## Description
Claude's tokenizer is not public, so `get_tokenizer("claude-*")`
returned `EstimatingTokenCounter(chars_per_token=3.5)` — a
**character-ratio estimate**. The estimator's chars-per-token flips with
the *detected content type* (JSON 3.2 / code 3.5 / English 4.0 / CJK
1.5), so:
- the **same bytes** count differently before vs after compression → a
fold could appear to *increase* tokens;
- it **disagrees with the pipeline's** estimator on the same content.
Calibration vs a real BPE (tiktoken `o200k_base`) on representative
content:
| content | char-est(3.5) / o200k |
|---|---|
| English | **1.28×** (overcount 28%) |
| code | **0.83×** (undercount 17%) |
| JSON | 0.97× |
| diff | 1.02× |
i.e. the estimate is off **−17% … +28%**, and the error is
content-dependent (non-uniform) — which is exactly what produces
impossible `tok_after > tok_before` deltas.
This prices Claude against **tiktoken `o200k_base`** — a real,
deterministic, **monotone** BPE. It's not Claude's exact vocab, but it's
within ~10–20% and, crucially, **consistent before/after**, which is
what compression ratios and context-pressure gating actually need.
Closes #
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
- [x] Performance improvement
- [ ] Breaking change
- [ ] Documentation update
- [ ] Code refactoring (no functional changes)
## Changes Made
- `TiktokenCounter.__init__` accepts an explicit `encoding` override (so
a model can be priced against a chosen encoding regardless of name-based
resolution).
- `_create_anthropic` now returns `TiktokenCounter(model,
encoding="o200k_base")`, **failing open to the character estimator** if
the tiktoken vocab can't be loaded (reuses the existing `load_encoding`
timeout/guard).
- Updated the `MODEL_PATTERNS` comment and `test_get_anthropic_model` to
the new contract; added
`test_claude_priced_with_real_bpe_not_char_estimate`.
**Blast radius is contained:** `content_router` keeps its own
module-level estimator for routing decisions, so only the **handler's
reported counts** change. `tiktoken` is already a dependency.
**Composes with #2542** (tokenizer-consistent before/after): that PR
makes both endpoints use *one* tokenizer; this PR makes that one
tokenizer a *real BPE*. Together they fully eliminate the
inflated/phantom lines. This PR is based on `main` and is independently
valid.
## Calibration note (please review)
The one behavioral consumer of the handler's count is the
background-compression gate (`original_tokens >=
_background_compression_min_tokens`). Because o200k differs from the old
estimate by ~±20% depending on content, that threshold now trips on
slightly different requests. It's *more* accurate, but the threshold was
tuned against the estimator — worth a re-check. No other gate consumes
the handler count (routing uses `content_router`'s estimator).
## Testing
- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check` + `ruff format --check`)
- [x] Type checking passes (`mypy`)
- [x] New tests added
- [x] Manual testing performed
### Test Output
```text
$ ruff check <changed files> && ruff format --check <changed files>
All checks passed!
4 files already formatted
$ mypy headroom/tokenizers/registry.py headroom/tokenizers/tiktoken_counter.py
Success: no issues found in 2 source files
$ pytest tests/test_tokenizer.py tests/test_tokenizers.py -q
55 passed, 14 skipped
```
## Real Behavior Proof
- **Unit:** `get_tokenizer("claude-opus-4-8")` →
`TiktokenCounter(encoding_name="o200k_base")`; `count_text(sample)` ==
`tiktoken.get_encoding("o200k_base").encode(sample)` exactly; a
`tool_result` shrunk 300→3 words drops 508→13 tokens (folds register).
- **Live proxy** (Anthropic path, `--proxy-extension lossless_guard`):
foldable request logs `tok_before=694 tok_after=231 tok_saved=463
transforms=turn_hook` — real o200k-scale numbers (vs the estimator's 607
for the same payload), clean fold, no inflation.
- **Not tested:** exact agreement with Anthropic's *own* count_tokens
API (o200k is a proxy; a follow-up could calibrate against it offline).
GPT paths unchanged (already tiktoken).
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [ ] Documentation — N/A (internal; docstrings updated)
- [x] My changes generate no new warnings
- [x] New and existing unit tests pass locally with my changes
- [x] I did **not** edit `CHANGELOG.md`
## Additional Notes
Follow-ups (not here): (1) extend the same real-BPE treatment to other
private-tokenizer providers (Gemini/Cohere/Moonshot), each with its own
calibration; (2) optional opt-in calibration against Anthropic's
`count_tokens` API to true-up the ~10–20% absolute offset.
`.gitattributes` declares `*.py text eol=lf` and `*.sh text eol=lf`, but
74 files (73 .py, 1 .sh) are stored in the index with CRLF line endings,
violating that contract. Every macOS/Linux clone reports these files as
"modified" on fresh checkout because git's diff engine sees the stored
bytes don't match the attribute contract, even though the working tree
and index match byte-for-byte.
Running `git add --renormalize .` rewrites each affected blob so the
stored form matches the attribute declaration. No semantic changes —
every affected file's diff is "N insertions, N deletions" with inserts
and deletes being the same lines modulo line endings.
Follow-up commit adds `.git-blame-ignore-revs` so `git blame` / GitHub
blame skip this mechanical commit.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
