Add friction-evidence models for agent interaction GSoC proposal by SumeetDUTTA · Pull Request #2 · mesa/GSoC-learning-space

SumeetDUTTA · 2026-03-22T15:11:21Z

Adds three working models demonstrating Mesa interaction friction points:

Market Auction — exposes request-reply messaging gaps
- Workaround: shared inbox pattern
- Evidence: 30 steps, 8 sales, revenue tracking
Needs-Driven Wolf-Sheep — exposes behavior-selection friction
- Workaround: priority logic embedded in step()
- Evidence: action metrics show all four branches active
Opinion Diffusion — exposes pub-sub communication gaps
- Workaround: manual neighbor subscription wiring
- Evidence: 40 steps, opinions converge as expected

Each model includes:

Reproducible run with fixed seed
Measured outputs and interpretation
Clear Mesa friction-point documentation
Proposed minimal API improvements
Smoke tests proving reproducibility

These evidence models form the core of the 175-hour agent interaction framework GSoC proposal.

…iled insights on background, interest in Mesa, learning goals, and future contributions.

… objectives in agent-based modeling and Mesa contributions.

…g bid handling and auction logic

…ection logic

… logic

…pinion Diffusion models: clarify goals, setup, and results; enhance reproducibility with code snippets; improve structure and readability.

… Opinion Diffusion models: implement unit tests for model initialization, step execution, and data collection.

coderabbitai · 2026-03-22T15:11:27Z

Important

Review skipped

Auto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: 03ce2281-98c9-4aa2-85dc-23ce1c8c4017

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

🔍 Trigger review

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

Copilot

Pull request overview

This PR adds three “friction-evidence” Mesa models (market auction, needs-driven wolf-sheep, opinion diffusion) intended to demonstrate gaps in agent interaction patterns for a GSoC proposal, along with supporting writeups and smoke tests.

Changes:

Add three behavioral experiment models under models/behavioral_experiment/01_* through 03_*, each with code, README evidence, and smoke tests.
Update candidate materials (motivation.md, models/ANALYSIS.md) and improve top-level README.md formatting.
Add VS Code pytest configuration.

Reviewed changes

Copilot reviewed 16 out of 16 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
motivation.md	Filled in motivation/fit for Mesa and learning goals.
README.md	Formatting adjustments (spacing/markdown consistency).
models/ANALYSIS.md	Notes about running/analyzing advanced Wolf-Sheep issues.
.vscode/settings.json	Configure pytest runner defaults for VS Code.
models/behavioral_experiment/01_market_auction/model.py	Implements a seller/buyer auction interaction model.
models/behavioral_experiment/01_market_auction/agents.py	Defines Buyer/Seller agents and a Bid message object.
models/behavioral_experiment/01_market_auction/test_smoke.py	Adds basic execution/log-structure smoke tests.
models/behavioral_experiment/01_market_auction/README.md	Documents friction point + reproducible run + outputs.
models/behavioral_experiment/02_needs_driven_wolf_sheep/model.py	Implements needs-driven sheep actions + metrics collection.
models/behavioral_experiment/02_needs_driven_wolf_sheep/agents.py	Sheep/Wolf/GrassPatch agent behaviors with internal drives.
models/behavioral_experiment/02_needs_driven_wolf_sheep/test_smoke.py	Adds initialization, datacollector, and metric smoke tests.
models/behavioral_experiment/02_needs_driven_wolf_sheep/README.md	Documents friction point + reproducible run + outputs.
models/behavioral_experiment/03_opinion_diffusion/model.py	Implements opinion diffusion over a random network.
models/behavioral_experiment/03_opinion_diffusion/agents.py	Defines OpinionAgent using mesa_signals observables.
models/behavioral_experiment/03_opinion_diffusion/test_smoke.py	Adds initialization, bounds, and message-receipt smoke tests.
models/behavioral_experiment/03_opinion_diffusion/README.md	Documents friction point + reproducible run + outputs.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-03-22T15:15:20Z

models/behavioral_experiment/02_needs_driven_wolf_sheep/model.py

+    def __init__(
+        self,
+        scenario: NeedsDrivenWolfSheepScenario = NeedsDrivenWolfSheepScenario,
+    ):
+        super().__init__(scenario=scenario)


The default value for scenario is the NeedsDrivenWolfSheepScenario class, not an instance. Calling NeedsDrivenWolfSheepModel() without passing a scenario will make scenario.height/width/... fail at runtime. Default this parameter to an instance (e.g., NeedsDrivenWolfSheepScenario()) or accept None and construct a default inside __init__.

Copilot · 2026-03-22T15:15:20Z

models/behavioral_experiment/03_opinion_diffusion/test_smoke.py

+	sys.path.insert(0, str(MESA_SOURCE_ROOT))
+
+
+def _build_model(seed: int = 42):
+	from model import OpinionDiffusionModel
+
+	return OpinionDiffusionModel(
+		num_agents=20,
+		avg_degree=5,
+		learning_rate=0.1,
+		contrarian_probability=0.2,
+		rng=seed,
+	)
+
+
+def test_model_initializes():
+	m = _build_model(seed=42)
+	assert m.round == 0
+	assert m.time == 0
+	assert len(m.agents) == 20
+	assert len(m.history) == 1
+
+	first = m.history[0]
+	for key in ("round", "mean_opinion", "min_opinion", "max_opinion"):
+		assert key in first
+
+
+def test_model_runs_10_steps():
+	m = _build_model(seed=42)
+	for _ in range(10):
+		m.step()
+
+	assert m.round == 10
+	assert m.time == 10
+	assert len(m.history) == 11
+	assert m.history[-1]["round"] == 10
+
+
+def test_opinions_stay_in_unit_interval():
+	from agents import OpinionAgent
+
+	m = _build_model(seed=42)
+	for _ in range(15):
+		m.step()
+
+	for agent in m.agents_by_type[OpinionAgent]:
+		assert 0.0 <= agent.opinion <= 1.0
+
+
+def test_agents_receive_neighbor_messages():
+	from agents import OpinionAgent
+
+	m = _build_model(seed=42)
+	m.step()
+
+	received_total = sum(
+		agent.messages_received for agent in m.agents_by_type[OpinionAgent]
+	)
+	assert received_total > 0
+
+
+def test_seeded_runs_advance_consistently():
+	m1 = _build_model(seed=42)
+	m2 = _build_model(seed=123)
+
+	m1.step()
+	m2.step()
+
+	assert m1.round == m2.round == 1
+	assert m1.time == m2.time == 1
+	assert len(m1.history) == len(m2.history) == 2
+
+
+if __name__ == "__main__":
+	test_model_initializes()
+	test_model_runs_10_steps()
+	test_opinions_stay_in_unit_interval()
+	test_agents_receive_neighbor_messages()
+	test_seeded_runs_advance_consistently()
+	print("All tests passed!")


This file mixes tabs and spaces for indentation (e.g., the sys.path.insert block and most function bodies are tab-indented). This can cause style/tooling issues and is inconsistent with standard Python formatting (PEP 8). Re-indent using spaces consistently.

Suggested change

sys.path.insert(0, str(MESA_SOURCE_ROOT))

def _build_model(seed: int = 42):

from model import OpinionDiffusionModel

return OpinionDiffusionModel(

num_agents=20,

avg_degree=5,

learning_rate=0.1,

contrarian_probability=0.2,

rng=seed,

)

def test_model_initializes():

m = _build_model(seed=42)

assert m.round == 0

assert m.time == 0

assert len(m.agents) == 20

assert len(m.history) == 1

first = m.history[0]

for key in ("round", "mean_opinion", "min_opinion", "max_opinion"):

assert key in first

def test_model_runs_10_steps():

m = _build_model(seed=42)

for _ in range(10):

m.step()

assert m.round == 10

assert m.time == 10

assert len(m.history) == 11

assert m.history[-1]["round"] == 10

def test_opinions_stay_in_unit_interval():

from agents import OpinionAgent

m = _build_model(seed=42)

for _ in range(15):

m.step()

for agent in m.agents_by_type[OpinionAgent]:

assert 0.0 <= agent.opinion <= 1.0

def test_agents_receive_neighbor_messages():

from agents import OpinionAgent

m = _build_model(seed=42)

m.step()

received_total = sum(

agent.messages_received for agent in m.agents_by_type[OpinionAgent]

)

assert received_total > 0

def test_seeded_runs_advance_consistently():

m1 = _build_model(seed=42)

m2 = _build_model(seed=123)

m1.step()

m2.step()

assert m1.round == m2.round == 1

assert m1.time == m2.time == 1

assert len(m1.history) == len(m2.history) == 2

if __name__ == "__main__":

test_model_initializes()

test_model_runs_10_steps()

test_opinions_stay_in_unit_interval()

test_agents_receive_neighbor_messages()

test_seeded_runs_advance_consistently()

print("All tests passed!")

sys.path.insert(0, str(MESA_SOURCE_ROOT))

def _build_model(seed: int = 42):

from model import OpinionDiffusionModel

return OpinionDiffusionModel(

num_agents=20,

avg_degree=5,

learning_rate=0.1,

contrarian_probability=0.2,

rng=seed,

)

def test_model_initializes():

m = _build_model(seed=42)

assert m.round == 0

assert m.time == 0

assert len(m.agents) == 20

assert len(m.history) == 1

first = m.history[0]

for key in ("round", "mean_opinion", "min_opinion", "max_opinion"):

assert key in first

def test_model_runs_10_steps():

m = _build_model(seed=42)

for _ in range(10):

m.step()

assert m.round == 10

assert m.time == 10

assert len(m.history) == 11

assert m.history[-1]["round"] == 10

def test_opinions_stay_in_unit_interval():

from agents import OpinionAgent

m = _build_model(seed=42)

for _ in range(15):

m.step()

for agent in m.agents_by_type[OpinionAgent]:

assert 0.0 <= agent.opinion <= 1.0

def test_agents_receive_neighbor_messages():

from agents import OpinionAgent

m = _build_model(seed=42)

m.step()

received_total = sum(

agent.messages_received for agent in m.agents_by_type[OpinionAgent]

)

assert received_total > 0

def test_seeded_runs_advance_consistently():

m1 = _build_model(seed=42)

m2 = _build_model(seed=123)

m1.step()

m2.step()

assert m1.round == m2.round == 1

assert m1.time == m2.time == 1

assert len(m1.history) == len(m2.history) == 2

if __name__ == "__main__":

test_model_initializes()

test_model_runs_10_steps()

test_opinions_stay_in_unit_interval()

test_agents_receive_neighbor_messages()

test_seeded_runs_advance_consistently()

print("All tests passed!")

Copilot · 2026-03-22T15:15:21Z

models/behavioral_experiment/02_needs_driven_wolf_sheep/test_smoke.py

+	sys.path.insert(0, str(MESA_SOURCE_ROOT))
+
+
+def _small_scenario(seed: int = 42):
+	from model import NeedsDrivenWolfSheepScenario
+
+	return NeedsDrivenWolfSheepScenario(
+		rng=seed,
+		width=10,
+		height=10,
+		initial_sheep=30,
+		initial_wolves=8,
+		sheep_reproduce=0.04,
+		wolf_reproduce=0.03,
+		wolf_gain_from_food=16.0,
+		sheep_gain_from_food=4.0,
+		grass=True,
+		grass_regrowth_time=12,
+	)
+
+
+def test_model_initializes():
+	from model import NeedsDrivenWolfSheepModel
+
+	m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())
+	assert m.time == 0
+	assert m.running is True
+	assert len(m.agents) > 0
+
+	df = m.datacollector.get_model_vars_dataframe()
+	assert len(df) == 1
+
+
+def test_model_runs_10_steps_and_collects_data():
+	from model import NeedsDrivenWolfSheepModel
+
+	m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())
+	for _ in range(10):
+		m.step()
+
+	assert m.time == 10
+	df = m.datacollector.get_model_vars_dataframe()
+	assert len(df) == 11
+
+
+def test_datacollector_has_expected_columns():
+	from model import NeedsDrivenWolfSheepModel
+
+	m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())
+	m.step()
+
+	df = m.datacollector.get_model_vars_dataframe()
+	expected = {
+		"Wolves",
+		"Sheep",
+		"Grass",
+		"AvgSheepFear",
+		"MaxSheepFear",
+		"AvgSheepFatigue",
+		"AvgSheepHunger",
+		"FleeCount",
+		"ForageCount",
+		"RestCount",
+		"WanderCount",
+	}
+	assert expected.issubset(set(df.columns))
+
+
+def test_action_counts_are_non_negative():
+	from model import NeedsDrivenWolfSheepModel
+
+	m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())
+	m.step()
+	row = m.datacollector.get_model_vars_dataframe().iloc[-1]
+
+	for key in ("FleeCount", "ForageCount", "RestCount", "WanderCount"):
+		assert row[key] >= 0
+
+
+def test_grass_metric_zero_when_grass_disabled():
+	from model import NeedsDrivenWolfSheepModel, NeedsDrivenWolfSheepScenario
+
+	scenario = NeedsDrivenWolfSheepScenario(
+		rng=42,
+		width=10,
+		height=10,
+		initial_sheep=20,
+		initial_wolves=5,
+		grass=False,
+	)
+	m = NeedsDrivenWolfSheepModel(scenario=scenario)
+	m.step()
+
+	row = m.datacollector.get_model_vars_dataframe().iloc[-1]
+	assert row["Grass"] == 0
+
+
+def test_seeded_run_advances_time_consistently():
+	from model import NeedsDrivenWolfSheepModel
+
+	m1 = NeedsDrivenWolfSheepModel(scenario=_small_scenario(seed=42))
+	m2 = NeedsDrivenWolfSheepModel(scenario=_small_scenario(seed=123))
+
+	m1.step()
+	m2.step()
+	assert m1.time == m2.time == 1
+
+
+if __name__ == "__main__":
+	test_model_initializes()
+	test_model_runs_10_steps_and_collects_data()
+	test_datacollector_has_expected_columns()
+	test_action_counts_are_non_negative()
+	test_grass_metric_zero_when_grass_disabled()
+	test_seeded_run_advances_time_consistently()
+	print("All tests passed!")


This file uses tab indentation in several places (e.g., the sys.path.insert block). Standard Python formatting expects spaces, and mixed indentation can break linters/formatters and lead to subtle issues. Please convert indentation to spaces consistently.

Suggested change

sys.path.insert(0, str(MESA_SOURCE_ROOT))

def _small_scenario(seed: int = 42):

from model import NeedsDrivenWolfSheepScenario

return NeedsDrivenWolfSheepScenario(

rng=seed,

width=10,

height=10,

initial_sheep=30,

initial_wolves=8,

sheep_reproduce=0.04,

wolf_reproduce=0.03,

wolf_gain_from_food=16.0,

sheep_gain_from_food=4.0,

grass=True,

grass_regrowth_time=12,

)

def test_model_initializes():

from model import NeedsDrivenWolfSheepModel

m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())

assert m.time == 0

assert m.running is True

assert len(m.agents) > 0

df = m.datacollector.get_model_vars_dataframe()

assert len(df) == 1

def test_model_runs_10_steps_and_collects_data():

from model import NeedsDrivenWolfSheepModel

m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())

for _ in range(10):

m.step()

assert m.time == 10

df = m.datacollector.get_model_vars_dataframe()

assert len(df) == 11

def test_datacollector_has_expected_columns():

from model import NeedsDrivenWolfSheepModel

m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())

m.step()

df = m.datacollector.get_model_vars_dataframe()

expected = {

"Wolves",

"Sheep",

"Grass",

"AvgSheepFear",

"MaxSheepFear",

"AvgSheepFatigue",

"AvgSheepHunger",

"FleeCount",

"ForageCount",

"RestCount",

"WanderCount",

}

assert expected.issubset(set(df.columns))

def test_action_counts_are_non_negative():

from model import NeedsDrivenWolfSheepModel

m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())

m.step()

row = m.datacollector.get_model_vars_dataframe().iloc[-1]

for key in ("FleeCount", "ForageCount", "RestCount", "WanderCount"):

assert row[key] >= 0

def test_grass_metric_zero_when_grass_disabled():

from model import NeedsDrivenWolfSheepModel, NeedsDrivenWolfSheepScenario

scenario = NeedsDrivenWolfSheepScenario(

rng=42,

width=10,

height=10,

initial_sheep=20,

initial_wolves=5,

grass=False,

)

m = NeedsDrivenWolfSheepModel(scenario=scenario)

m.step()

row = m.datacollector.get_model_vars_dataframe().iloc[-1]

assert row["Grass"] == 0

def test_seeded_run_advances_time_consistently():

from model import NeedsDrivenWolfSheepModel

m1 = NeedsDrivenWolfSheepModel(scenario=_small_scenario(seed=42))

m2 = NeedsDrivenWolfSheepModel(scenario=_small_scenario(seed=123))

m1.step()

m2.step()

assert m1.time == m2.time == 1

if __name__ == "__main__":

test_model_initializes()

test_model_runs_10_steps_and_collects_data()

test_datacollector_has_expected_columns()

test_action_counts_are_non_negative()

test_grass_metric_zero_when_grass_disabled()

test_seeded_run_advances_time_consistently()

print("All tests passed!")

sys.path.insert(0, str(MESA_SOURCE_ROOT))

def _small_scenario(seed: int = 42):

from model import NeedsDrivenWolfSheepScenario

return NeedsDrivenWolfSheepScenario(

rng=seed,

width=10,

height=10,

initial_sheep=30,

initial_wolves=8,

sheep_reproduce=0.04,

wolf_reproduce=0.03,

wolf_gain_from_food=16.0,

sheep_gain_from_food=4.0,

grass=True,

grass_regrowth_time=12,

)

def test_model_initializes():

from model import NeedsDrivenWolfSheepModel

m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())

assert m.time == 0

assert m.running is True

assert len(m.agents) > 0

df = m.datacollector.get_model_vars_dataframe()

assert len(df) == 1

def test_model_runs_10_steps_and_collects_data():

from model import NeedsDrivenWolfSheepModel

m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())

for _ in range(10):

m.step()

assert m.time == 10

df = m.datacollector.get_model_vars_dataframe()

assert len(df) == 11

def test_datacollector_has_expected_columns():

from model import NeedsDrivenWolfSheepModel

m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())

m.step()

df = m.datacollector.get_model_vars_dataframe()

expected = {

"Wolves",

"Sheep",

"Grass",

"AvgSheepFear",

"MaxSheepFear",

"AvgSheepFatigue",

"AvgSheepHunger",

"FleeCount",

"ForageCount",

"RestCount",

"WanderCount",

}

assert expected.issubset(set(df.columns))

def test_action_counts_are_non_negative():

from model import NeedsDrivenWolfSheepModel

m = NeedsDrivenWolfSheepModel(scenario=_small_scenario())

m.step()

row = m.datacollector.get_model_vars_dataframe().iloc[-1]

for key in ("FleeCount", "ForageCount", "RestCount", "WanderCount"):

assert row[key] >= 0

def test_grass_metric_zero_when_grass_disabled():

from model import NeedsDrivenWolfSheepModel, NeedsDrivenWolfSheepScenario

scenario = NeedsDrivenWolfSheepScenario(

rng=42,

width=10,

height=10,

initial_sheep=20,

initial_wolves=5,

grass=False,

)

m = NeedsDrivenWolfSheepModel(scenario=scenario)

m.step()

row = m.datacollector.get_model_vars_dataframe().iloc[-1]

assert row["Grass"] == 0

def test_seeded_run_advances_time_consistently():

from model import NeedsDrivenWolfSheepModel

m1 = NeedsDrivenWolfSheepModel(scenario=_small_scenario(seed=42))

m2 = NeedsDrivenWolfSheepModel(scenario=_small_scenario(seed=123))

m1.step()

m2.step()

assert m1.time == m2.time == 1

if __name__ == "__main__":

test_model_initializes()

test_model_runs_10_steps_and_collects_data()

test_datacollector_has_expected_columns()

test_action_counts_are_non_negative()

test_grass_metric_zero_when_grass_disabled()

test_seeded_run_advances_time_consistently()

print("All tests passed!")

Copilot · 2026-03-22T15:15:21Z

models/behavioral_experiment/01_market_auction/model.py

+    def step(self) -> None:
+        self.round += 1
+
+        # 1) Seller posts the current price.
+        self.seller.post_price()
+
+        # 2) Buyers submit their bids(via shared inbox workaround).
+        self.agents_by_type[Buyer].shuffle_do('step')
+
+        # 3) Seller processes the highest valid bid.
+        self.seller.step()
+


step() overrides mesa.Model.step but never advances self.time (or calls super().step()). The accompanying smoke tests assert that m.time increments with each step(), so this is likely to fail and also makes per-round timestamps (e.g., in logs) misleading. Consider calling super().step() (if it owns time advancement) or explicitly incrementing self.time to keep time and round consistent.

Copilot · 2026-03-22T15:15:21Z

models/behavioral_experiment/03_opinion_diffusion/model.py

+            }
+        )
+
+    def step(self) -> None:


step() doesn't advance the model clock (self.time) or call super().step(). The test suite asserts m.time == 10 after 10 calls to m.step(), so this will likely fail and also affects any time-based logging/behavior that relies on model.time. Align round and time by advancing time in step() (or delegating to the base class).

Suggested change

def step(self) -> None:

def step(self) -> None:

# Advance the model clock to keep `self.time` aligned with `round`.

self.time += 1

Copilot · 2026-03-22T15:15:22Z

models/behavioral_experiment/02_needs_driven_wolf_sheep/model.py

+
+    def step(self):
+        self.agents_by_type[Sheep].shuffle_do("step")
+        self.agents_by_type[Wolf].shuffle_do("step")


NeedsDrivenWolfSheepModel.step() doesn't advance self.time (and doesn't call super().step()). The smoke tests assert that m.time increases by 1 per call, so the current implementation likely breaks those assertions and can desynchronize DataCollector indexing if it keys off time.

Suggested change

self.agents_by_type[Wolf].shuffle_do("step")

self.agents_by_type[Wolf].shuffle_do("step")

# Advance model time so that it stays in sync with step calls and data collection.

self.time += 1

…mework analysis, adding detailed model descriptions and problems exposed

SumeetDUTTA added 8 commits March 15, 2026 23:40

Update motivation.md: Complete personal motivation sections with deta…

42741d4

…iled insights on background, interest in Mesa, learning goals, and future contributions.

initial commit

7afd38d

Update motivation.md: Refine personal background and clarify learning…

8e85483

… objectives in agent-based modeling and Mesa contributions.

Implement Market Auction model with Buyer and Seller agents, includin…

62c0f58

…g bid handling and auction logic

Add Needs-Driven Wolf-Sheep model with behavior tuning and action sel…

82255fa

…ection logic

Add Opinion Diffusion model with agent communication and broadcasting…

0e96cc3

… logic

Refactor README.md for Market Auction, Needs-Driven Wolf-Sheep, and O…

e294bed

…pinion Diffusion models: clarify goals, setup, and results; enhance reproducibility with code snippets; improve structure and readability.

Add test smoke files for Market Auction, Needs-Driven Wolf-Sheep, and…

367e8fa

… Opinion Diffusion models: implement unit tests for model initialization, step execution, and data collection.

Copilot AI review requested due to automatic review settings March 22, 2026 15:11

Copilot started reviewing on behalf of SumeetDUTTA March 22, 2026 15:11 View session

Copilot AI reviewed Mar 22, 2026

View reviewed changes

Refactor ANALYSIS.md: update structure and content for behavioral fra…

0e2cc6b

…mework analysis, adding detailed model descriptions and problems exposed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add friction-evidence models for agent interaction GSoC proposal#2

Add friction-evidence models for agent interaction GSoC proposal#2
SumeetDUTTA wants to merge 9 commits intomesa:mainfrom
SumeetDUTTA:main

SumeetDUTTA commented Mar 22, 2026

Uh oh!

coderabbitai bot commented Mar 22, 2026 •

edited

Loading

Review skipped

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Mar 22, 2026

Uh oh!

Copilot AI Mar 22, 2026

Uh oh!

Copilot AI Mar 22, 2026

Uh oh!

Copilot AI Mar 22, 2026

Uh oh!

Copilot AI Mar 22, 2026

Uh oh!

Copilot AI Mar 22, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

SumeetDUTTA commented Mar 22, 2026

Uh oh!

coderabbitai bot commented Mar 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Review skipped

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Mar 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 22, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

coderabbitai bot commented Mar 22, 2026 •

edited

Loading