context window exceeded loading six prior call summaries plus current transcript together

TL;DR

Replace the six full prior summaries with a short rolling brief of open items and decisions from those calls, load the current transcript in full, and only pull a prior summary in full when the current call references it directly. Start with the run input combining six prior summaries with the current transcript, and the run log showing where it overflowed, work on one affected call, record, or run first, and prove the fix there before running the full set. Most cases clear once the cause named in step 2 is corrected at its source rather than retried unchanged.

context window exceeded loading six prior call summaries plus current transcript together

Use this when

• You see this exact message or symptom: context window exceeded loading six prior call summaries plus current transcript together
• One run, record, call, or object is affected and you can name it
• A retry without changing anything reproduces the same result

Not for this skill when

• The system fails with a different message and none of the signals here appear
• Nothing has failed yet and you are doing first time setup or general planning
• Every service from this vendor is down for all users, which is a vendor outage to wait out first

Steps

1. Reproduce the failure once using the run input combining six prior summaries with the current transcript, and the run log showing where it overflowed, and record the time, the workspace or account, and the one item it names. Verify: you have one failing item identified, not a similar older failure
2. Inspect the combined size of the inputs against the run limit, and which prior content the summary actually needed. Verify: you can point to the specific value, field, segment, or state that does not match what this operation needs
3. Apply the fix at that source: replace the six full prior summaries with a short rolling brief of open items and decisions from those calls, load the current transcript in full, and only pull a prior summary in full when the current call references it directly. Verify: the corrected value or setting is visible in the system itself, not only in a local file or the agent notes
4. Re-run the original operation on the single affected item first. Verify: that one item completes with no trace of the failure described above, and the run completes and its summary still picks up the open item carried over from the earlier calls
5. Check the downstream result a user or the next job would see, comparing it against the source for the same item. Verify: the downstream result agrees with the source in content and in timing
6. Repeat for the full set, watch the first few items in the same log you started from, and write the root cause and the changed setting into the run notes. Verify: the full run finishes, the notes name the failure and the fix, and no earlier item regressed

Variant phrasings

context window exceeded loading six prior call summaries plus current transcript together

The subject-first phrasing of the same failure. The fix is the same, start at step 1 and confirm the item the log or record names.

Tool-first phrasing of this failure

The phrasing searchers use once they know which system raised it. It is the same underlying problem, not a separate bug.

Why does this keep happening after a retry

The repeat-occurrence phrasing. A retry without the step 2 and step 3 checks almost always reproduces it, because the cause sits in the input, setting, or record state, not in the attempt.

Compatibility: Agent summarization with prior call context, at current versions

Why it happens

Stacking several full summaries on top of a full transcript exhausts the working space before generation starts, even though only a fraction of the prior material is relevant.

Provenance

Resolved from the public thread: https://vectle.com/posts/psttjtyuKRGD6U8oZg5qVCsg

Resolved from the public thread: https://vectle.com/posts/psttjtyuKRGD6U8oZg5qVCsg

Thread query: context window exceeded loading six prior call summaries plus current transcript together

TL;DR: Replace the six full prior summaries with a short rolling brief of open items and decisions from those calls, load the current transcript in full, and only pull a prior summary in full when the current call references it directly. Start with the run input combining six prior summaries with the current transcript, and the run log showing where it overflowed, work on one affected call, record, or run first, and prove the fix there before running the full set. Most cases clear once the cause named in step 2 is corrected at its source rather than retried unchanged.