diff --git a/CHANGELOG.md b/CHANGELOG.md index 62840aeca..8d812c1ff 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -27,6 +27,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 `` XML tags, giving downstream consumers (LLMs, loggers, attribution parsers) a machine-readable provenance boundary and preventing misattribution in multi-agent threads. +- **cli:** the startup banner no longer advertises + `HEADROOM_COMPRESSION_STABLE_AFTER_TURN` and + `HEADROOM_STALE_READ_COMPRESS_AFTER_TURNS` as tuning knobs. Both were read + only to render the `Performance Tuning` banner section and were never wired + into the compression path, so setting them changed the banner but had no + effect on behavior. The banner now surfaces only the embedding sidecar, + which is a real, consumed setting. - **memory/embedder:** cap CPU thread oversubscription in the local torch/sentence-transformers embedder. Concurrent encodes previously each fanned out to ~`os.cpu_count()` BLAS/OpenMP threads, so under load the memory diff --git a/headroom/cli/proxy.py b/headroom/cli/proxy.py index 229693374..1d479d106 100644 --- a/headroom/cli/proxy.py +++ b/headroom/cli/proxy.py @@ -1327,31 +1327,16 @@ Memory (Multi-Provider): context_tool_line = f" Context Tool: {_selected_context_tool()}" # Performance tuning section — only shown when at least one tuning var is active. - _stable_turn = _get_env_int_optional("HEADROOM_COMPRESSION_STABLE_AFTER_TURN") or 0 - _stale_turns = _get_env_int_optional("HEADROOM_STALE_READ_COMPRESS_AFTER_TURNS") or 0 _embed_socket = os.environ.get("HEADROOM_EMBEDDING_SERVER_SOCKET") or ( embedding_server and (embedding_server_socket or f"/tmp/headroom-embed-{port}.sock") ) _tuning_lines: list[str] = [] - if _stable_turn: - _tuning_lines.append( - f" Prefix stability: conservative for first {_stable_turn} turns" - f" (HEADROOM_COMPRESSION_STABLE_AFTER_TURN={_stable_turn})" - ) - if _stale_turns: - _tuning_lines.append( - f" Stale read compression: reads older than {_stale_turns} turns eligible" - f" (HEADROOM_STALE_READ_COMPRESS_AFTER_TURNS={_stale_turns})" - ) if _embed_socket: _tuning_lines.append(f" Embedding sidecar: {_embed_socket}") if _tuning_lines: tuning_section = "\nPerformance Tuning:\n" + "\n".join(_tuning_lines) else: - tuning_section = ( - "\nPerformance Tuning: (all defaults — set HEADROOM_COMPRESSION_STABLE_AFTER_TURN" - " / HEADROOM_STALE_READ_COMPRESS_AFTER_TURNS to tune)" - ) + tuning_section = "" click.echo(f""" ╔═══════════════════════════════════════════════════════════════════════╗