fix(config): route remaining boolean keys through _config_bool — string 'false' no longer truthy

[Brian Krabach (bkrabach)]

The bug

Follow-up to microsoft/amplifier-module-provider-openai#74 (squash 8485663).
That PR's read-only cross-check of this repo (HEAD 9916a68) found this
module already has a correct boolean-parsing helper —
AnthropicProvider._config_bool() (__init__.py:577-584) — used by six
config keys, but five boolean-ish keys bypassed it and read config with no
coercion at all.

The app-cli wizard writes boolean ConfigField answers as the STRING
"true"/"false" (see the field_type="boolean" fields in get_info()).
A plain self.config.get(key, default) returns that string unchanged, and
every one of these keys is consumed in a truthiness context — any
non-empty string, including the literal string "false", is truthy in
Python. A user answering "false" in the wizard therefore got the feature
turned ON.

enable_prompt_caching is the live-reachable instance: it IS exposed
as a field_type="boolean" ConfigField with string default "true"
(__init__.py:975-982), so a wizard-driven "false" answer silently
enabled prompt caching — and, post-#104, also fed the
cache_stable_region_ttl_1h beta-header gate
(if self.enable_prompt_caching: at __init__.py:812), which then
misread too.

Audit table

Full re-audit of every self.config.get() call in the constructor, not
just the five keys named going in:

key	site (pre-fix)	was it broken?	fixed how
raw	:661	YES — no coercion at all	routed through _config_bool()
use_streaming	:748	YES — no coercion	routed through _config_bool()
filtered	:749-751	YES — no coercion	routed through _config_bool()
enable_prompt_caching	:752	YES — no coercion; wizard-exposed boolean ConfigField, LIVE-REACHABLE	routed through _config_bool()
enable_web_search	:753-755	YES — no coercion	routed through _config_bool()
retry_jitter	:676	already safe	uses _config_bool() (pre-existing)
fallback_on_overload	:691-693	already safe	uses _config_bool() (pre-existing)
enable_1m_context	:703-705	already safe	uses _config_bool() (pre-existing)
persist_fallback_state	:712-714	already safe	uses _config_bool() (pre-existing)
refusal_fallback_enabled	:720-722	already safe	uses _config_bool() (pre-existing)
cache_stable_region_ttl_1h	:773-775	already safe	uses _config_bool() (pre-existing)

No other uncoerced boolean-ish config key exists in the constructor —
every remaining self.config.get() call reads a numeric, string, or
choice value (max_tokens, temperature, timeout, model names,
thinking_type, speed, etc.), never a boolean.

The fix

Each of the five keys is now read as
self._config_bool(self.config.get(key, default)), mirroring the exact
call shape already used by the six safe keys. This module's
_config_bool() coerces (does not fail loud on garbage — anything
outside 1/true/yes/on resolves to False); no new helper was
introduced, matching the module's own existing convention exactly.

Tests

tests/test_config_bool_parsing.py — 21 tests:

• per affected key: string "false" → False, string "true" → True,
  real bool passthrough, absent → documented default
• one integration-flavored assertion for the live-reachable key:
  enable_prompt_caching="false" (string) → zero cache_control blocks
  in a built request

Fail-before/pass-after proof: stashed just the source fix (kept the
new test file) and ran the new tests against pre-fix main — 11
failed / 10 passed (the 10 passes are the real-bool-passthrough and
absent-default cases, which were never broken — real bools and defaults
were always the correct type). Restored the fix — all 21 pass.

Full suite: 695 passed — baseline was 674 passed (verified via a
clean run before touching anything, post-#103/#104), plus the 21 new
tests = 695 exactly. No regressions.

python_check on touched files:
amplifier_module_provider_anthropic/__init__.py carries 15 pre-existing
pyright errors + 18 pre-existing ruff-lint/stub warnings (SDK
Optional-attribute narrowing, an unsorted __all__/import block, blind-
exception lint nits, a TODO stub comment) — confirmed identical (15
errors / 18 warnings, same codes, line numbers shifted only by this
diff's own +6 net lines) before and after this change via git stash.
ruff format/ruff check show zero diff needed on this diff's own
lines. The new test file is ruff format/ruff check clean; its two
pyright import-resolution errors are the same isolated-file false
positive every existing test file in this repo also reports when checked
outside the project's pytest rootdir/venv (verified against the
unmodified tests/test_prompt_cache_breakpoints.py, which reports the
identical "AnthropicProvider" is unknown import symbol /
"tests._helpers" could not be resolved pair) — a tool-environment
artifact, not a real defect.

Precedent

microsoft/amplifier-module-provider-openai#74 (squash 8485663) fixed
the identical anti-pattern in the openai provider and did the read-only
cross-check that found this repo's gap. This PR closes that gap.

---

🤖 Generated with Amplifier

Co-Authored-By: Amplifier 240397093+microsoft-amplifier@users.noreply.github.com

[Brian Krabach (bkrabach)]

Self-authored fix, merging at user direction under the documented maintainer admin-merge pattern (see microsoft/amplifier-module-provider-openai#74 for precedent). All required checks are green: license/cla pass, and the full pytest matrix (ubuntu/macos/windows × py3.11/3.12) passes. Merging via gh pr merge --squash.