feat: priority-based context file selection + CLAUDE.md support (#2301)
Previously, all project context files (AGENTS.md, .cursorrules, .hermes.md) were loaded and concatenated into the system prompt. This bloated the prompt with potentially redundant or conflicting instructions. Now only ONE project context type is loaded, using priority order: 1. .hermes.md / HERMES.md (walk to git root) 2. AGENTS.md / agents.md (recursive directory walk) 3. CLAUDE.md / claude.md (cwd only, NEW) 4. .cursorrules / .cursor/rules/*.mdc (cwd only) SOUL.md from HERMES_HOME remains independent and always loads. Also adds CLAUDE.md as a recognized context file format, matching the convention popularized by Claude Code. Refactored the monolithic function into four focused helpers: _load_hermes_md, _load_agents_md, _load_claude_md, _load_cursorrules. Tests: replaced 1 coexistence test with 10 new tests covering priority ordering, CLAUDE.md loading, case sensitivity, injection blocking.
This commit is contained in:
Teknium
@@ -457,22 +457,31 @@ def load_soul_md() -> Optional[str]:
|
||||
return None
|
||||
|
||||
|
||||
def build_context_files_prompt(cwd: Optional[str] = None, skip_soul: bool = False) -> str:
|
||||
"""Discover and load context files for the system prompt.
|
||||
def _load_hermes_md(cwd_path: Path) -> str:
|
||||
""".hermes.md / HERMES.md — walk to git root."""
|
||||
hermes_md_path = _find_hermes_md(cwd_path)
|
||||
if not hermes_md_path:
|
||||
return ""
|
||||
try:
|
||||
content = hermes_md_path.read_text(encoding="utf-8").strip()
|
||||
if not content:
|
||||
return ""
|
||||
content = _strip_yaml_frontmatter(content)
|
||||
rel = hermes_md_path.name
|
||||
try:
|
||||
rel = str(hermes_md_path.relative_to(cwd_path))
|
||||
except ValueError:
|
||||
pass
|
||||
content = _scan_context_content(content, rel)
|
||||
result = f"## {rel}\n\n{content}"
|
||||
return _truncate_content(result, ".hermes.md")
|
||||
except Exception as e:
|
||||
logger.debug("Could not read %s: %s", hermes_md_path, e)
|
||||
return ""
|
||||
|
||||
Discovery: AGENTS.md (recursive), .cursorrules / .cursor/rules/*.mdc,
|
||||
and SOUL.md from HERMES_HOME only. Each capped at 20,000 chars.
|
||||
|
||||
When *skip_soul* is True, SOUL.md is not included here (it was already
|
||||
loaded via ``load_soul_md()`` for the identity slot).
|
||||
"""
|
||||
if cwd is None:
|
||||
cwd = os.getcwd()
|
||||
|
||||
cwd_path = Path(cwd).resolve()
|
||||
sections = []
|
||||
|
||||
# AGENTS.md (hierarchical, recursive)
|
||||
def _load_agents_md(cwd_path: Path) -> str:
|
||||
"""AGENTS.md — hierarchical, recursive directory walk."""
|
||||
top_level_agents = None
|
||||
for name in ["AGENTS.md", "agents.md"]:
|
||||
candidate = cwd_path / name
|
||||
@@ -480,31 +489,51 @@ def build_context_files_prompt(cwd: Optional[str] = None, skip_soul: bool = Fals
|
||||
top_level_agents = candidate
|
||||
break
|
||||
|
||||
if top_level_agents:
|
||||
agents_files = []
|
||||
for root, dirs, files in os.walk(cwd_path):
|
||||
dirs[:] = [d for d in dirs if not d.startswith('.') and d not in ('node_modules', '__pycache__', 'venv', '.venv')]
|
||||
for f in files:
|
||||
if f.lower() == "agents.md":
|
||||
agents_files.append(Path(root) / f)
|
||||
agents_files.sort(key=lambda p: len(p.parts))
|
||||
if not top_level_agents:
|
||||
return ""
|
||||
|
||||
total_agents_content = ""
|
||||
for agents_path in agents_files:
|
||||
agents_files = []
|
||||
for root, dirs, files in os.walk(cwd_path):
|
||||
dirs[:] = [d for d in dirs if not d.startswith('.') and d not in ('node_modules', '__pycache__', 'venv', '.venv')]
|
||||
for f in files:
|
||||
if f.lower() == "agents.md":
|
||||
agents_files.append(Path(root) / f)
|
||||
agents_files.sort(key=lambda p: len(p.parts))
|
||||
|
||||
total_content = ""
|
||||
for agents_path in agents_files:
|
||||
try:
|
||||
content = agents_path.read_text(encoding="utf-8").strip()
|
||||
if content:
|
||||
rel_path = agents_path.relative_to(cwd_path)
|
||||
content = _scan_context_content(content, str(rel_path))
|
||||
total_content += f"## {rel_path}\n\n{content}\n\n"
|
||||
except Exception as e:
|
||||
logger.debug("Could not read %s: %s", agents_path, e)
|
||||
|
||||
if not total_content:
|
||||
return ""
|
||||
return _truncate_content(total_content, "AGENTS.md")
|
||||
|
||||
|
||||
def _load_claude_md(cwd_path: Path) -> str:
|
||||
"""CLAUDE.md / claude.md — cwd only."""
|
||||
for name in ["CLAUDE.md", "claude.md"]:
|
||||
candidate = cwd_path / name
|
||||
if candidate.exists():
|
||||
try:
|
||||
content = agents_path.read_text(encoding="utf-8").strip()
|
||||
content = candidate.read_text(encoding="utf-8").strip()
|
||||
if content:
|
||||
rel_path = agents_path.relative_to(cwd_path)
|
||||
content = _scan_context_content(content, str(rel_path))
|
||||
total_agents_content += f"## {rel_path}\n\n{content}\n\n"
|
||||
content = _scan_context_content(content, name)
|
||||
result = f"## {name}\n\n{content}"
|
||||
return _truncate_content(result, "CLAUDE.md")
|
||||
except Exception as e:
|
||||
logger.debug("Could not read %s: %s", agents_path, e)
|
||||
logger.debug("Could not read %s: %s", candidate, e)
|
||||
return ""
|
||||
|
||||
if total_agents_content:
|
||||
total_agents_content = _truncate_content(total_agents_content, "AGENTS.md")
|
||||
sections.append(total_agents_content)
|
||||
|
||||
# .cursorrules
|
||||
def _load_cursorrules(cwd_path: Path) -> str:
|
||||
""".cursorrules + .cursor/rules/*.mdc — cwd only."""
|
||||
cursorrules_content = ""
|
||||
cursorrules_file = cwd_path / ".cursorrules"
|
||||
if cursorrules_file.exists():
|
||||
@@ -528,31 +557,41 @@ def build_context_files_prompt(cwd: Optional[str] = None, skip_soul: bool = Fals
|
||||
except Exception as e:
|
||||
logger.debug("Could not read %s: %s", mdc_file, e)
|
||||
|
||||
if cursorrules_content:
|
||||
cursorrules_content = _truncate_content(cursorrules_content, ".cursorrules")
|
||||
sections.append(cursorrules_content)
|
||||
if not cursorrules_content:
|
||||
return ""
|
||||
return _truncate_content(cursorrules_content, ".cursorrules")
|
||||
|
||||
# .hermes.md / HERMES.md — per-project agent config (walk to git root)
|
||||
hermes_md_content = ""
|
||||
hermes_md_path = _find_hermes_md(cwd_path)
|
||||
if hermes_md_path:
|
||||
try:
|
||||
content = hermes_md_path.read_text(encoding="utf-8").strip()
|
||||
if content:
|
||||
content = _strip_yaml_frontmatter(content)
|
||||
rel = hermes_md_path.name
|
||||
try:
|
||||
rel = str(hermes_md_path.relative_to(cwd_path))
|
||||
except ValueError:
|
||||
pass
|
||||
content = _scan_context_content(content, rel)
|
||||
hermes_md_content = f"## {rel}\n\n{content}"
|
||||
except Exception as e:
|
||||
logger.debug("Could not read %s: %s", hermes_md_path, e)
|
||||
|
||||
if hermes_md_content:
|
||||
hermes_md_content = _truncate_content(hermes_md_content, ".hermes.md")
|
||||
sections.append(hermes_md_content)
|
||||
def build_context_files_prompt(cwd: Optional[str] = None, skip_soul: bool = False) -> str:
|
||||
"""Discover and load context files for the system prompt.
|
||||
|
||||
Priority (first found wins — only ONE project context type is loaded):
|
||||
1. .hermes.md / HERMES.md (walk to git root)
|
||||
2. AGENTS.md / agents.md (recursive directory walk)
|
||||
3. CLAUDE.md / claude.md (cwd only)
|
||||
4. .cursorrules / .cursor/rules/*.mdc (cwd only)
|
||||
|
||||
SOUL.md from HERMES_HOME is independent and always included when present.
|
||||
Each context source is capped at 20,000 chars.
|
||||
|
||||
When *skip_soul* is True, SOUL.md is not included here (it was already
|
||||
loaded via ``load_soul_md()`` for the identity slot).
|
||||
"""
|
||||
if cwd is None:
|
||||
cwd = os.getcwd()
|
||||
|
||||
cwd_path = Path(cwd).resolve()
|
||||
sections = []
|
||||
|
||||
# Priority-based project context: first match wins
|
||||
project_context = (
|
||||
_load_hermes_md(cwd_path)
|
||||
or _load_agents_md(cwd_path)
|
||||
or _load_claude_md(cwd_path)
|
||||
or _load_cursorrules(cwd_path)
|
||||
)
|
||||
if project_context:
|
||||
sections.append(project_context)
|
||||
|
||||
# SOUL.md from HERMES_HOME only — skip when already loaded as identity
|
||||
if not skip_soul:
|
||||
|
||||
Reference in New Issue
Block a user