# Complete browser and crawler reads

Status: implemented and verified; follows the complete HTTP source repair.

The operator's no-truncation requirement also covers browser and crawler page
reads. The final audit found independent prefix cuts in Playwright, the legacy
browser service and crawler formatting; preserving full HTTP responses alone
does not repair those paths.

1. Remove successful prefix cuts from browser content/DOM/element reads and
   evaluation serialization, including predecessor service serialization.
   Preserve valid complete JSON. Distinguish a selected element, evaluation
   result, controls snapshot and complete returned document view.
2. Issue a distinct immutable page-content capability with exact content hash,
   source URL, producer/action, invocation identity, capture and session
   provenance. A browser observation is not an HTTP fetch receipt or proof of
   a read-only action; JavaScript evaluation can mutate the page.
3. Remove crawler per-page/global text clipping and discarded link/metadata
   tails. Preserve code whitespace and all static sections. Keep requested
   page/depth scope explicit. Resource failures must not masquerade as a
   successful complete prefix or a successful multi-page crawl.
4. Route these complete returned views through the same capacity admission,
   full-request source workers, exact quote checks and contiguous checkpoint
   mechanism used by HTTP fetches. Preserve Stop, task ownership and original
   source scope through adapters and normalization.
5. Provide host-owned extraction resumption without replaying potentially
   mutating JavaScript. Ordinary browser/crawl reads may be repeated to obtain
   a new observation; an evaluation result must reopen its saved source.
6. Verify actual large producer results, serializer boundaries, late facts,
   copied/stale capabilities, complete-view normalization, bounded pending
   coverage and resumption. Rebuild and validate the installed package before
   committing and pushing the coherent repair.

Bounded UI/control summaries remain observations of their explicit scope;
they cannot establish a complete document read. This work does not widen
Telegram tool permissions or reuse active browser sessions in acceptance tests.

Depends on [complete-source extraction](WO-web-source-full-coverage-extraction-20261013.md)
and [inference contract/output budgets](WO-fallback-contract-cooldown-20261013.md).

## Verification

The [installed browser receipt](evidence/browser-complete-source-live-20261013.json)
records six successful real Playwright tool reads against isolated Chromium:
content, DOM, innerText, textContent, innerHTML and evaluate. The complete DOM
has 477,626 characters; evaluation retains valid JSON with all 350 rows and its
late Unicode field. No user browser, local inference, external source site,
runtime installation or Telegram transport was used. The exact installed
bundle SHA256 is recorded; this covers execution tools, not a GUI benchmark or
real Telegram delivery.

The isolated producer suites pass 98 tests. Shared runner/extraction/fallback/
budget suites pass 264 with one existing opt-in test skipped, including exact
contiguous resumption with no browser replay,
ownership/Stop rejection and honest unresolved facets. Telegram suites pass
115, including genuine source receipts, actual child-page destinations beyond
clipped event text, unsafe URL rejection and existing native settlement checks.
Crawler Python parser/BFS fixtures run the actual implementation with a fixture
transport; no live Crawlee service or full browser-driven Telegram conversation
is claimed. Bounded rapid UI snapshots now explicitly report omitted frames and
text and state that they are not complete page reads.

All workspace packages rebuild, the 583-file tarball audit has zero warnings,
and the compiler-free fresh npm install passes. The operator's publication
directory and active runtime are unchanged by these isolated acceptance runs.
