Repository navigation
fix: whole diagnostic messages; name causes and workarounds - #27
Conversation
- Failure messages were cut off on their way to the user (a tensile_safety failure ended mid-advice): message buffers below 1024 characters are widened along every path, the C API keeps up to 4096 characters per handle (CableDyn_GetLastError still truncates to the caller's buffer), the driver's ErrMsg holds 4096 and the OpenFAST module uses ErrMsgLen. - A weightless line gets an accurate diagnosis: a finite-EI line longer than its span is reported as weightless, with no catenary and able to bow only in compression, instead of "net-heavy ... too long"; an EI = 0 line within a 1e-6 relative band of neutral buoyancy is rejected at its line type as weightless and slack (also in the Python reader), instead of failing later with a generic solver message. - A note when a static state stretches a line beyond maxStrain (10 % when unset); a note per section of at most four segments each longer than a tenth of the line. - The rejections of a shared line between two Coupled points, a finite-EI cable ending on a Connect/Free/Coupled point, a Coupled End A with Connect points, and deck waves/current on a mixed deck now name the unsupported capability and a workaround; an anchor below the seabed names the tolerance rule and the depth to use. Results are unchanged: every example and test deck writes byte-identical outputs, except a neutral EI = 0 deck now rejected at its line type. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
Widen the message buffers that still cut solver messages: the mixed standalone runner and its initialisation report (4096), the as-laid friction, seabed and kernel buffers of the static solvers, the OpenFAST mesh and Hermite module buffers, and the per-line messages of the mooring system and the aggregate (1024). The seed notes of a failed EI=0 static solve and the initialisation notes of a line end with an omission marker instead of stopping mid-note; a line summary holds a whole cable note and the strain note. Keep the net-buoyant rule unchanged (dry mass not above the displaced mass). Only an EI=0 type within a relative 1e-6 below the displaced mass is named neutrally buoyant; the Python deck reader mirrors it. The shared-line rejection offers the Connect-point split only for an EI=0 line and says what applies to a finite-EI one. The Coupled End A rejection says the end would need motionFile coupling and qualifies the coupled mixed deck advice. The coarse-section warning compares each segment with 1/8 of the whole line, so it no longer depends on how a line is split into sections; no example deck triggers it. The static strain note uses 10 % when maxStrain is absent or 0, and prints a small maxStrain with its digits. In the Hermite dynamic assembly the element kernels write into small message buffers, the tangent worker sets its message only on failure, and the Cosserat assembly no longer blank-fills its per-element messages. Results are byte-identical. New driver tests cover the band edge, a finite-EI shared line, and the coarse-section warning and strain note on the standalone mixed route. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
Widening every message buffer to 1024 characters slowed the dynamic step by up to 5 %, because element, node and Gauss-point kernels reset their whole message buffer on every call. A hot-path buffer now only holds the longest text that can actually reach it, and long messages are still assembled in full on the cold failure paths. Back to their previous lengths, each bounded by the kernels it calls: the Hermite element, drag and wave-load locals and the per-element message array (200), the Hermite element and sampling locals, the torsion element and line, the EI=0 element assembly, the Cosserat assembly and energy, and the per-node seabed, kinematics, range and static-friction buffers. The EI=0 load and added-mass assemblies, the assembly input checks and the rod seabed queries pass their kernels a 200- or 120-character share of the caller's message, so a kernel no longer resets a 1024-character buffer. The per-node seabed query of the Hermite static Newton step and the per-node kinematics of the deck fluid update use their own short buffers. Every message still fits whole, the blank-on-success contract of public kernels is unchanged, and results are byte-identical. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
The rejection of deck waves or current on the still-water routes listed the C API and single-turbine OpenFAST, which never reach it, and told a FAST.Farm user to let the host supply the fluid. It now names the route that rejects the deck: a standalone mixed EI=0/finite-EI deck is told to remove the OPTION, use a single-family deck, or couple the deck to OpenFAST with SeaState; a FAST.Farm deck is told the farm runs in still water and to remove the OPTION. The troubleshooting rows, the changelog and the driver test follow. The friction-anchor mapping, run twice per step, now gives its per-node seabed query only a short share of the caller's message buffer, as the load assembly does. A cable whose notes ended with the omission marker in its 1024-character buffer lost the static strain note when the notes were copied into the 2048-character line summary. A note that fits now goes before the marker, which stays last. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
Message buffers added since the branch point that can receive a longer message than they hold now hold it whole: - the node-value and segment-tension recovery of a finite-EI cable (node channels and .t.out rows), whose element failure carries the recovery prefix and a 200-character element message, and the node recovery of a range-graph sample, which gets its own buffer while the per-element curvature samples keep their short one; - the anchor force of an EI=0 line (anchor uplift channels), which carries the end-force recovery's load-assembly message; - the host wrench of a pinned rod, which carries the mooring system's coupled-motion and acceleration-derivative messages; - the exact-curvature query of the OpenFAST Hermite module and the step audit of an EI=0 line (1024, as their neighbours). The per-element law tensions of the step audit hold the kernels' bound (KERNEL_MSG_LEN). Buffers on per-station or per-node paths that already hold every message they receive (rod contact reach and waterplane estimate, Hermite node recovery kernels) are unchanged. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
The rotation- and snap-resolved sub-stepping merged from dev kept a plain sub-step's message in 300 characters, the law tensions of sub_tensions in 160, and the viscoelastic coefficients of segment_wave_stiffness in 200. A plain step's message (the tensile qualification failure) runs to several hundred characters and a law tension message with its prefix to about 250, so they now take 1024 characters, as the recovery rungs do; the per-element coefficient message takes KERNEL_MSG_LEN, the kernels' bound. The messages are discarded on these paths, so no output changes. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
The active tension of finite-EI cables merged from dev added message buffers that could cut a message short: the committed force and acceleration of a cable received a length-rebuild message of up to about 234 characters in 200, the step-start load and committed-length messages of an EI = 0 line went into 160, and the control take-back, the finite-section mesh of a CONTROL row and the segment-length update of the Hermite OpenFAST module held 512 and 300. These cold-path buffers now take 1024 characters; the buffers that receive a kernel message directly (distributed-load assembly and seabed stiffness at the committed or sub-step lengths) take KERNEL_MSG_LEN, the kernels' bound. No output changes. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 3526199d1c
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
The axial damping of a finite-EI cable under active length control wrote its kernel message into em2 while the failure handler reports em_e, the per-element kernel buffer, so a non-finite damping force or Jacobian on a controlled line returned a blank or stale message. Both controlled branches now write em_e, as the uncontrolled ones do. A scan of every source file for an error report that names a different message variable than the calls before it finds no other case. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
|
Codex Review: Didn't find any major issues. Swish! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
The snapshot test of a controlled cable marched the restored model against a copy taken before the snapshot. Restore clears the carried Newton factor, which the copy still holds, and the iterate a step stops at depends on the factor's age, so the two matched bit for bit only by chance: the merged dev failed the check on the Linux Debug runner while the same tree passed on the pull request. Both models now march with tangent reuse off, the documented condition for an exact restart, as the torsion restart test already does. The coupled cables of the OpenFAST module run with reuse off, so their restart tests are not affected. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
|
Codex Review: Didn't find any major issues. Keep it up! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
With tangent reuse off the snapshot test still failed on the Linux Debug runner. Restore also clears the cached committed force, so the restored model evaluates F_n afresh on its next step while the copy taken before the snapshot takes it from the cache of its previous step's last iteration. The copy's cache is now cleared as well, so both models take the same path, and the test prints the largest position and velocity difference after the three steps. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
|
Codex Review: Didn't find any major issues. More of your lovely PRs please. Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
Summary
Failure and rejection messages are whole, name the actual cause, and give the workaround. No acceptance rule or result changes.
... at element 64, xi= 0.5000; increase). Buffers of 200, 300 and 256 characters in the Hermite cable, the OpenFAST module and the deck driver cut it off.CableDyn_GetLastErrorstill truncates to the caller's buffer, and the Python binding reads 4097 bytes.EI = 0static solve, a line's initialisation notes) ends with "further ... notes omitted" instead of stopping mid-note.EI = 0line type rejected as net-buoyant whose mass lies within 1e-6 below the displaced mass is named neutrally buoyant, and the Python reader words it the same way.maxStrain(or 10 % if unset) is noted. Before, a line 50 % shorter than its span converged at 100 % strain without a word.Connect/Free/Coupledpoints.Tests
pre-commit run --all-filesand the Sphinx build with-Wpass.Checklist
pre-commit run --all-filespassesctest --test-dir build --output-on-failurepassespython -m pytest tests python/testspasses (if Python or validation records changed)[Unreleased](heading added if missing) for user-visible changesdoc/updated for changed inputs, options, or outputsfeat:,fix:,docs:, ...)git commit -s) under theDeveloper Certificate of Origin