Unverified50% confidenceEventExact time
In a real case, fully reading from a 600-line configuration sample returned more than 36,000 characters, whereas first searching for the location and then reading the relevant region returned only 397 characters in total, while both target values were still present.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Pi Context View Plugin: Making Agent Context and Skills Visible at a Glance
bilibili五里墩茶社10/27/2026
Related Entities
Related Claims
UnverifiedBased on measurements from more than 7,500 real API counts, the median call for claude-in-chrome returning a screenshot is 1,855 tokens, while the median call returning only text is 373 tokens, with screenshot calls at about 5 times text calls.72% similarUnverifiedIn a pydantic-ai test, after 10 parallel tool calls (21 new blocks), the next request read 6,827 tokens from cache; after 11 calls (23 blocks), the read count was 0 and 7,534 tokens were written again.71% similarUnverifiedIn frozen replay test scenarios, to achieve complete recall, some cases require reading 290 to 426 out of 407 to 454 candidates.69% similarUnverifiedIn a held-out evaluation on 32 briefs, the new rules read 22 of the explicit budgets (25) correctly, versus 11 for the old regex; and 25 of the explicit deadlines (27) correctly, versus 8 for the old regex.66% similarUnverifiedIn actual testing of Claude Code 2.1.302, an index of 12,628 characters loaded all 154 lines; a 28,182-character ASCII file was truncated at line 136.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102528API
curl https://kongchang.com/api/v1/knowledge/claims/1102528MCP
get_claim(id=1102528)