fix(native): retain actionable final replies and document links

Co-Authored-By: Paperclip <noreply@paperclip.ing>

doc/plans/2026-10-04-native-completion-answer-fix.md

@@ -0,0 +1,15 @@
+# Native completion final-answer correction
+
+The completion constraint reduction remains held until the corrected source has live evidence for final-answer quality. Keep the original candidate, historical source and all original grades immutable.
+
+The correction keeps the shortened completion procedure while explicitly requiring a blocker explanation, owner and unblock action in the final reply. The existing document guidance now requires a canonical clickable document link. `write_document` returns a company/task-scoped `documentHref` in its idempotent receipt, derived in the document transaction from the saved key and actual task identity. No completion tool schema/description, fixed prompt, skill, permission or budget policy changes. This receipt repair is an additional production path beyond the original three-file instruction reduction.
+
+The Product E2E observation advances to v3. Its additional checks read only the actual run-attributed persisted provider final. A blocker label and action do not substitute for an explicit missing-access explanation. Document links must identify the exact task and one revisioned document at the instance origin; wrong origin, task, document, query, credentials or absent evidence fail. Exact call-ID joins, acceptance/termination, ordering, side-effect and budget checks remain enforced.
+
+After saving the strict native snapshot, each completion cell clicks the rendered final-reply link in the browser. It must open the canonical saved document and show the original content marker. Retain the navigation receipt and screenshot independently; a valid-looking Markdown URL alone does not qualify navigation.
+
+Calibrate with correct paraphrases and plausible wrong answers, including the action-only omission. Replay the retained observations only as labeled additional diagnostics; never overwrite or regrade the original results. Provider-free measurement still captures eighteen scripted start/resume/continuation projections. No synthetic receipt qualifies live model behavior.
+
+The human's paid-run authorization and subsequent request to fix the omission support one bounded corrective confirmation: the six exact `native-instruction-consolidation` candidate cells, one attempt each, no automatic retries, native Codex `gpt-5.6-sol`, ACPX Claude `claude-sonnet-5`, and OpenCode `openrouter/deepseek/deepseek-v4-flash-0731`, original local deadlines, and 1,000-cent company/agent hard stops. This is a new source/definition measurement, not a reroll of a frozen failure. No new baseline provider run, broader campaign or merge is part of this correction. Stop and inspect a usable behavior failure.
+
+Report exact source, definition/grader hashes, six outcomes, retained visible replies and document targets, actual run count, cleanup and billing coverage. Passing a single trial does not prove general equivalence, cause, live resume behavior, coding quality, speed or cost trends.