Merge pull request #2450 from Molecule-AI/feat/observability-config-schema

feat(config): observability block schema (#119 PR-1 of 4)

workspace/config.py

@@ -166,6 +166,43 @@ class SecurityScanConfig:
     operators who require a CVE gate know the gate is absent.  Closes #268."""
 
 
+@dataclass
+class ObservabilityConfig:
+    """Observability settings — heartbeat cadence and log verbosity.
+
+    Hermes-style block: groups platform-runtime knobs that operators
+    typically tune together (cadence, verbosity) into one declarative
+    section instead of scattering them across env vars and hard-coded
+    constants. Adopting this shape unblocks per-workspace tuning without
+    a code change and pre-positions the schema for tracing/event-log
+    settings that will land in follow-up PRs (#119 PR-2 / PR-3).
+
+    Today only ``heartbeat_interval_seconds`` and ``log_level`` have live
+    consumers; both fields are accepted but not yet wired to their final
+    sites in this PR (schema-only). Wiring lands in PR-3 of the series.
+
+    Example config.yaml snippet::
+
+        observability:
+          heartbeat_interval_seconds: 60
+          log_level: DEBUG
+    """
+
+    heartbeat_interval_seconds: int = 30
+    """Seconds between heartbeats sent to the platform. Default 30 matches
+    ``workspace/heartbeat.py``'s long-standing constant. Lower values
+    reduce platform-side detection latency for crashed workspaces; higher
+    values reduce platform write load. Bounds: clamped to [5, 300] at
+    parse time — outside that range the workspace either floods the
+    platform or looks dead before the next beat."""
+
+    log_level: str = "INFO"
+    """Python ``logging`` level for the workspace runtime. Accepts the
+    standard names (DEBUG, INFO, WARNING, ERROR, CRITICAL). Today the
+    runtime reads ``LOG_LEVEL`` env; PR-3 of the #119 stack switches to
+    this field with env still honored as an override for ops debugging."""
+
+
 @dataclass
 class ComplianceConfig:
     """OWASP Top 10 for Agentic Applications compliance settings.
@@ -264,6 +301,7 @@ class WorkspaceConfig:
     governance: GovernanceConfig = field(default_factory=GovernanceConfig)
     security_scan: SecurityScanConfig = field(default_factory=SecurityScanConfig)
     compliance: ComplianceConfig = field(default_factory=ComplianceConfig)
+    observability: ObservabilityConfig = field(default_factory=ObservabilityConfig)
     sub_workspaces: list[dict] = field(default_factory=list)
     effort: str = ""
     """Claude output effort level for the agentic loop: low | medium | high | xhigh | max.
@@ -289,6 +327,22 @@ def _derive_provider_from_model(model: str) -> str:
     return ""
 
 
+def _clamp_heartbeat(value: object) -> int:
+    """Coerce raw YAML/env input into the [5, 300]-second heartbeat band.
+
+    Outside that band the workspace either floods the platform with
+    sub-second beats or looks dead long before the next one — both
+    real failure modes seen on incidents, neither benign. Coerce here
+    so adapters and ``heartbeat.py`` can read the value without
+    re-validating.
+    """
+    try:
+        n = int(value)
+    except (TypeError, ValueError):
+        return 30
+    return max(5, min(300, n))
+
+
 def load_config(config_path: Optional[str] = None) -> WorkspaceConfig:
     """Load config from WORKSPACE_CONFIG_PATH or the given path."""
     if config_path is None:
@@ -336,6 +390,7 @@ def load_config(config_path: Optional[str] = None) -> WorkspaceConfig:
     _ss_raw = raw.get("security_scan", {})
     security_scan_raw = _ss_raw if isinstance(_ss_raw, dict) else {"mode": str(_ss_raw)}
     compliance_raw = raw.get("compliance", {})
+    observability_raw = raw.get("observability", {})
 
     # Resolve initial_prompt: inline string or file reference
     initial_prompt = raw.get("initial_prompt", "")
@@ -445,6 +500,12 @@ def load_config(config_path: Optional[str] = None) -> WorkspaceConfig:
             max_tool_calls_per_task=int(compliance_raw.get("max_tool_calls_per_task", 50)),
             max_task_duration_seconds=int(compliance_raw.get("max_task_duration_seconds", 300)),
         ),
+        observability=ObservabilityConfig(
+            heartbeat_interval_seconds=_clamp_heartbeat(
+                observability_raw.get("heartbeat_interval_seconds", 30)
+            ),
+            log_level=str(observability_raw.get("log_level", "INFO")).upper(),
+        ),
         sub_workspaces=raw.get("sub_workspaces", []),
         effort=str(raw.get("effort", "")),
         task_budget=int(raw.get("task_budget", 0)),

workspace/tests/test_config.py

@@ -9,6 +9,7 @@ from config import (
     A2AConfig,
     ComplianceConfig,
     DelegationConfig,
+    ObservabilityConfig,
     SandboxConfig,
     WorkspaceConfig,
     load_config,
@@ -523,3 +524,119 @@ def test_compliance_default_via_load_config(tmp_path, yaml_payload, expected_mod
     # prompt_injection was never overridden in any payload — must stay at
     # the dataclass default regardless of the mode value.
     assert cfg.compliance.prompt_injection == "detect"
+
+
+# ===== Observability block (#119 PR-1) =====
+#
+# Hermes-style declarative block grouping cadence + verbosity knobs into one
+# place. Schema-only in this PR — wiring into heartbeat.py / main.py lands in
+# PR-3. These tests pin the schema so the wiring PR can rely on the parsed
+# values matching the documented contract (defaults, clamping bounds,
+# log-level normalization).
+
+
+def test_observability_dataclass_default():
+    """ObservabilityConfig() — no args — yields the documented defaults."""
+    cfg = ObservabilityConfig()
+    assert cfg.heartbeat_interval_seconds == 30
+    assert cfg.log_level == "INFO"
+
+
+def test_observability_default_when_yaml_omits_block(tmp_path):
+    """No ``observability:`` key in YAML → dataclass defaults."""
+    config_yaml = tmp_path / "config.yaml"
+    config_yaml.write_text(yaml.dump({}))
+
+    cfg = load_config(str(tmp_path))
+    assert cfg.observability.heartbeat_interval_seconds == 30
+    assert cfg.observability.log_level == "INFO"
+
+
+def test_observability_explicit_yaml_override(tmp_path):
+    """Explicit YAML values flow through load_config to ObservabilityConfig."""
+    config_yaml = tmp_path / "config.yaml"
+    config_yaml.write_text(
+        yaml.dump(
+            {
+                "observability": {
+                    "heartbeat_interval_seconds": 60,
+                    "log_level": "DEBUG",
+                }
+            }
+        )
+    )
+
+    cfg = load_config(str(tmp_path))
+    assert cfg.observability.heartbeat_interval_seconds == 60
+    assert cfg.observability.log_level == "DEBUG"
+
+
+def test_observability_partial_override_keeps_other_defaults(tmp_path):
+    """Setting only heartbeat preserves the log_level default — and vice versa."""
+    config_yaml = tmp_path / "config.yaml"
+    config_yaml.write_text(
+        yaml.dump({"observability": {"heartbeat_interval_seconds": 45}})
+    )
+
+    cfg = load_config(str(tmp_path))
+    assert cfg.observability.heartbeat_interval_seconds == 45
+    assert cfg.observability.log_level == "INFO"
+
+
+@pytest.mark.parametrize(
+    "raw, expected",
+    [
+        # In-band values pass through unchanged.
+        (5, 5),
+        (30, 30),
+        (300, 300),
+        # Below floor → clamped up to 5s. Sub-5s heartbeats flooded the
+        # platform during incident IR-2026-03-11 (workspace stuck in a
+        # tight loop emitting beats faster than the platform could ack).
+        (1, 5),
+        (0, 5),
+        (-7, 5),
+        # Above ceiling → clamped down to 300s. >5min beats let crashed
+        # workspaces look healthy long enough to mask the failure.
+        (301, 300),
+        (3600, 300),
+        # Non-integer YAML values fall back to the documented default
+        # rather than crashing the workspace at boot.
+        ("not-a-number", 30),
+        (None, 30),
+    ],
+    ids=[
+        "floor_in_band",
+        "default_in_band",
+        "ceiling_in_band",
+        "below_floor_one",
+        "below_floor_zero",
+        "below_floor_negative",
+        "above_ceiling_just",
+        "above_ceiling_far",
+        "garbage_string",
+        "null",
+    ],
+)
+def test_observability_heartbeat_clamp(tmp_path, raw, expected):
+    """heartbeat_interval_seconds is clamped to the [5, 300] band at parse."""
+    config_yaml = tmp_path / "config.yaml"
+    config_yaml.write_text(
+        yaml.dump({"observability": {"heartbeat_interval_seconds": raw}})
+    )
+
+    cfg = load_config(str(tmp_path))
+    assert cfg.observability.heartbeat_interval_seconds == expected
+
+
+def test_observability_log_level_uppercased(tmp_path):
+    """Lowercase or mixed-case log levels normalize to the canonical form
+    Python's ``logging`` module expects, so operators can write either
+    ``debug`` or ``DEBUG`` in YAML without surprise."""
+    config_yaml = tmp_path / "config.yaml"
+    config_yaml.write_text(
+        yaml.dump({"observability": {"log_level": "debug"}})
+    )
+
+    cfg = load_config(str(tmp_path))
+    assert cfg.observability.log_level == "DEBUG"