Skip to content
PidebugCLI & tooling

Investigate and respond to GitHub issue about Excel add-in context handling

Session from pi-for-excel-sessions on Hugging Face by thomasmustier · MIT · condensed by Coders Talk

13msession
2interventions
GOAL

Review a GitHub issue reporting a discrepancy in context-window behavior between OfficeAI and Pi for Excel, determine which parts were user error versus real bugs, and respond with a comment plus a follow-up issue.

  1. Prompt · +0
    Review this GitHub issue (#558) about context handling differences between OfficeAI and Pi for Excel — seems like RTFM but check what I'm missing
  2. Agent did · +0m
    Traced through the codebase (context-management-policy.md, compaction.md, selection.ts, auto-compaction.ts, read-range.ts, action-queue.ts) and pi-coding-agent docs to understand context window, selection auto-context, compaction triggers, and overflow handling
  3. Agent did · +3m
    Summarized findings: ~70% of the issue's questions are already answered in the docs (context scope, files workspace, serialization), but identified a genuine gap around overflow handling for small-context models
  4. Prompt · +4m
    Ok fine can you draft the comment please
  5. Intervention · +4m
    Asked for the draft without bolding or em-dashes
    Why: I wanted a plain-text comment I could actually post on GitHub without markdown flourishes.
  6. Break · 30m away, not counted
  7. Intervention · +5m
    Rewrote the draft themselves to be much more concise, pointing to docs directly and cutting the fluff, then had the agent continue from that tighter version
    Why: It's open source with docs — I wanted the reporter to actually read them, so I tightened it myself rather than let the agent pad it out.
  8. Prompt · +12m
    I posted. let's open the other issue and we can comment the link to the issue
  9. Agent did · +12m
    Checked labels, drafted and opened a new issue (#566) for the small-context-window overflow gap, relabeled #558 from bug to question, and posted a comment on #558 linking to #566
  10. Outcome · +13m
    Opened issue #566 tracking the overflow-handling gap, relabeled #558 to 'question', and posted a linking comment on #558
VERDICT

Next time I'd ask the agent up front to separate 'what's already documented' from 'what's an actual gap' so I get that split without a second pass. The correction that mattered was rewriting the comment draft myself — the agent's version was accurate but too padded with bold/em-dashes and explanation; once I tightened it and pointed straight at the docs, it was actually postable.

I tried this · 0

Discussion · 0

How Builds work