feat(cli): flag-gated per-CLI install verification for install --agent#189
Conversation
Add GRADATA_VERIFY_INSTALL env flag. When set (1/true/yes), _cmd_install_agent writes then reads a test rule via Brain.correct() + Brain.search() after each successful agent install. Failures surface explicit actionable errors. Flag OFF preserves current behavior. Tests (5 pass): - test_cli_install_agent_writes_config_under_fake_home - test_cli_install_agent_all_detects_existing_configs - test_cli_install_agent_verify_flag_off_preserves_current_behavior - test_cli_install_agent_verify_flag_on_shows_confirmation - test_cli_install_agent_verify_flag_skips_on_failed_install
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.
📝 Walkthrough• Install verification feature: Added WalkthroughThe CLI's agent install flow now optionally runs a post-install verification when GRADATA_VERIFY_INSTALL is enabled: it writes a temporary test correction via Brain, searches for a unique marker to confirm readback, and treats verification failures or exceptions as install failures. Tests and a dev dependency were added to exercise and support this behavior. ChangesInstall Verification Feature
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Suggested labels
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Warning There were issues while running some tools. Please review the errors and either fix the tool's configuration or disable the tool if it's a critical failure. 🔧 OpenGrep (1.20.0)OpenGrep fatal error (exit code 2): �[32m✔�[39m �[1mOpengrep OSS�[0m �[1m Loading rules from local config...�[0m Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@Gradata/src/gradata/cli.py`:
- Around line 320-323: The install verification is persisting synthetic
corrections by calling brain.correct(...) (lines ~320-333); change this to a
non-persistent verification flow or ensure explicit cleanup. Replace the
persistent call to brain.correct with a transient API (e.g., a
non-persistent/ephemeral verification method) if one exists, or if not, capture
the returned correction identifier and delete it immediately in a finally block
(use brain.delete_correction/delete_rule/forget or equivalent) so no synthetic
draft/final data remains in user memory after the install check. Ensure the fix
references the brain.correct invocation and the corresponding cleanup call so
re-running installs cannot accumulate fake rules/events.
- Around line 324-329: The current verify search uses a static key
"gradata-install-verify-{name}" which can match older artifacts; change the
write to include a unique marker (e.g., timestamp or UUID) and use that exact
marker for the readback so you prove the same record was written and read.
Concretely: when writing the test rule, append a unique_token (uuid4 or
time-based string) to the rule content/key (store it in a local variable like
unique_token), then replace the brain.search call with a lookup/search for
f"gradata-install-verify-{name}-{unique_token}" (or fetch by returned record id
if write returns one) and assert the returned result contains that unique_token;
update variables/results/had_failure handling accordingly.
In `@Gradata/tests/test_cli_install_agent.py`:
- Around line 10-17: The test helper builds base_env using os.environ.copy()
which leaks host feature flags (e.g., GRADATA_VERIFY_INSTALL) into tests; modify
the helper that sets base_env so it either starts from a minimal clean env (not
os.environ.copy()) or explicitly removes/unsets any GRADATA_* and related
feature flags (specifically ensure GRADATA_VERIFY_INSTALL is not present) before
returning; update the logic around the base_env variable creation/update (the
code that sets HOME, USERPROFILE, XDG_CONFIG_HOME, PYTHONPATH and then updates
with env) to guarantee deterministic “flag off” behavior.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 0a2c488f-78aa-488c-b01f-4d1e5bb847a2
📒 Files selected for processing (2)
Gradata/src/gradata/cli.pyGradata/tests/test_cli_install_agent.py
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (8)
- GitHub Check: pytest ubuntu-latest / py3.11
- GitHub Check: pytest macos-latest / py3.12
- GitHub Check: pytest windows-latest / py3.12
- GitHub Check: pytest windows-latest / py3.11
- GitHub Check: pytest ubuntu-latest / py3.12
- GitHub Check: pytest macos-latest / py3.11
- GitHub Check: pytest (py3.11)
- GitHub Check: pytest (py3.12)
🧰 Additional context used
📓 Path-based instructions (2)
Gradata/src/**/*.py
📄 CodeRabbit inference engine (Gradata/AGENTS.md)
Gradata/src/**/*.py: Prefersentence-transformersfor local embeddings,google-genaifor Gemini embeddings,cryptographyfor AES-GCM encrypted system.db,bm25sfor BM25 rule ranking, andmem0aifor external memory adapters — guard all optional dependency imports withtry / except ImportErrorat the call site, never at module level
Maintain strict layering: Layer 0 (Primitives: _types.py, _db.py, _events.py, _paths.py, _file_lock.py; Patterns: contrib/patterns/) must never import from Layer 1 (Enhancements: enhancements/, rules/) or Layer 2 (Public API: brain.py, cli.py, daemon.py, mcp_server.py)
Never use bareexcept: pass— use typed exceptions or at minimumlogger.warning(...)withexc_info=Trueto avoid silent failure in a memory product
Never import from out-of-scope sibling directories../Sprites/or../Hausgem/withingradata/*code — that is a layering bug
Never leak private-sibling paths into public docs/code — no references to../Sprites/,../Hausgem/, email addresses, OneDrive paths, or Sprites-specific examples from insidegradata/*
Use atomic-write helper when writing JSON files to prevent corruption from mid-write crashes
Files:
Gradata/src/gradata/cli.py
Gradata/tests/**/*.py
📄 CodeRabbit inference engine (Gradata/AGENTS.md)
Gradata/tests/**/*.py: SetBRAIN_DIRenvironment variable viatmp_pathin conftest.py for test isolation — ensure_paths.pymodule cache refreshes when callingBrain.init()directly inside tests
Add unit tests intests/test_*.pyfor every CI push without LLM calls (deterministic); mark integration tests with@pytest.mark.integrationand skip them by default (they hit real LLM APIs)
Files:
Gradata/tests/test_cli_install_agent.py
Boss review (GRA-214)Good feature direction. Per-CLI verification gates a real reliability gap. Three issues to fix before merge: 1. Synthetic correction persists in user memory (blocking)
2. Verify search should use the exact unique token for readbackThe search uses just 3. Test helper leaks host env vars (blocking)
VerdictFix items 1 and 3, tighten item 2, re-request review. This is close — the core logic is sound and the test coverage is good. |
There was a problem hiding this comment.
Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.
There was a problem hiding this comment.
Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.
There was a problem hiding this comment.
Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@Gradata/pyproject.toml`:
- Line 58: Remove the duplicate dependency entry "httpx>=0.27.0" from the dev
extras so it is only declared once under the llm optional group; locate the dev
extras block in the pyproject toml and delete the "httpx>=0.27.0" line (the llm
= ["httpx>=0.27.0"] entry should remain unchanged) to avoid redundant
declarations when installing --all-extras.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 571f8ea5-eb87-40bf-842a-16353bec49b4
⛔ Files ignored due to path filters (1)
Gradata/uv.lockis excluded by!**/*.lock
📒 Files selected for processing (3)
Gradata/pyproject.tomlGradata/src/gradata/cli.pyGradata/tests/test_cli_install_agent.py
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (8)
- GitHub Check: pytest ubuntu-latest / py3.12
- GitHub Check: pytest macos-latest / py3.11
- GitHub Check: pytest ubuntu-latest / py3.11
- GitHub Check: pytest windows-latest / py3.11
- GitHub Check: pytest macos-latest / py3.12
- GitHub Check: pytest windows-latest / py3.12
- GitHub Check: pytest (py3.11)
- GitHub Check: pytest (py3.12)
🧰 Additional context used
📓 Path-based instructions (3)
Gradata/tests/**/*.py
📄 CodeRabbit inference engine (Gradata/AGENTS.md)
Gradata/tests/**/*.py: SetBRAIN_DIRenvironment variable viatmp_pathin conftest.py for test isolation — ensure_paths.pymodule cache refreshes when callingBrain.init()directly inside tests
Add unit tests intests/test_*.pyfor every CI push without LLM calls (deterministic); mark integration tests with@pytest.mark.integrationand skip them by default (they hit real LLM APIs)
Files:
Gradata/tests/test_cli_install_agent.py
Gradata/**/pyproject.toml
📄 CodeRabbit inference engine (Gradata/AGENTS.md)
Maintain
dependencies = []in pyproject.toml — the base package is pure Python + stdlib with all heavy dependencies gated as optional extras: embeddings, gemini, encrypted, ranking, adapters-mem0
Files:
Gradata/pyproject.toml
Gradata/src/**/*.py
📄 CodeRabbit inference engine (Gradata/AGENTS.md)
Gradata/src/**/*.py: Prefersentence-transformersfor local embeddings,google-genaifor Gemini embeddings,cryptographyfor AES-GCM encrypted system.db,bm25sfor BM25 rule ranking, andmem0aifor external memory adapters — guard all optional dependency imports withtry / except ImportErrorat the call site, never at module level
Maintain strict layering: Layer 0 (Primitives: _types.py, _db.py, _events.py, _paths.py, _file_lock.py; Patterns: contrib/patterns/) must never import from Layer 1 (Enhancements: enhancements/, rules/) or Layer 2 (Public API: brain.py, cli.py, daemon.py, mcp_server.py)
Never use bareexcept: pass— use typed exceptions or at minimumlogger.warning(...)withexc_info=Trueto avoid silent failure in a memory product
Never import from out-of-scope sibling directories../Sprites/or../Hausgem/withingradata/*code — that is a layering bug
Never leak private-sibling paths into public docs/code — no references to../Sprites/,../Hausgem/, email addresses, OneDrive paths, or Sprites-specific examples from insidegradata/*
Use atomic-write helper when writing JSON files to prevent corruption from mid-write crashes
Files:
Gradata/src/gradata/cli.py
🔇 Additional comments (2)
Gradata/src/gradata/cli.py (1)
294-297: LGTM!Also applies to: 313-344
Gradata/tests/test_cli_install_agent.py (1)
9-23: LGTM!Also applies to: 58-117
| "bandit>=1.7", | ||
| "coverage>=7.0", | ||
| "ruff>=0.4", | ||
| "httpx>=0.27.0", |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Description: Check if tests import or use httpx directly
rg -n --type=py -C3 'import httpx|from httpx' tests/Repository: Gradata/gradata
Length of output: 106
🏁 Script executed:
#!/bin/bash
# Find test directories and files
fd -type d -name 'test*' | head -20Repository: Gradata/gradata
Length of output: 230
🏁 Script executed:
#!/bin/bash
# List repository structure
git ls-files | grep -E '(test|spec)' | head -20Repository: Gradata/gradata
Length of output: 859
🏁 Script executed:
#!/bin/bash
# Read pyproject.toml to verify httpx placement
cat -n Gradata/pyproject.toml | sed -n '25p;30p;35p;40p;50p;58p;65p'Repository: Gradata/gradata
Length of output: 446
🏁 Script executed:
#!/bin/bash
# Get context around line 58 in pyproject.toml
cat -n Gradata/pyproject.toml | sed -n '50,65p'Repository: Gradata/gradata
Length of output: 435
🏁 Script executed:
#!/bin/bash
# Search for httpx usage in tests
rg 'import httpx|from httpx' Gradata/tests/ -nRepository: Gradata/gradata
Length of output: 169
🏁 Script executed:
#!/bin/bash
# Also check if tests reference llm extra or call code that uses httpx
rg 'httpx' Gradata/tests/ -n -C 2Repository: Gradata/gradata
Length of output: 1215
🏁 Script executed:
#!/bin/bash
# Read test_byo_key_provider.py to understand httpx usage context
cat -n Gradata/tests/test_byo_key_provider.py | head -40Repository: Gradata/gradata
Length of output: 1633
🏁 Script executed:
#!/bin/bash
# Check if BYOKeyProvider is only in llm or also in base package
rg 'class BYOKeyProvider|from.*BYOKeyProvider|import.*BYOKeyProvider' Gradata/src/ -nRepository: Gradata/gradata
Length of output: 457
🏁 Script executed:
#!/bin/bash
# Check if BYOKeyProvider could ever be imported or used without llm extra
# Look for any base/pure-python code that references BYOKeyProvider
rg 'BYOKeyProvider' Gradata/src/gradata --type=py | grep -v 'llm'Repository: Gradata/gradata
Length of output: 169
🏁 Script executed:
#!/bin/bash
# Check how CI installs the package - does it use [dev,llm] or just [dev]?
cat Gradata/.github/workflows/test.yml | grep -A5 -B5 'pip install\|pyproject.toml'Repository: Gradata/gradata
Length of output: 126
🏁 Script executed:
#!/bin/bash
# Find CI test workflow files
fd -name 'test.yml' -o -name 'test.yaml' 2>/dev/nullRepository: Gradata/gradata
Length of output: 41
🏁 Script executed:
#!/bin/bash
# Check test.yml location from earlier results
find . -path '*/.github/workflows/test.yml' 2>/dev/nullRepository: Gradata/gradata
Length of output: 88
🏁 Script executed:
#!/bin/bash
# Look at the test workflow file
cat -n .github/workflows/test.yml | grep -A10 -B5 'pip install\|extras'Repository: Gradata/gradata
Length of output: 412
Remove httpx>=0.27.0 from dev extras—it's already declared in the llm extras.
httpx is already a dependency of the llm optional group (line 35). Since tests import BYOKeyProvider from gradata.llm and CI installs with --all-extras, this creates unnecessary duplication.
Current state
llm = ["httpx>=0.27.0"] # line 35
dev = [
"pytest>=8.0",
...
"httpx>=0.27.0", # line 58 — redundant
]
Remove line 58 to eliminate the duplication and reduce maintenance surface.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@Gradata/pyproject.toml` at line 58, Remove the duplicate dependency entry
"httpx>=0.27.0" from the dev extras so it is only declared once under the llm
optional group; locate the dev extras block in the pyproject toml and delete the
"httpx>=0.27.0" line (the llm = ["httpx>=0.27.0"] entry should remain unchanged)
to avoid redundant declarations when installing --all-extras.
1 participant
Summary
Add GRADATA_VERIFY_INSTALL env flag (1/true/yes) to _cmd_install_agent. When set, after each successful agent install, writes a test rule via Brain.correct() then reads it back via Brain.search(). Failures surface explicit actionable errors. Flag OFF preserves current behavior.
Test plan
5 tests pass in tests/test_cli_install_agent.py
Flag details