- max_units_at_impact(): walks the LIVE bid book for a genuine, ticker-
specific instant-exit liquidity check, replacing a flat 25%-of-flow
guess (a price-vs-volume elasticity regression was tried first and
abandoned - confounded by demand-driven volume on real data). Surfaced
as an [exit-thin] WARNING flag, not a hard cap - a single order-book
snapshot is less reliable than the 30-day flow aggregate that still
drives n_lim/filtering (using it as a hard cap once silently zeroed
out a real recipe from one noisy snapshot).
- tref_precise(): real variance of daily traded volume instead of a
Poisson unit-independence bound, wired into stage 2 only (bounded
candidate set, cached). Also fixed: was averaging only over trading
days, overstating flow ~3x for sparse tickers.
- n_out(): dropped the demand-coverage term, which penalized thin
resting-bid books even though production sells via patient asks taken
by walk-up buyers with no resting bid at all.
- --sort area: profit/day per tile of TOTAL footprint, now including the
single-tier hab area a building's workforce drags along (was building
area only).
- --deprec/--reclaim-frac: amortizes unreclaimed capex, not full capex -
real FIO reclaim data showed 50-86% returned even at near-100%
condition, contradicting a 100%->0 decay-curve assumption.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Where to park idle cash in a buy-low/sell-high position while it has no
better use - scans every ticker for real bid/ask spread and liquidity,
scoring round-trip (buy-dip, sell-recovery) via the same empirical
first-passage model as sell.py's optimal-ask fix, instead of an assumed
random walk. Dropped the universe's top pick from ~94%/day to ~1%/day
with real waits of 19-194+ days under the corrected model. Default
--rate 0.0 matches the tool's own idle-cash premise (sell.py's rate of
0.05 assumes cash is earmarked, which isn't this tool's case).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
A driftless-random-walk closed form was tried first and backtested wrong
against 3 years of real exchange history (overstated touch probability
2-4x, confounded by discrete daily-VWAP sampling and real mean-reversion).
Replaced with puga.history.empirical_touch(): a non-parametric estimator
measuring first-passage directly from a ticker's own history, conditioned
on current state (trailing-60d z-score) since mean reversion's effect
depends on where price is now, not just move size. Queue-depth (existing
resting quantity) folds in as a deterministic shift of the hitting time,
not a max, ranking by the resulting hit_factor rather than a point
estimate of median days (which created a false cliff at the 50%-touched
threshold). Optional fixed-horizon right-censoring avoids recency bias
in "never reached" samples.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
network.py: tools/network.py now computes freight cost from the real fuel
model (puga.shipping.round_trip_cost) for direct-jump transfers instead of
the flat 9250 AIC placeholder; gateway transfers or an explicit trip_cost
in the chain YAML still use that as a fallback. puga/network.py's combine()
docstring now flags that its "flows cancel, only freight matters" claim
only holds under a symmetric-price basis (uni30, the default) - under
--basis real it understates the benefit of physical transfer by the
bid-ask spread on the moved quantity.
whatif.py: now charges marginal freight too - only the EXTRA round trips
an addition needs beyond the base's existing traffic, so a small addition
riding along on already-necessary hauls costs ~0, while one that adds
meaningfully to shipped tonnage doesn't get a free pass.
Terminology: "profit/day ÷ capex" was being reported as "ROI/day X%",
which invites reading it as a compoundable rate. It's just 1/payback_days -
there's no reinvestment mechanism and every opportunity here is
capacity/market-limited, so it can't be annualized like a real yield.
Payback in days is now the primary number everywhere (scan.py, simulate.py,
network.py, whatif.py); see docs/decisions.md for the reasoning.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Pulls real player-posted freight jobs from FIO's /localmarket/shipping
endpoints (public, no auth - distinct from the CONTD player-contract
system, which isn't exposed via any API). Ranks by margin after real
one-way fuel cost (puga.shipping.leg_cost), flagging ads that exceed the
account's ship hold or route through an unmeasured gateway.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Calibrated from a controlled slider sweep across 5 real destinations, read
from the live APEX Ship Flight Control DOM. Covers STL cruise, FTL
jumps/charges, gateway hops (measured LOCK fees for ANT<->HRT/BEN), and
per-planet landing fuel. Scoped to this account's one hull/reactor; open
gaps (gravity dependence, hull generalization, gateway one-way links,
per-gateway volume caps) are documented in the module docstring.
tools/shiptrip.py is the simple entry point (ship + from + to, works out
jumps/charges/landing itself); tools/shipcost.py takes explicit physics
params for when the breakdown is already known. puga/route.py now also
resolves CX station codes (ANT, HRT, ...), not just planets/systems - this
was needed for the gateway-aware lookups to work at all.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Finds manufactured goods currently selling below their implied
production cost (live input cost vs output price) - candidates to buy
and hold for a price-reversion bounce, the mirror of the "is this
worth building" question saturation.py already answers.
Backtested first (326 output tickers, 287 deduplicated dip-onset
episodes across 112 distinct tickers): +3mo forward return mean
+21.3%/median +8.9%/73.2% hit rate at >=10 units/day volume - real
signal, not noise, but only ~0.10-0.24%/day, far below the 14-29%/day
marginal ROI this session's production builds found. Documented
prominently in the tool's own docstring and CLAUDE.md so it doesn't
get mistaken for a primary strategy - it's for excess idle capital
once better-yielding builds are exhausted, not before.
Promoted daily_prices() out of tools/history.py into puga/history.py
so both tools share it, per the self-improve rule.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Ranks every planet with a given extraction factor using FIO's bulk
planet data, pricing founding cost straight from FIO's own
BuildRequirements (real environment-extras materials for that specific
planet, not guessed temperature/pressure thresholds - PRUNplanner's own
calculations don't model those either). Takes --from an existing base
to report jump distance via tools/route.py, since pure-factor ranking
alone is misleading: the best-factor planets found for FEO were all
500-2600+ ly away, confirming Vulcan (merely decent factor, same system
as Deimos) was still the right practical pick.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
PRUNplanner doesn't model travel, so nothing in the project could answer
"how far is planet X" until now. Builds a graph from /systemstars (698
systems, real jump connections + 3D coordinates) and runs Dijkstra
weighted by straight-line ly (what FTL fuel/time actually scale with),
reporting jump count alongside.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- puga/network.py + tools/network.py: model a multi-base chain (e.g. mine LST at one base,
ship it, consume it at another). Simulates each base independently, nets a transferred
material's producer-surplus against consumer-need, charges real freight only on what's
moved, cm_free for a founding covered by a Core Module Kit. Worked example in plans/chains/.
- puga/saturation.py: real price-band filtering. FIO's order_book NarrowPriceBandLow/High and
WidePriceBandLow/High match APEX's own displayed Price Band exactly (verified live) - an
order outside it is a stale artifact, not just uncompetitive. Added in_band() and
effective_demand(); effective_supply() gained the same hard band filter alongside its
existing soft vwap-proximity filter (renamed that param mult to free up `band`). Wired into
tools/scan.py stage 2 in place of the raw, unfiltered demand figure. Was flagged as an
unimplemented refinement in saturation-design.md since the original design review.
- tools/sell.py: self-contained tranche split (aggressive tranche capped at a volume quantile,
median normally or 80th pct with --tight when a payment is imminent and stockout risk
outweighs margin; patient tranche priced under the next competitor tier). Instant-bid
comparison moved behind --show-bid (off by default).
- Docs and roadmap updated accordingly.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- pyproject.toml + puga/cli.py: `pip install -e .` installs a `puga <tool>` command, so no
venv path is needed (replaces requirements.txt)
- tools/plan_push.py: `pull <uuid>` reads a plan (incl. UI edits) back into a YAML spec;
recipe entries may carry an amount so switched-off recipes round trip; fixes a variable
that overwrote the plan name in build_payload, with a regression test
- README: usage with the puga command, and a section on working on the same plans in the
PRUNplanner UI and from Claude (write, edit in UI, read back)
- CLAUDE.md updated accordingly
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- tools/simulate.py + puga/simulate.py: replica of PRUNplanner's simulator (flows and
efficiency verified against screenshots), reports real new capex (planned minus built)
- tools/scan.py: staffing variants, freight, HQ/experts, --planet mode, demolish-later,
--min-n as a pure market-size filter, --json output
- tools/history.py, tools/persistence.py: margin history and short-horizon payback checks
- tools/plan_push.py: guarded delete; tools/state.py: syncs to empire/
- README with features and setup; CLAUDE.md made generic
- Own-empire material (profile, state, plans, notes) moved to gitignored empire/;
generic examples in plans/examples and state/company.example.yaml
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
dodoxandClaude Sonnet 5