BUG-353 fallbacks used undefined window columns and un-narrowed clock/focus values, so Docker next build failed typecheck and could not publish the already-pushed staging head.
Co-authored-by: Cursor <cursoragent@cursor.com>
Disable provider thinking so Flash CoT cannot fill max_tokens, raise the
spoken budget to 16384, emit a server-owned step tree, and continue once
when the body ends on length.
Co-authored-by: Cursor <cursoragent@cursor.com>
Users pick a clock range instead of a coarse period plus notes, so
rectification and window consult scan that range instead of a leftover afternoon bucket.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep report_schema_invalid for the user, but record the inner check, retry plan bind once, and format self-hosted timestamptz so the report list no longer shows 时间未知.
Co-authored-by: Cursor <cursoragent@cursor.com>
Empty ledgers stay in natural-language collection. After the first dated
event, dasha conflict probes reverse-infer 前事 and block offer until
answered. Unique-minute confirmation stays closed at a representative
time; adopt reverse-verifies remaining probes. Records BUG-348–351.
Co-authored-by: Cursor <cursoragent@cursor.com>
Thinking disappeared on failure and never reached session storage. Keep the
sanitized chain on disk and on errors, and regroup the sidebar around reports,
charts, favorites, and dated history titles.
Co-authored-by: Cursor <cursoragent@cursor.com>
Enumerate evidence kinds so education cannot be proposed as a kind, and stream Chinese thinking on a separate channel that collapses when the reply arrives.
Co-authored-by: Cursor <cursoragent@cursor.com>
BUG-341 added declared_birth_window, but the natal-minute helper still returned boolean, so next build could not pass that mode into serverChartFromProfile.
Co-authored-by: Cursor <cursoragent@cursor.com>
Conflict nodes stay server-owned; the Agent writes the question and option copy so users can tap instead of typing through an interrogation.
Co-authored-by: Cursor <cursoragent@cursor.com>
Rectification stays optional. Reported minutes can consult and generate reports; date-plus-period uses a declared window instead of a midpoint or 00:00. Updates BUG-341.
Co-authored-by: Cursor <cursoragent@cursor.com>
Rectification dropped tool.activity started events and treated length finishes as completed. Share generation settings with consultation, keep the activity line through streaming, and name multi-domain chart calculation.
Co-authored-by: Cursor <cursoragent@cursor.com>
Homepage bootstrap never escaped the loading shell when a new web image changed chunk hashes. Stamp deploymentId, stop caching chat HTML, and hard-reload failed chunk loads once.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep unique-top and width on confirmation only, and stop lagna-frame follow-ups from blocking cards on an already-scored cluster.
Co-authored-by: Cursor <cursoragent@cursor.com>
The quality gate still expected the old board-only varga sentence ban, and public dasha ledger copy leaked raw scores.
Co-authored-by: Cursor <cursoragent@cursor.com>
BUG-330: the compact board sat in the same layer as the composer, so peek copy overlapped the sheet title. Overlay only below 768px; desktop stays a side column.
Co-authored-by: Cursor <cursoragent@cursor.com>
Use the quiet overlay scrollbar on chat and the house board, replace the blocking mobile dialog with a bottom sheet, and emit agent deltas before billing so users can read progress and stop a run.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep representative-time cards off while method coverage is still open.
New cases bind Skill 10.0.9; existing 10.0.8 packages stay hashed.
Co-authored-by: Cursor <cursoragent@cursor.com>
The board was live data sitting under chat, so each new event looked like nothing changed. Keep candidate cards in the transcript and group 换升 by minute for the side panel.
Co-authored-by: Cursor <cursoragent@cursor.com>
Docker npm run build failed on Failed to type check. The skill-package-registry Import traces were only file-tracing noise; houseTable used && on string|null, and eight-method tests compared impossible literals that tsconfig still typechecks.
Co-authored-by: Cursor <cursoragent@cursor.com>
Interviews skipped D2/D11 and D30 unless the user volunteered them, so those scoring layers almost never ran. Ask them after family, keep relocation out of rotation, and display Bhava/Pranapada transitions without delaying adopt.
Co-authored-by: Cursor <cursoragent@cursor.com>
Window scan now drives d5_refine when D24 changes, family events use D3, and pada/Hora/Ghati are display-only. New cases bind Skill 10.0.7 without unique-minute confirmation.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep confirmation fail-closed until the public AA set is ready, and rewrite Technique Audit from the attached VedAstro status instead of a hardcoded blocked row.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep family on D12+D7 instead of mixing it into D4, score D5 on education, and show a natal recast plus technique audit after adopt without unique-minute claims.
Co-authored-by: Cursor <cursoragent@cursor.com>
Dated family evidence now moves candidates via D12 and kin houses, career receipts expose both D1-10 and D10, and appearance/marks may be asked as auxiliary first-house scores. New cases bind Skill 10.0.4.
Co-authored-by: Cursor <cursoragent@cursor.com>
Surface D9/D10 change minutes, event-dasha match copy, dual-dasha conflict, and a post-adopt consult handoff so users can keep narrowing or start a reading from a representative time.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep collecting while a method follow-up can still distinguish candidates, and show adoption cards only after offer-candidates. Align the natal house snapshot with the agent text column.
Co-authored-by: Cursor <cursoragent@cursor.com>
Transcript limits were collapsing the create schema, and joined profile selects typed as GenericStringError, so Docker next build failed after tests passed.
Co-authored-by: Cursor <cursoragent@cursor.com>
Incomplete Flash generations were billed as completed consultations. Fail
those runs, keep the partial text, and reuse the rectification like/copy/rerun
bar on ordinary chat replies.
Co-authored-by: Cursor <cursoragent@cursor.com>
Stop accepting client-supplied birth data on those paths, and cap session writes plus location lookups so a logged-in caller cannot farm compute.
Co-authored-by: Cursor <cursoragent@cursor.com>
Foreground still skips the heavy overview stack, but overlaps a timed
gateway so official evidence can merge when it finishes in budget.
Co-authored-by: Cursor <cursoragent@cursor.com>
Web consult already computed Yoga, Arudha, KP, and related layers, then
stripped them before the spoken model. Keep those executed structures in
toModelOutput so answers cannot invent degrees from parametric knowledge.
Co-authored-by: Cursor <cursoragent@cursor.com>
The homepage was waiting on a full chart plus four extra engines, so the card timed out and showed the failure copy on every visit.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep comparative tables in chat, but hide the long audit behind a collapsed control so the reply stays readable.
Co-authored-by: Cursor <cursoragent@cursor.com>
Adjacent minutes still cannot confirm a unique birth minute. A scored
representative time can now be accepted, and the copy must say the minute
is not unique.
Co-authored-by: Cursor <cursoragent@cursor.com>
Manual SKILL.md updates were blocked by registry sha256 and a byte-equal versions/ gate. Consult now loads the operator-maintained tree; rectification and personal-report stay hashed.
Co-authored-by: Cursor <cursoragent@cursor.com>
Web was round-robinning missing domains and waiting to score until the user said they had no more events. Server follow-up now uses the eight-method plan, rescored snapshots stay candidates, and D9/D10 observations never become user labels.
Co-authored-by: Cursor <cursoragent@cursor.com>
SQL kinds now match the TypeScript ledger so batch ingest can confirm dated events. Confirm no longer burns the opening focus, recap uses server date labels, and the Agent sees indistinguishable width instead of a fake unique minute.
Co-authored-by: Cursor <cursoragent@cursor.com>
Web answers were thinner than a local Agent calling yinduzhanxing-skill:
theme-subset vargas, no visible audit table, and a prompt that dropped the
invocation contract. Bind the commercial method, compute D1–D60 plus Western
layers, and deliver the same Full-Spectrum checklist.
Co-authored-by: Cursor <cursoragent@cursor.com>
Activating the skill answered with the entrypoint plus a flat listing of every
file in the package, and nothing carried over between requests: the agent is
rebuilt per request, no thread memory is configured, and the replayed history is
plain question/answer text. So the model re-activated on every turn and paid for
that listing every time, twice more whenever a retry opened a fresh model loop.
The method is now read from the hash-verified package and bound into the
instructions, and the activation tools are withdrawn while skill_read stays. The
agents also stopped loading from the working-tree view, whose reference listing
no hash covered - only SKILL.md was compared - so what the model sees is finally
what the registry pinned.
Withdrawing an activation the model could forget also removes the failure it
mostly produced: the contract no longer waits on a model action for method, and
the no-birth-time path has no contract left to repair.
Measured against this package: activation 118,352 bytes, bound method 47,289.
Co-authored-by: Cursor <cursoragent@cursor.com>
The evidence field is optional, so reading the mahadasha through it yields
undefined as well as null, which the lookup did not accept. staging's typecheck
was failing on this before this branch touched it.
Co-authored-by: Cursor <cursoragent@cursor.com>
Activating the skill returned 129,651 bytes, of which 99KB was a flat list of
1,592 undifferentiated file paths against 30KB of actual method. The one line
telling the model to open the strict-workflow router sat inside that method,
so no reference was ever opened and every answer was composed from the model's
own background knowledge over server evidence.
The route is already decided server-side and the skill already states which
checklist each route requires, so the selection needs no model turn: read the
mandated sections from the hash-pinned package and hand them to the model with
the evidence they apply to. A route the router declares no checklist for is
reported as such rather than filled in with another route's.
The receipt now reports delivered sections separately from model-initiated
reads, because only one of those is under the model's control.
Co-authored-by: Cursor <cursoragent@cursor.com>
Homepage visits were failing closed whenever the 30s generation missed. Return an evidence-backed card immediately, polish in the background, and remember the day's card locally.
Co-authored-by: Cursor <cursoragent@cursor.com>
The model packet read chart.modules.dasha_boundaries, a key the engine never
wrote, so no answer ever had sub-period boundaries while the receipt still
reported precise timing as allowed. The server now cuts the running mahadasha
into antardashas out of the periods the packet already shows, exposes them as
their own evidence section, and precise timing requires that section.
A run whose calculation succeeded and whose model then wrote nothing was
answered with a fixed apology and billed as completed. It now asks once more
against the cached calculation, and fails with empty_answer—no charge—if that
attempt is silent too.
Co-authored-by: Cursor <cursoragent@cursor.com>
A staging run answered "which year?" with nothing but the model explaining that
its own tool calls had failed. Two causes, one upstream of the other.
The domains parameter accepted any string, so it stated no vocabulary at all
while the skill's methodology names strict-workflow checklists the tool has
never accepted. The model followed the skill, the schema took it, and the call
died in the registry two steps later. Enumerating the accepted values puts the
vocabulary where the model reads it. Aliases stay in the enum: they are a
promise the instructions make and a test pins.
Mastra reports an input-schema rejection by resolving with a validation
envelope rather than throwing, so enumerating alone would have turned those
rejections into tool.completed for calls that never ran. The stream now reads
that envelope for what it is.
Text written before the runtime contract is ready was held rather than dropped,
so a later successful call released the model's narration of its own failures as
the entire visible answer. Dropping it means a run that cannot answer says so.
Co-authored-by: Cursor <cursoragent@cursor.com>
Report pages now scroll inside the chat shell lock, and admin product save forks a draft or retires a published plan instead of rejecting with a generic constraint error.
Co-authored-by: Cursor <cursoragent@cursor.com>
