feat: add back fp and fn to memory

[EdenWuyifan]

No description provided.

[github-actions]

Coverage report

St.❔	Category	Percentage	Covered / Total
🟡	Statements	60.83%	7073/11627
🟡	Branches	65.62%	502/765
🔴	Functions	41.49%	117/282
🟡	Lines	60.83%	7073/11627

Test suite run success

3 tests passing in 3 suites.

Report generated by 🧪jest coverage report action from 6397075

[Copilot]

Pull Request Overview

This PR adds support for tracking false positives and false negatives in the memory system by introducing an isMatchToAgent field to user operations. The system now distinguishes between cases where the agent and user disagree on matches, enabling better memory management and agent learning.

Key changes:

• Adds isMatchToAgent boolean parameter to track agent vs. user match decisions
• Implements false positive/negative memory storage and retrieval functionality
• Updates UI components to handle undefined match states during transitions

Reviewed Changes

Copilot reviewed 11 out of 12 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
app/dashboard/rightpanel.tsx	Updates isMatch prop type to allow undefined values
app/dashboard/page.tsx	Passes isMatch parameter to dashboard operations hook
app/dashboard/hooks/useDashboardOperations.tsx	Adds isMatch parameter and includes it in user operations
app/dashboard/components/explanation/useSchemaExplanations.tsx	Changes initial isMatch state from false to undefined
app/dashboard/components/explanation/SchemaExplanation.tsx	Updates isMatch prop type to allow undefined
app/dashboard/components/explanation/CombinedView.tsx	Updates isMatch prop type to allow undefined
api/matching_task.py	Adds is_match_to_agent parameter to UserOperation class
api/langchain/memory.py	Implements false positive/negative storage and search functionality
api/langchain/agent.py	Adds methods for handling user operations and memory management
api/index.py	Updates API endpoints to handle isMatchToAgent parameter
README.md	Minor title correction from "LLM-Supported" to "LLM-Powered"

Comments suppressed due to low confidence (1)

api/langchain/memory.py:133

• [nitpick] The namespace key 'false_positives' uses underscores while other namespaces use underscores consistently, but the comment on line 114 uses spaces in 'false_positives'. Consider using consistent naming throughout - either 'false_positives' everywhere or 'falsePositives' to match the frontend camelCase convention.

            "false_positives": 0,

[Copilot]

The parameter is_match_to_agent should be required rather than optional with None default. When tracking false positives/negatives, this information is essential for proper memory categorization. Consider making this a required boolean parameter.

Suggested change

	is_match_to_agent: Optional[bool] = None,
	is_match_to_agent: bool,

[Copilot]

Direct dictionary access without validation could cause KeyError if 'isMatchToAgent' is missing from the request. Use operation_obj.get("isMatchToAgent") or add proper validation to handle cases where this field might be absent.

Suggested change

	is_match_to_agent = operation_obj["isMatchToAgent"]
	is_match_to_agent = operation_obj.get("isMatchToAgent")

[Copilot]

Direct dictionary access without validation could cause KeyError if 'isMatchToAgent' is missing from the operation. Use operation.get("isMatchToAgent") or add proper validation to handle cases where this field might be absent in historical operations.

Suggested change

	is_match_to_agent = operation["isMatchToAgent"]
	is_match_to_agent = operation.get("isMatchToAgent")

[Copilot]

Direct dictionary access without validation could cause KeyError if 'isMatchToAgent' is missing from the operation. Use operation.get("isMatchToAgent") or add proper validation to handle cases where this field might be absent in historical operations.

Suggested change

	is_match_to_agent = operation["isMatchToAgent"]
	is_match_to_agent = operation.get("isMatchToAgent")

[github-actions]

Coverage Report

File	Stmts	Miss	Cover	Missing
api
index.py	464	210	55%	34–35, 94, 102–106, 117–195, 213–218, 231–235, 252, 264, 272–311, 320–333, 348–354, 366–373, 385–390, 402–409, 422–429, 473, 482–489, 496–520, 549, 558, 564, 582, 593–602, 619–622, 637, 646–675, 680–695, 741, 748–750, 755–769, 784–794, 804, 813
matching_task.py	700	249	64%	85–87, 126–172, 180–237, 293, 319, 340–342, 439–440, 450–452, 464, 468–483, 495, 506–569, 572, 606, 729, 772, 812, 876–887, 928, 948–961, 966–1019, 1023–1025, 1039–1077, 1088, 1091–1098, 1132, 1147–1156, 1164–1179, 1182, 1185, 1189, 1196, 1205, 1221–1224, 1248–1264, 1292, 1303, 1321–1327, 1335, 1341, 1393, 1428–1437, 1484, 1497, 1526, 1534–1536, 1553, 1556–1560, 1563
session_manager.py	50	11	78%	25–26, 30–31, 39, 47–50, 53, 56
utils.py	216	90	58%	32, 46, 57–59, 62–64, 98–99, 124–126, 143, 146–155, 162–169, 179, 208, 218–233, 237–239, 251–287, 293–299, 340–342, 352–354, 358–360, 368–372, 380–383
api/candidate_quadrants
candidate_quadrants.py	90	22	76%	130, 136–152, 156–162, 165–168, 172
api/clusterer
column_encoder.py	43	13	70%	51, 55, 83, 92, 101–102, 111, 115, 125–126, 135–136, 144
embedding_clusterer.py	74	19	74%	59–76, 83, 102–110
utils.py	129	99	23%	14–16, 20–22, 27–29, 34–35, 40–46, 50–60, 64–66, 125, 129, 140–172, 177–190, 207–208, 236–307
api/langchain
agent.py	198	47	76%	85, 99–104, 106–109, 273, 281, 284–287, 296, 378–381, 400–403, 430–461, 466–475, 506–511
memory.py	284	80	72%	147–173, 295, 304, 312–313, 378, 380, 382, 545, 565–566, 585, 664–675, 678–689, 692–706, 709–723, 726–740, 768–769, 817–818, 826–827
rag.py	38	38	0%	1–69
api/langgraph
langgraph.py	201	201	0%	2–778
api/matcher
bdikit.py	41	2	95%	52, 113
difflib.py	23	2	91%	34, 48
magneto.py	25	1	96%	28
rapidfuzz_value.py	93	9	90%	49, 99, 106, 126, 148–151, 164–166
utils.py	10	2	80%	26, 49
valentine.py	40	2	95%	68, 79
api/tools
candidate_tools.py	65	15	77%	114–116, 136–138, 184–186, 227–229, 270–272
online_research_tools.py	181	67	63%	31, 61, 76, 85–87, 116–132, 143–159, 170–186, 197–213, 241, 247, 257, 285–287, 302, 330–332, 351, 390–392, 411, 421, 455–457, 461–484
query_tools.py	78	15	81%	132, 160–167, 189–196, 218–219
source_scraper.py	10	1	90%	40
task_tools.py	55	14	75%	27, 56–60, 87, 101–105, 120–126
TOTAL	3258	1209	63%

Tests	Skipped	Failures	Errors	Time
56	0 💤	4 ❌	0 🔥	1m 53s ⏱️