extropy estimate assumes early convergence, ignores timeline events

[DeveshParagiri]

Bug

extropy estimate predicts ~3 effective timesteps for a 6-timestep evolving scenario, but the simulation will actually run all 6 because early convergence is auto-disabled when future timeline events exist.

Evidence

ASI scenario: 5,000 agents, 6 monthly timesteps, each with a timeline event.

Estimated LLM Calls
                      Calls      Input Tok     Output Tok
  Pass 1              5,122    ~11,104,496     ~1,024,400
  ...
  Total:   $5.93

Estimate says "Effective timesteps: ~3 (early stop at ~100% exposure)" — but the simulation engine disables early convergence when allow_early_convergence is None (auto) and future timeline events exist (stopping.py:366). All 6 timesteps will run, so actual cost is ~2x the estimate.

Expected Behavior

Estimate should apply the same auto-convergence logic as the simulation engine: if the scenario has timeline events at future timesteps, assume all timesteps will run.

[DeveshParagiri]

Deeper analysis: estimator is 4-5x off

The estimator undercounts for three compounding reasons:

1. Ignores re_reasoning_intensity

The ASI scenario has re_reasoning_intensity: extreme on timesteps 1, 2, 3, and 6. When extreme, the engine forces ALL aware agents to re-reason (engine.py:656-660). The estimator doesn't model this at all — it uses a flat 2% re-reasoning rate (estimator.py:214).

2. Ignores early convergence auto-disable

As noted in the original issue, the estimator assumes early stop at ~3 timesteps. The engine runs all 6 because allow_early_convergence: null + future timeline events = disabled.

3. Doesn't model conversations

Medium/high fidelity adds 4-8 LLM calls per conversation (all fast model). The estimator counts zero conversation calls.

Actual vs estimated for ASI (5,000 agents × 6 timesteps)

	Estimator	Actual (projected)
Effective timesteps	3	6
Reasoning calls	~5,100	~21,000-22,000
Total LLM calls	~10,200	~42,000+
Cost	$5.93	$25-35

Per-timestep breakdown (projected)

Timestep	Intensity	Reasoning calls	Why
1	extreme	~4,000	Seed exposure (broadcast)
2	extreme	~5,500	Remaining exposed + ALL re-reason
3	extreme	~5,000	ALL aware agents forced
4	high	~300	Multi-touch only
5	high	~1,500	Some re-reasoning
6	extreme	~5,000	ALL aware agents forced

What needs fixing

The estimator needs to:

1. Read re_reasoning_intensity from each timeline event and model forced re-reasoning (extreme = all aware, high = fraction)
2. Apply the same early convergence auto-disable logic as the engine
3. Account for conversation calls based on fidelity setting

[DeveshParagiri]

Example: estimator vs reality for ASI scenario (5,000 agents × 6 timesteps)

What the estimator says

Effective timesteps: ~3 (early stop at ~100% exposure)
Total calls: ~10,200
Cost: $5.93

What actually runs (projected)

The estimator misses three things: (1) re_reasoning_intensity: extreme forces ALL aware agents to re-reason on timesteps 1/2/3/6, (2) early convergence is auto-disabled because every timestep has a timeline event, (3) conversations are not counted.

Reasoning calls per timestep:

Timestep	Intensity	Reasoning calls	Why
1	extreme	~4,000	Seed exposure (broadcast)
2	extreme	~5,500	Remaining exposed + ALL re-reason
3	extreme	~5,000	ALL aware forced
4	high	~300	Multi-touch only
5	high	~1,500	Some re-reasoning
6	extreme	~5,000	ALL aware forced
Total		~21,000

LLM calls breakdown by fidelity (gpt-5-mini @ $0.25/$2.00 per MTok):

                        MEDIUM FIDELITY          HIGH FIDELITY
─────────────────────────────────────────────────────────────
Reasoning events:       ~21,000                  ~21,000
Pass 1 calls:           21,000                   21,000
Pass 2 calls:           21,000                   42,000 (2× for public stmt)
Conversation calls:     ~21,000 × 15% × 1 × 4   ~21,000 × 15% × 2 × 6
                        = ~12,600                = ~37,800

Total LLM calls:        ~54,600                  ~100,800

Cost:

	Medium	High
Pass 1 (21K × ~2.2K in / 200 out)	~$20	~$20
Pass 2 (21-42K × ~300 in / 70 out)	~$4.5	~$9
Conversations (12-38K × ~800 in / 150 out)	~$6	~$18
Total	~$30	~$47

Time at 1000 RPM (Azure gpt-5-mini):

	Medium	High
Total calls	~55K	~101K
At 1000 RPM	~55 min	~101 min
With burst headroom	~45-55 min	~80-100 min

Estimator vs actual:

	Estimator	Actual (medium)	Actual (high)
Calls	~10K	~55K	~101K
Cost	$5.93	~$30	~$47
Time	N/A	~50 min	~90 min

Conversation % is a guess (15% of agents request talk_to). For a scenario like ASI where everyone has strong opinions, could be 30%+ — which would double the conversation line items.

[RandomOscillations]

Verification update (2026-02-24): issue still reproduces in current code.

Current estimator logic remains timeline-unaware:

• extropy/simulation/estimator.py:235-238 applies a generic exposure early-stop.
• It does not mirror simulation runtime gating that uses future timeline events / allow_early_convergence policy.

Given this mismatch, the CLI estimate surface has been temporarily stubbed to prevent misleading pre-run numbers while preserving estimator internals for later parity work.

Temporary CLI behavior:

• estimate is hidden from top-level help.
• Direct invocation returns a temporary-disabled message referencing this issue.

Keeping this issue open until estimator parity is implemented and tested against runtime stop behavior.