fix(readme): point agent-rules install path at the new in-package location#31
Merged
fix(readme): point agent-rules install path at the new in-package location#31
Conversation
…ation PR #23 moved `docs/agent-rules.md` → `taosmd/docs/agent-rules.md` and exposed it via `importlib.resources` as `taosmd.agent_rules()`, but the README still told the install agent to read the old path — which 404s on anyone following the install ritual after #23 shipped. Update step 5 of the install instructions to use the helper (`python -c "import taosmd; print(taosmd.agent_rules())"`) and fix the adjacent reference link to the new in-package path. Both editable and wheel installs now work as advertised.
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughThe README.md documentation is updated to change Step 5 of the "Let your agent install it" instructions from directing users to manually copy the "Memory — taosmd" rules block to fetching it programmatically via Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
Code Review SummaryStatus: No Issues Found | Recommendation: Merge Files Reviewed (1 file)
Reviewed by grok-code-fast-1:optimized:free · 161,512 tokens |
jaylfc
added a commit
that referenced
this pull request
Apr 19, 2026
… sections PR #31 clarified the headline (lines 7-9) that our 97.0% is end-to-end Judge accuracy, not Recall@5. But three downstream references still labelled it as Recall@5: 1. Benchmark Results table (line 158) — column header was "Recall@5" even though our 97% is Judge and the competitors' numbers are the different, looser Recall@5 metric. Split into "Score" + "Metric" columns so each row is honestly labelled; added a clarifying paragraph below the table pointing at both benchmark scripts. 2. Fusion Strategy Comparison (line 181) — column said "Recall@5" but all four strategies were measured with the same Judge harness. Renamed header to "Judge accuracy" and softened the "MemPalace- equivalent" label to "same algorithm as MemPalace" so it describes the retrieval approach, not the metric. 3. Key Features list (line 263) — "97.0% Recall@5" → "97.0% end-to-end Judge accuracy". Remaining Recall@5 references are all intentional: competitors' published numbers, the narrative paragraph explaining the metric difference, and the code-block comment for `longmemeval_recall.py` which is the Recall@5 reproduction script.
jaylfc
added a commit
that referenced
this pull request
Apr 19, 2026
… sections (#32) PR #31 clarified the headline (lines 7-9) that our 97.0% is end-to-end Judge accuracy, not Recall@5. But three downstream references still labelled it as Recall@5: 1. Benchmark Results table (line 158) — column header was "Recall@5" even though our 97% is Judge and the competitors' numbers are the different, looser Recall@5 metric. Split into "Score" + "Metric" columns so each row is honestly labelled; added a clarifying paragraph below the table pointing at both benchmark scripts. 2. Fusion Strategy Comparison (line 181) — column said "Recall@5" but all four strategies were measured with the same Judge harness. Renamed header to "Judge accuracy" and softened the "MemPalace- equivalent" label to "same algorithm as MemPalace" so it describes the retrieval approach, not the metric. 3. Key Features list (line 263) — "97.0% Recall@5" → "97.0% end-to-end Judge accuracy". Remaining Recall@5 references are all intentional: competitors' published numbers, the narrative paragraph explaining the metric difference, and the code-block comment for `longmemeval_recall.py` which is the Recall@5 reproduction script.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
PR #23 moved
docs/agent-rules.md→taosmd/docs/agent-rules.mdbut the README still tells the install agent to read the old path — 404s on anyone following the install ritual right now. Update step 5 to use thetaosmd.agent_rules()helper that PR #23 was designed for, plus fix the adjacent reference link. Pre-existing bug surfaced during a flat-repo audit.Summary by CodeRabbit