docs: update documentation after stream command removal

[jackspirou]

Summary

• Remove outdated references to the stream command that was removed in PR refactor: consolidate to single memory-efficient scanner implementation #4
• Update documentation to reflect the consolidated memory-efficient implementation
• Regenerate shell completions

Changes

• CLAUDE.md: Removed reference to stream.go file
• cmd/tokenizer/README.md:
  • Removed explicit stream command examples
  • Updated section title from "Streaming Mode" to "Processing Large Files"
  • Clarified that memory-efficient streaming is automatic for piped input
• llama3/IMPLEMENTATION.md: Fixed NewScannerOptions references to use the new NewScanner API
• Shell completions: Regenerated to remove stream command references

Related

• Follows up on refactor: consolidate to single memory-efficient scanner implementation #4 which consolidated the tokenizer implementation

🤖 Generated with Claude Code

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.

❌ Your project status has failed because the head coverage (21.44%) is below the target coverage (80.00%). You can increase the head coverage or adjust the target coverage.

@@           Coverage Diff           @@
##           master       #5   +/-   ##
=======================================
  Coverage   21.44%   21.44%           
=======================================
  Files          26       26           
  Lines        2392     2392           
=======================================
  Hits          513      513           
  Misses       1862     1862           
  Partials       17       17           

Flag	Coverage Δ
unittests	21.44% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

---

Continue to review full report in Codecov by Sentry.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 501e035...445ebf7. Read the comment docs.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.