fix(context): task-sized workers and compact tool/result references #493
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "fix/task-sized-context"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Scope
Implement the operator's KISS context-efficiency request for Main, Dispatcher workers and Subagents. No 5K total-context gate, no tokenization round trip, no summary-model dependency.
Verification (head
f54e520)Activation / limitations
Not deployed yet. The old isolated probe imposed an incorrect 90-second overall test deadline. It is replaced by a versioned opt-in probe with no overall deadline, request-local text/reasoning/tool/token activity, and explicit unknown queue/prefill before first progress. A corrected isolated real qwen3.8-flash-next probe PASSED in 138.466 seconds: two requests with reported input 1,585/2,517 tokens, exactly one fixture tool call, 43,304 raw tool characters and a 733-character summary. This verifies an isolated read-only model/tool turn, NOT production activation. Four activity regressions cover >90-second continuing progress, unknown queue/prefill, keepalives versus meaningful own deltas, and frozen completed timings. The versioned probe retains diagnostic artifacts instead of deleting referenced evidence at teardown. No live ledger edits, restarts or model routing changes. Explicit tool allowlists and existing guards/assessment thresholds are unchanged. This does not prove an arbitrary operator prompt/direct MCP schema meets a 5K base-context target, nor resolve every Minerva compaction/recovery problem.
Follow-up proof on
f54e520: versioned opt-in real qwen3.8-flash-next probe PASSED without an overall deadline in 234.492s. First request 91.089s / 1,648 input tokens; second 143.357s / 2,614 input tokens. Exactly one fixture tool call; final summary 664 characters. Own emitted-token/text events observed (4/76). Original 43,304-byte tool artifact remains readable and its SHA-256 verified. No live-agent activation claimed. Four activity regressions plus full suite: 2,613 pass, 1 existing optional skip, zero failures.