Teknium ebb428aed5 test(anthropic): trim DeepSeek proxy replay tests to two invariants + local wire probe ...

Fold the adapter-level unsigned-preservation case and the name-detector matrices
into one parametrized invariant (thinking family keeps unsigned only; non-thinking
DeepSeek and unrelated models still take the generic third-party strip) plus the
native-endpoint immutability guard. Add evals/anthropic_proxy_thinking_replay.py,
a real-AIAgent probe against a synthetic local Anthropic-compatible relay used for
the before/after wire check.

2026-09-06 05:37:03 -07:00

..

browser_use

refactor(browser_exec): schema diet 803->663 tok/call, A/B-gated; eval harness runs on Windows + Nous auth (#96300)

2026-08-27 04:39:19 -07:00

codebase_navigability

docs+evals: AGENTS.md for the facade/siblings layout; codebase-navigability benchmark harness

2026-09-03 23:55:56 -07:00

compaction

fix(compression): lean compaction makes exactly one auxiliary request per attempt

2026-08-30 09:03:57 -07:00

core_tool_deferral

lint: explicit encoding on harness file opens (ruff unspecified-encoding)

2026-08-29 19:04:29 -07:00

gateway_status_render

refactor(gateway): iteration-progress formatter lives in agent/session_activity, tests trimmed to the invariant bar

2026-09-06 05:35:12 -07:00

readtool

feat(tools): unicode-equivalent filename retry + near-miss suggestions in read_file

2026-08-09 23:35:07 -07:00

session_search_schema

eval: session_search schema A/B harness + PR #95570 reference results

2026-08-26 08:24:21 -07:00

webhook_auth

fix(webhook): only webhook-signature commits a delivery to the Standard Webhooks path

2026-09-06 05:35:48 -07:00

__init__.py

docs+evals: AGENTS.md for the facade/siblings layout; codebase-navigability benchmark harness

2026-09-03 23:55:56 -07:00

anthropic_proxy_thinking_replay.py

test(anthropic): trim DeepSeek proxy replay tests to two invariants + local wire probe

2026-09-06 05:37:03 -07:00

cli_deferred_notice.py

fix(banner): deferred update notice keeps prompt_toolkit routing; drop dead console arg; PTY harness

2026-09-06 05:36:26 -07:00

fanout_resource_bench.py

bench: explicit utf-8 encoding on text-mode opens (ruff PLW1514)

2026-09-03 02:31:59 -07:00

slack_stream_wire_contract.py

test(evals): wire-contract A/B harness for Slack chat.*Stream payloads

2026-09-06 05:34:36 -07:00