 51s · writing 25s · tools 57s · harness 4.6s
timed 1h42m ██▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ active 10m (10%) · idle 1h32m
Plans
- The current goal is to provide an interface that makes tool and agent behaviour more legible for humans using pi in their terminal interactively.
- Once that's solid, we can help both humans and agents to more easily analyse previous sessions and traces, including when pi is running in RPC mode, remotely, or there is a large number of agent sessions we need to read to get insights from.
Note: A nice side benefit of 1. is that tools like traceline can help agents running interactive pi subagents in tmux to monitor them without risking context bloat from tool outputs.
Status: There are several things left to do in 1., including
- maturing
cachemire(implemented, live-tested, conformant with the family design language, and now shipped as experimental while the UX settles; see issue #6), - making
contextimatemore useful beyond upfront context (for example, are my MCP servers and skills efficient when loaded?) - and other refinements tracked in issues.