refactor(proxy): parse HEADROOM_OUTPUT_HOLDOUT in one place

The same try/float(runtime_env.getenv('HEADROOM_OUTPUT_HOLDOUT', '0') or '0')/except ValueError -> 0.0 parse was written five times. The copies were in gateway_turn.shape_gateway_body, the Anthropic chat handler, the OpenAI chat handler, the OpenAI Responses shaper, and openai._output_shaping_holdout_fraction. Each new shaper path copied it again.

It now lives once, as output_shaper.output_holdout_fraction(), next to the other live shaper knobs that already read runtime_env. Every caller imports it alongside the shaper functions it already uses. The parse is unchanged, so behaviour is identical, including hot-reload through runtime_env.

Evidence: grep -rn HEADROOM_OUTPUT_HOLDOUT headroom | grep getenv now finds only output_shaper.py.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

Assisted-by: claude-code:claude-opus-5-5
Headline-Session: 6e77a807-8dd4-4a77-a2fa-ddce6dc2515e
Headline-AI-Share: 38% strict / 38% weighted
This commit is contained in:
Tejas Chopra
2026-10-09 17:14:51 -07:00
co-authored by Claude Opus 5.5
parent a9815bbb5f
commit a1098e6ce9
4 changed files with 22 additions and 36 deletions
+2 -6
View File
@@ -1178,7 +1178,6 @@ def shape_gateway_body(
and the block is re-appended deterministically. Never raises.
"""
try:
from headroom.proxy import runtime_env
from headroom.proxy.output_savings import (
assign_arm,
conversation_key_from_body,
@@ -1188,6 +1187,7 @@ def shape_gateway_body(
from headroom.proxy.output_shaper import (
OutputShaperSettings,
classify_turn,
output_holdout_fraction,
resolve_verbosity_level,
shape_openai_chat_request,
shape_request,
@@ -1201,11 +1201,7 @@ def shape_gateway_body(
)
if not settings.enabled:
return False
try:
holdout = float(runtime_env.getenv("HEADROOM_OUTPUT_HOLDOUT", "0") or "0")
except ValueError:
holdout = 0.0
arm = assign_arm(conversation_key_from_body(provider_body), holdout)
arm = assign_arm(conversation_key_from_body(provider_body), output_holdout_fraction())
messages = provider_body.get("messages")
turn_kind = classify_turn(messages if isinstance(messages, list) else []).value
stratum = stratum_key(
+2 -8
View File
@@ -3558,6 +3558,7 @@ class AnthropicHandlerMixin:
from headroom.proxy.output_shaper import (
OutputShaperSettings,
classify_turn,
output_holdout_fraction,
resolve_verbosity_level,
shape_request,
)
@@ -3571,15 +3572,8 @@ class AnthropicHandlerMixin:
# conversation is treatment or control. This keeps the A/B
# comparison clean AND keeps the prefix cache stable (we
# never flip a conversation's system-prompt tail mid-stream).
from headroom.proxy import runtime_env
_holdout = 0.0
try:
_holdout = float(runtime_env.getenv("HEADROOM_OUTPUT_HOLDOUT", "0") or "0")
except ValueError:
_holdout = 0.0
_conversation = conversation_key_from_body(body)
_arm = assign_arm(_conversation, _holdout)
_arm = assign_arm(_conversation, output_holdout_fraction())
# Stratum from request features observable now (mirrors the
# offline baseline so live and learned strata line up).
+6 -22
View File
@@ -840,7 +840,6 @@ def _shape_openai_responses_payload(
must not be able to break request forwarding.
"""
try:
from headroom.proxy import runtime_env
from headroom.proxy.output_savings import (
assign_arm,
conversation_key_from_responses_body,
@@ -851,6 +850,7 @@ def _shape_openai_responses_payload(
from headroom.proxy.output_shaper import (
OutputShaperSettings,
classify_responses_turn,
output_holdout_fraction,
resolve_verbosity_level,
shape_responses_request,
)
@@ -859,10 +859,7 @@ def _shape_openai_responses_payload(
if not settings.enabled:
return [], False
try:
holdout = float(runtime_env.getenv("HEADROOM_OUTPUT_HOLDOUT", "0") or "0")
except ValueError:
holdout = 0.0
holdout = output_holdout_fraction()
conversation = conversation_key_from_responses_body(payload)
arm = assign_arm(conversation, holdout)
@@ -1550,15 +1547,6 @@ def _openai_responses_from_sse(sse_text: str) -> dict[str, Any] | None:
return completed
def _output_shaping_holdout_fraction() -> float:
from headroom.proxy import runtime_env
try:
return float(runtime_env.getenv("HEADROOM_OUTPUT_HOLDOUT", "0") or "0")
except ValueError:
return 0.0
def _shape_openai_responses_for_output(
payload: dict[str, Any],
*,
@@ -1578,6 +1566,7 @@ def _shape_openai_responses_for_output(
OutputShaperSettings,
ShapeResult,
classify_openai_responses_input,
output_holdout_fraction,
resolve_verbosity_level,
shape_openai_responses_request,
)
@@ -1589,7 +1578,7 @@ def _shape_openai_responses_for_output(
assert result.labels is not None
key = conversation_key or conversation_key_from_body(payload)
arm = assign_arm(key, _output_shaping_holdout_fraction())
arm = assign_arm(key, output_holdout_fraction())
turn_kind = classify_openai_responses_input(payload.get("input")).value
stratum = stratum_key(
turn_kind=turn_kind,
@@ -4932,7 +4921,6 @@ class OpenAIHandlerMixin:
# Mutating `body` in place is sufficient here — the outbound request
# serializes `body` fresh, so no body-mutation tracker is needed.
if not _bypass:
from headroom.proxy import runtime_env
from headroom.proxy.output_savings import (
assign_arm,
conversation_key_from_body,
@@ -4943,6 +4931,7 @@ class OpenAIHandlerMixin:
from headroom.proxy.output_shaper import (
OutputShaperSettings,
classify_turn,
output_holdout_fraction,
resolve_verbosity_level,
shape_openai_chat_request,
)
@@ -4956,13 +4945,8 @@ class OpenAIHandlerMixin:
# or control, which keeps the A/B comparison clean and the
# provider prefix cache stable (the steering block never flips
# mid-conversation).
_holdout = 0.0
try:
_holdout = float(runtime_env.getenv("HEADROOM_OUTPUT_HOLDOUT", "0") or "0")
except ValueError:
_holdout = 0.0
_conversation = conversation_key_from_body(body)
_arm = assign_arm(_conversation, _holdout)
_arm = assign_arm(_conversation, output_holdout_fraction())
_turn_kind = classify_turn(body.get("messages", [])).value
_stratum = stratum_key(
turn_kind=_turn_kind,
+12
View File
@@ -135,6 +135,18 @@ class OutputShaperSettings:
)
def output_holdout_fraction() -> float:
"""Fraction of conversations held out of shaping (``HEADROOM_OUTPUT_HOLDOUT``).
Read live, like the other shaper knobs. Unset or unparseable means 0.0 (no
holdout); :func:`~headroom.proxy.output_savings.assign_arm` clamps the range.
"""
try:
return float(runtime_env.getenv("HEADROOM_OUTPUT_HOLDOUT", "0") or "0")
except ValueError:
return 0.0
def shaper_enabled_for(config: Any) -> bool | None:
"""Resolve the output-shaper gate for a proxy config.