Request:
- Add a recent one-month listed IPO review to the latest candidate report.
- Make this review a standing analyst skill requirement for future broad IPO candidate reports.
Changes:
- Added a 2026-05-22 to 2026-06-22 IPO review table covering structure, fundamentals, T1 allotment demand, D1 performance, and PM lessons.
- Mapped recent T1/D1 outcomes back to the current candidate batch and flagged the 00901 D1 price data gap.
- Added a Recent Listing Review Overlay section to the project analyst skill.
Verification:
- Ran git diff --check.
- Recomputed the recent review sample from analysis_model_v0_dataset.csv: 11 IPOs, 10 D1 observations, 9 nonnegative D1 returns, 1 negative D1 return, average D1 return 91.2%.
Request:
- Update the current HK IPO candidates after subscription multiples changed again.
- Refresh the candidate ranking and defensive risk/reward view.
Changes:
- Archived the 2026-06-22T13:57:38Z VBKR/Jieli T0.95 market-heat snapshot.
- Re-archived the HKEX current new-listing page and rebuilt snapshots/model dataset.
- Updated the June 22 candidates report with the latest heat multiples, ranking, execution guidance, and defensive score table.
- Refreshed the model report analysis timestamp.
Verification:
- Ran git diff --check and git diff --cached --check.
- Confirmed SQLite PRAGMA integrity_check = ok.
- Parsed changed CSV snapshots and confirmed 13 latest T0_95_final_heat rows.
- Checked the current candidate ranking against data/snapshots/analysis_model_v0_dataset.csv.
Request:
- Analyze the current HK IPO batch from break probability, capital efficiency, and risk/reward.
- Test whether names such as 01688 deserve a higher defensive ranking than their heat score implies.
Changes:
- Added rules/ipo_break_risk_reward_v0.yaml as an experimental defensive overlay.
- Split the new framework into break protection, capital efficiency, and upside optionality.
- Added historical break-rate calibration anchors from analysis_model_v0_dataset.csv.
- Updated the 2026-06-22 IPO report with a defensive risk/reward ranking and dual execution guidance.
- Logged the rule change and its caveats.
Verification:
- Ran git diff --check and git diff --cached --check.
- Parsed the new YAML file with PyYAML.
- Recomputed key historical break-rate anchors from the current model dataset.
Request:
- Compare fundamentals for 01688 and 01956 against the current HK IPO candidate batch.
- Add the comparison to the 2026-06-22 IPO report.
Changes:
- Added a fundamentals section explaining 01688 as a mature cash-generative manufacturing platform.
- Added a fundamentals section explaining 01956 as a high-growth AI services IPO that remains loss-making.
- Added a 13-company comparison table and clarified how fundamentals should affect the heat-adjusted subscription ranking.
Verification:
- Ran git diff --check for Markdown formatting and whitespace.
Request:
- Update the latest Hong Kong IPO candidate list and rescore it based on subscription multiples.
Changes:
- Archived the 2026-06-22 HKEX Main Board New Listing Information page, adding 02697, 03952, 06715, and 06915 to the current candidate set.
- Archived and extracted the four new prospectuses, refreshed current HKEX document facts, and rebuilt the v0 analysis dataset to 311 rows.
- Archived a 2026-06-22T08:55:00Z VBKR/Jieli market-heat snapshot and wrote only still-actionable T0.95 rows to avoid look-ahead leakage for already-closed IPOs.
- Improved prospectus date parsing for split weekday/month text, glued noon/commence phrases, and current new-listing expected listing-date updates.
- Added a Chinese 2026-06-22 latest IPO report ranking candidates after the subscription-multiple overlay.
Verification:
- Ran py_compile for archive_hkex_documents.py, archive_t0_5_market_heat.py, archive_hkex_current_new_listings.py, and build_analysis_dataset.py.
- Re-ran HKEX current-page seeding, document archiving, market-heat archiving, and analysis dataset build as of 2026-06-22T08:55:00Z.
- Ran git diff --check and git diff --cached --check.
- Ran SQLite integrity_check and foreign_key_check.
- Verified source_refs paths, file existence, and SHA-256 hashes.
Next useful context:
- 01956 is the only current candidate with both strong T0 structure and >100x actionable heat in this snapshot.
- Recheck 03952 and 06715 near the 2026-06-25 cutoff; their structure is strong but 2026-06-22 heat is below 10x.
- Official T1 allotment facts for 06067 and 06132 were still unavailable at this archive timestamp.
Request:
- Use the analyst workflow to analyze the latest Hong Kong IPOs, connect their source data, and produce a current report.
Changes:
- Added a current HKEX New Listing Information page seeder that archives the official page, seeds visible tickers, and records source_refs.
- Archived current HKEX prospectus and allotment-result sources for the 16 visible Main Board candidates and extracted their text.
- Extended prospectus parsing for offer price, derived gross proceeds, HDR offerings, and listing-date text extracted with split characters.
- Rebuilt the analysis dataset and added a Chinese 2026-06-21 latest IPO report separating live T0 watchlist names from past-cutoff T1/D1 candidates.
Verification:
- Ran py_compile for update_recent_ipo_list.py, archive_hkex_current_new_listings.py, archive_hkex_documents.py, and build_analysis_dataset.py.
- Re-ran HKEX current page seeding, document archiving, and analysis dataset build as of 2026-06-21T08:44:59Z.
- Ran git diff --check and git diff --cached --check.
- Ran SQLite integrity_check and foreign_key_check.
- Verified source_refs paths, file existence, SHA-256 hashes, and report source paths.
Next useful context:
- Capture T0.95 market heat before the 2026-06-23 and 2026-06-24 order cutoffs before converting the new watchlist into execution calls.
- Treat 02667 as a stale/special HKEX page item until a fresh June timetable or official result appears.
Request:
- Refresh today's HK IPO analyst view for the current candidate set.
Changes:
- Refreshed the 2026 HKEX new-listing report archive and synchronized source hashes across 2026 report-backed rows.
- Re-ran HKEX document archiving for 01392, 06067, 06132, 02335, and 06106; no official T1 allotment facts were available at 2026-06-18T08:16:33Z.
- Rebuilt the v0 analysis dataset and model report as of 2026-06-18T08:16:33Z.
- Added a Chinese 2026-06-18 cross-candidate analysis update that treats 06106/02335 as past standard subscription cutoff, flags 01392 for a post-23:00 HKT T1 refresh, and lists newly visible HKEX page tickers as pending archivist work.
Verification:
- Ran scripts/update_recent_ipo_list.py for 2026-01-01 through 2026-06-18.
- Ran scripts/archive_hkex_documents.py for 01392,06067,06132,02335,06106.
- Ran scripts/build_analysis_dataset.py as of 2026-06-18T08:16:33Z.
- Ran git diff --check and git diff --cached --check.
- Ran py_compile for the touched workflow scripts.
- Ran SQLite integrity_check and foreign_key_check.
- Verified durable report paths exist and source_refs have no missing paths or hash mismatches.
Next useful context:
- Re-run archivist after 2026-06-18T15:00:00Z to capture 01392 allotment results if published.
- Add a seed/archive path for current HKEX New Listing Information page candidates before scoring 02672, 01191, 09637, 09630, 06228, 03661, 01956, 02272, 01688, and 02667.
Request:
- Use the project analyst workflow to analyze the latest upcoming Hong Kong IPO candidates.
Changes:
- Refreshed recent HK IPO target coverage through 2026-06-17 and archived current HKEX source updates.
- Archived 06675 allotment results and D1 Yahoo price performance for boundary-case review.
- Archived a 2026-06-17 T0.5 VBKR/Jieli market-heat snapshot for still-actionable 02335 and 06106.
- Rebuilt the v0 analysis dataset and snapshots at 2026-06-17T08:20:00Z.
- Added a Chinese horizontal analyst report ranking 06106, 02335, 06132, 06067, 01392, with 06675 separated as a T1/D1 review sample.
Verification:
- Ran SQLite PRAGMA integrity_check and foreign_key_check.
- Ran git diff --check and git diff --cached --check.
- Confirmed report source paths exist.
Next useful context:
- 06106 is the top still-actionable T0.5 candidate at this as-of time.
- 02335 needs another pre-deadline heat sample before a stronger call.
- 01392, 06067, and 06132 are now mainly waiting for T1 official allotment results.
Request:
- Reflect that near-final market heat can be used when the user can still place an IPO order at T0.95.
Changes:
- Added T0_95_final_heat as a separate analyst decision stage with executability and no-leakage rules.
- Added an experimental T0.95 rule overlay for late-order heat scoring and calibration discipline.
- Updated archivist guidance and the market-heat archiver so snapshots can be explicitly stored as T0_95_final_heat.
- Added market_heat_stage to the analysis dataset and refreshed the model report to show T0.95 coverage separately.
Verification:
- Ran py_compile for the modified scripts.
- Checked archive_t0_5_market_heat.py --help for the new --stage option.
- Rebuilt data/snapshots/analysis_model_v0_dataset.csv and reports/2026-06-15_analysis_model_v0.md.
- Ran git diff --check.
Next useful context:
- Current archived heat rows remain T0_5_market_heat only; there are no true T0.95 rows yet.
- external_ipo_history.public_oversubscription_times is still calibration-only unless a comparable value is archived before the executable order cutoff.
Request:
- Summarize recent three-year HK IPO T0.5 coverage and statistics.
Changes:
- Added a Chinese Markdown report that separates true subscription-period T0.5 snapshots from external final public oversubscription history.
- Reported current true T0.5 coverage, active future T0.5 rows, final heat proxy buckets, and top recent high-heat IPOs.
- Documented model implications for short T2/D1 exits and future T0.5 sampling.
Verification:
- Ran git diff --check.
- Reconciled counts against data/hk_ipo.sqlite with read-only SQLite queries.
Next useful context:
- True historical T0.5 coverage is currently zero for listed IPOs in 2023-06-15 to 2026-06-15 because T0.5 snapshots only started on 2026-06-15.
- external_ipo_history.public_oversubscription_times is a post-hoc heat proxy, not an original T0.5 input.
Request:
- Add historical data around T0.5 margin heat and rebuild the model.
Changes:
- Add external_ipo_history to store third-party historical IPO records separately from true T0.5 market-heat snapshots.
- Add scripts/archive_ipohk_history.py to archive ipohk structured listed IPO history.
- Archive 807 ipohk rows, including final oversubscription, one-lot win rate, grey-market return, and first-day return where available.
- Extend the v0 analysis dataset with true T0.5 market-heat columns and separate external final-heat columns.
- Rebuild reports/2026-06-15_analysis_model_v0.md with T0.5 coverage and external final-heat calibration.
- Add a Chinese report explaining why historical final oversubscription cannot be treated as T0.5 margin snapshots.
- Update analyst and archivist skills to keep T0.5 and external final history separate.
Verification:
- .venv/bin/python -m py_compile scripts/build_analysis_dataset.py scripts/archive_ipohk_history.py scripts/archive_t0_5_market_heat.py
- .venv/bin/python scripts/build_analysis_dataset.py --as-of 2026-06-15T19:20:00Z
- Python sqlite3 PRAGMA integrity_check returned ok and foreign_key_check returned zero rows.
- Confirmed 807 external_ipo_history rows, 792 rows with external final oversubscription, 5 true T0.5 market-heat rows, and 297 analysis dataset rows.
- git diff --cached --check
Next useful context:
- True T0.5 historical backtesting still requires ongoing frozen margin-heat snapshots during each IPO subscription window.
Request:
- Test whether subscription-period T0.5 market heat data can be captured and incorporated into IPO analysis.
Changes:
- Add an ipo_market_heat table for non-official market-heat snapshots.
- Add a VBKR/Jieli archive script for expected margin subscription multiples.
- Archive the 2026-06-15T18:40:00Z heat snapshot for 01392, 02335, 06067, 06106, and 06132.
- Add an experimental T0.5 overlay rule file and a Chinese cross-IPO trial report.
- Update archivist and analyst skills so T0.5 remains separate from official T1 allotment demand.
Verification:
- .venv/bin/python -m py_compile scripts/archive_t0_5_market_heat.py scripts/build_analysis_dataset.py scripts/update_sync_state.py
- Python sqlite3 PRAGMA integrity_check returned ok and foreign_key_check returned zero rows.
- Confirmed 5 ipo_market_heat rows and 5 t0_5_market_heat source_refs for the frozen snapshot.
- git diff --cached --check
Next useful context:
- T0.5 data is non-official and should be resampled during the subscription window, then compared against T1 official allotment results.
Request:
- Combine the currently selected T0 IPO reports into one cross-sectional analysis report.
Changes:
- Add a Chinese horizontal T0 report comparing 01392, 02335, 06067, 06106, and 06132.
- Rank the selected IPOs by the current T0 model and short-exit discipline focused on T2/D1 selling.
- Backfill 02335's Chinese company name from its Chinese HKEX prospectus and archive the source PDF plus extracted text.
- Refresh the v0 analysis dataset and sync-state snapshots at 2026-06-15T18:20:00Z.
Verification:
- .venv/bin/python -m py_compile scripts/build_analysis_dataset.py scripts/generate_ipo_report.py scripts/extract_pdf_text.py scripts/update_sync_state.py
- Python sqlite3 PRAGMA integrity_check returned ok and foreign_key_check returned zero rows.
- Confirmed 02335 Chinese source_ref, extracted text manifest row, and selected horizontal report content.
- git diff --cached --check
Next useful context:
- Untracked PDF exports of individual reports and the horizontal report were left out of this focused commit.
Request:
- Update the selected analyst reports so stock/company names include Chinese names and use Chinese names first.
Changes:
- Updated the selected T0 reports for 01392, 06067, 06106, and 06132 to show Chinese company names in the title and summary, with English names in parentheses.
- Added company_name_zh to the analyst dataset so report generation has access to Chinese names.
- Updated the report generator to prefer Chinese company names and fall back to English names only when Chinese names are unavailable.
- Filled Chinese company names for the selected tickers in ipo_master and refreshed snapshots.
Verification:
- Compiled build_analysis_dataset.py and generate_ipo_report.py.
- Ran generator dry-runs for 06132 and 01392 to confirm Chinese-first output.
- Ran SQLite integrity_check and foreign_key_check.
- Ran git diff --check.
Next useful context:
- Future generated analyst reports now use company_name_zh first when available.
Request:
- Generate an analyst report for HK IPO ticker 02335.
Changes:
- Archived the official HKEXnews 02335 prospectus PDF and extracted text under project-relative data paths.
- Seeded 02335 T0 prospectus facts, source references, sync state, and analysis snapshots.
- Generated reports/2026-06-15_02335_T0_prospectus_analysis.md in Simplified Chinese with concrete T0/T1/T2/D1 dates and short-exit T2/D1 discipline.
- Made PDF text extraction tolerant of invalid Unicode surrogate characters emitted by pypdf.
Verification:
- Compiled archive_hkex_documents.py, generate_ipo_report.py, build_analysis_dataset.py, extract_pdf_text.py, and update_sync_state.py.
- Ran SQLite integrity_check and foreign_key_check.
- Verified the archived 02335 PDF hash, extracted-text manifest row, and analysis dataset row.
- Ran git diff --check.
Next useful context:
- 02335 is currently T0_prospectus; T1_allotment is pending for 2026-06-23.
Request:
- Generate an analyst report for HK IPO ticker 06067.
Changes:
- Archived the official HKEXnews 06067 prospectus PDF and extracted text under project-relative data paths.
- Seeded 06067 T0 prospectus facts, source references, sync state, and analysis snapshots.
- Generated reports/2026-06-15_06067_T0_prospectus_analysis.md in Simplified Chinese with concrete T0/T1/T2/D1 dates and short-exit T2/D1 discipline.
- Updated the HKEX document archiver so over-allotment shares are only recorded when the prospectus supports them, with explicit no-option cases stored as zero.
Verification:
- Compiled archive_hkex_documents.py, generate_ipo_report.py, build_analysis_dataset.py, extract_pdf_text.py, and update_sync_state.py.
- Ran SQLite integrity_check and foreign_key_check.
- Verified the archived 06067 PDF hash, extracted-text manifest row, and analysis dataset row.
- Ran git diff --check.
Next useful context:
- 06067 is currently T0_prospectus; T1_allotment is pending for 2026-06-22.
Request:
- Analyze HK IPO ticker 01392 with the analyst skill.
- Preserve the in-flight 06132 archive/report work already created for the prior request.
Changes:
- Archived official HKEX prospectus PDFs and extracted text for 01392 and 06132.
- Seeded structured T0 facts into the SQLite archive and refreshed CSV snapshots and sync state.
- Rebuilt the v0 analysis dataset and model calibration report.
- Generated Simplified Chinese T0 prospectus-stage analyst reports for 01392 and 06132.
- Adjusted report stage calendars so T2 uses the previous business day before D1 when listing is separated from allocation by a weekend.
Verification:
- Compiled modified Python scripts with in-memory syntax checks.
- Ran SQLite quick_check and foreign_key_check.
- Confirmed DB row counts match CSV snapshots for key tables.
- Verified 01392/06132 source paths are repo-relative, raw files exist, hashes match, and PDF text manifest rows are ok.
- Ran git diff --cached --check.
Next useful context:
- 01392 T1 is due on 2026-06-18; rerun analyst after allotment results are archived.
- 06132 T1 is due on 2026-06-22; rerun analyst after allotment results are archived.
Request:
- Make analyst reports Chinese by default and record the rule in the analyst skill.
Changes:
- Add a Simplified Chinese default-language rule to the analyst skill.
- Update the single-IPO report generator to emit Chinese Markdown sections, labels, actions, risks, triggers, and exit plans.
- Preserve ticker symbols, stage codes, rule ids, score buckets, and source paths as machine-readable identifiers.
- Regenerate the 06106 T0 report in Chinese.
- Document the Chinese report default in README and the rule change log.
Verification:
- Ran py_compile for scripts/generate_ipo_report.py.
- Generated a 06106 dry-run report and checked Chinese section headings.
- Regenerated reports/2026-06-15_06106_T0_prospectus_analysis.md.
- Ran git diff --check.
Next useful context:
- Future analyst prediction and review reports should be written in Simplified Chinese unless the user explicitly requests another language.
Request:
- Include the concrete T0, T1, T2, and D1 dates in every analyst report.
Changes:
- Add a Stage Calendar section to the single-IPO report generator.
- Require analyst reports to include ticker-specific T0 subscription window, T1 allotment-result date, T2 grey-market date/window, and D1 listing date.
- Update the 06106 T0 report with its concrete stage dates.
- Document the requirement in the analyst skill, README, and rule change log.
Verification:
- Ran py_compile for scripts/generate_ipo_report.py.
- Generated a 06106 dry-run report and checked the stage calendar.
- Ran git diff --check.
Next useful context:
- For 06106, T0 is 2026-06-15 to 2026-06-18, T1/T2 is 2026-06-23, and D1 is 2026-06-24.
Request:
- Emphasize that the analyst model is for selling allocated IPO shares in T2 grey market or on D1, not for long-term holding.
Changes:
- Add explicit T2/D1 sell discipline to the analyst skill.
- Update ipo_score_v0 targets and holding policy so D1 sell return is primary and T2 is the intended extension when reliable grey-market data exists.
- Clarify that D5/D20/D60 are review labels only, not planned holding targets.
- Update the model report, single-ticker report generator, README, and the 06106 report language to reflect the short-exit horizon.
Verification:
- Rebuilt the model report with the same dataset timestamp and confirmed the analysis dataset did not change.
- Ran py_compile for build_analysis_dataset.py and generate_ipo_report.py.
- Generated a 06106 dry-run report showing T2/D1 exit discipline.
- Ran git diff --check.
Next useful context:
- T2 is still disabled in v0 until archivist approves a reliable grey-market data source; D1 remains the live modeled sell label.
Request:
- Use the analyst skill to analyze upcoming IPO 06106 and generate a Markdown report.
Changes:
- Add a stage-safe T0_prospectus analyst report for 06106.
- Record the v0 score, calibrated historical probability, key T0 positives, risks, triggers, and source path.
Verification:
- Confirmed 06106 has no structured T1 demand yet, so the report is T0_prospectus.
- Reviewed the report for stage safety and repo-relative source paths.
- Ran git diff --check.
Next useful context:
- Re-run analyst after 06106 allotment results are archived around 2026-06-23 to generate a T1_allotment report.
Request:
- Let the analyst skill generate a Markdown report directly when a new IPO ticker is provided.
Changes:
- Add scripts/generate_ipo_report.py for stage-safe single-ticker reports from the v0 analysis dataset.
- Auto-select T1 reports when structured allotment demand exists and otherwise use T0 prospectus-stage reporting.
- Keep post-listing D1/D5/D20/D60 outcomes out of prediction reports while using historical buckets for calibration.
- Document the workflow in the analyst skill and README.
Verification:
- Ran py_compile for scripts/generate_ipo_report.py.
- Generated stdout dry-run reports for 06106 and 06658.
- Wrote temporary Markdown reports under /tmp for output-path validation.
- Ran git diff --check.
Next useful context:
- Before generating a report for a ticker absent from the analysis dataset, run archivist updates and rebuild scripts/build_analysis_dataset.py.
Request:
- Re-analyze the IPO model using the updated historical archive after T1 demand backfill.
Changes:
- Regenerate the v0 analysis dataset from the current SQLite archive.
- Refresh the v0 calibration report with expanded T1 coverage and new empirical bucket rates.
- Update the report template to show pending T1 rows and field-level blanks.
- Clarify v0 limitations and record why the score formula stays unchanged for this refresh.
Verification:
- Ran scripts/build_analysis_dataset.py against data/hk_ipo.sqlite.
- Ran py_compile for scripts/build_analysis_dataset.py.
- Checked dataset row count, T1 demand coverage, source-only T1 gaps, and repo-relative paths.
- Ran git diff --check.
Next useful context:
- T1 structured coverage is now 291 rows, with 06106 and 06675 still pending_not_due.
- The high-conviction T1 bucket remains differentiated, but middle and low buckets are still not monotonic enough for a v1 rule change.
Request:
- Use archivist to close the 137 T1 ipo_demand source-only gaps using extracted PDF text.
Changes:
- Add an incremental T1 demand text backfill script.
- Parse existing allotment-result extracted text into ipo_demand.
- Archive linked Summary PDFs from old HKEX HTML allotment-result pages.
- Correct allotment-result selection to prefer primary result announcements over clarification or supplemental notices.
- Add robust line-aware allotment parsing and document the workflow in archivist and README.
- Record the backfill result in a report.
Execution:
- Selected 137 source-only T1 demand gaps.
- Wrote 137 ipo_demand rows, increasing ipo_demand from 154 to 291 rows.
- Archived 38 new HKEX allotment-result PDFs and extracted their text.
- Confirmed an incremental rerun selects 0 gaps and writes 0 rows.
Verification:
- Ran git diff --cached --check.
- Ran py_compile for archive_hkex_documents.py and backfill_t1_demand_from_text.py.
- Checked SQLite integrity and foreign keys.
- Confirmed DB row counts match CSV snapshots.
- Verified no T1 complete row is missing ipo_demand.
- Verified source_refs paths/files/hashes and PDF extracted-text manifest hashes.
Next useful context:
- T1 demand structure is complete for listed rows; 06106 and 06675 remain pending_not_due.
- T2 grey-market and due price-performance gaps remain separate archivist priorities.
- Analyst output should be regenerated before using the new T1 demand facts for scoring.
Request:
- Use the audit skill to check historical data completeness and self-correct the audit criteria after the missed PDF extracted-text gap.
Changes:
- Add a mandatory derived-evidence checklist to the audit skill.
- Require broad historical audits to reconcile PDF source_refs, extracted text files, manifest rows, and hashes.
- Add a historical data completeness audit report for the current archive.
Findings:
- Source integrity and PDF extracted-text completeness now pass.
- Full historical completeness still fails due to incomplete structured T1 demand, unresolved T2 grey-market data, open due price-performance tasks, and missing context fields.
Verification:
- Ran SQLite integrity, foreign-key, source hash, snapshot, PDF manifest, extracted-text hash, stage coverage, and analysis-dataset checks.
- Ran scripts/extract_pdf_text.py and confirmed 557 PDF sources were skipped unchanged with 557 manifest rows.
- Ran git diff --check.
Request:
- Add extracted PDF text generation to the archivist workflow as a standard step.
Changes:
- Run PDF text extraction automatically for newly archived HKEX PDF sources.
- Make the PDF text extractor incremental and manifest-preserving.
- Document extracted-text handling in the archivist skill and README.
- Mark generated extracted text as no-diff data evidence.
- Backfill extracted text for all archived PDF source references.
Verification:
- Ran git diff --cached --check.
- Ran .venv/bin/python -m py_compile scripts/extract_pdf_text.py scripts/archive_hkex_documents.py.
- Ran full PDF extraction, then confirmed an incremental rerun skips unchanged files.
- Verified 557 PDF source_refs, 557 manifest rows, all status ok, and zero missing text/hash/path issues.
Next useful context:
- HKEX HTML notices and Yahoo JSON market data remain under data/raw and are not expected in data/extracted_text.
Request:
- Use the analyst skill to digest downloaded IPO archive data and start building an analysis model.
Changes:
- Add ipo_score_v0 as the first transparent stage-safe scoring rule set.
- Add build_analysis_dataset.py to derive model features, scores, decision bands, and empirical D1 calibration from SQLite.
- Generate analysis_model_v0_dataset.csv with 293 scored IPO rows and archived source paths.
- Add a model calibration report documenting coverage, T0/T1 bucket performance, usage, and known gaps.
- Record the initial model entry in the rule change log and document the command in README.
Verification:
- Ran py_compile for scripts/build_analysis_dataset.py.
- Regenerated the analysis dataset and report with as-of 2026-06-15T13:00:00Z.
- Checked CSV row count, source path coverage, and repo-relative path hygiene.
- Ran git diff --cached --check.
Next useful context:
- v0 should be treated as a transparent baseline, with T1 high-score calibration strongest and middle buckets still non-monotonic.
- T2 is excluded until a reliable grey-market source is approved.
Request:
- Rework archivist handling for stubborn T0/T1 HKEX document gaps and unresolved T2 grey-market gaps.
Changes:
- Query HKEXnews titleSearchServlet with IPO-date windows instead of only the latest title-search page.
- Recognize SHARE OFFER listing documents and archive official HTML allotment-result notices when no PDF is published.
- Mark source-only allotment completion clearly when structured demand parsing is not yet covered.
- Add a reusable grey-market gap marker and archivist source policy for T2 data.
- Archive newly discovered HKEX raw sources, update SQLite, and refresh CSV snapshots.
- Treat raw evidence files as binary in Git attributes.
Verification:
- Ran py_compile for archive_hkex_documents.py, update_sync_state.py, and mark_grey_market_gaps.py.
- Ran HKEX document archive backfill and grey-market gap marker.
- Checked SQLite integrity, foreign keys, source paths, source hashes, and DB-vs-snapshot row counts.
- Ran git diff --cached --check after marking raw archives binary.
Next useful context:
- T0 is now complete for 293 tickers.
- T1 has 291 complete and 2 pending_not_due tickers.
- T2 has 291 blocked gaps pending an approved grey-market source strategy.
Request:
- Adjust archivist after the audit findings and update historical data.
Changes:
- Teach the archivist skill to close audit-discovered gaps in priority order.
- Add scripts/archive_price_performance.py for due D1/D5/D20/D60 price-performance backfills.
- Document the price-performance backfill command in README.
- Archive raw Yahoo Finance chart responses under repo-relative data/raw/{ticker}/ paths.
- Populate price_performance with D1/D5/D20/D60 checkpoints and refresh source_refs, sync_runs, sync_tasks, and ticker_sync_state snapshots.
Execution:
- Ran .venv/bin/python scripts/archive_price_performance.py --as-of 2026-06-15T10:00:00Z.
- Selected 291 due price-performance tickers.
- Archived 273 price-history sources and wrote 1063 price-performance rows.
- Re-ran .venv/bin/python scripts/archive_hkex_documents.py --as-of 2026-06-15T10:05:00Z for the remaining open T0/T1 tasks; no additional completed T0/T1 stages resulted.
Verification:
- Compiled the new price-performance script.
- Ran git diff --check.
- Checked SQLite integrity and foreign keys.
- Confirmed database row counts match CSV snapshots.
- Verified all 979 source_refs use valid repo-relative paths, have files, have hashes, and SHA256 hashes match.
- Confirmed no generated Python caches or SQLite transient files remain.
Next useful context:
- price_performance now has 1063 rows: D1 273, D5 272, D20 267, D60 251.
- Remaining due price-performance gaps are 18 tickers where Yahoo history was unavailable or the request failed.
- T0/T1 gaps remain at T0 93 and T1 77; T2 grey-market remains unresolved pending a reproducible source strategy.
Request:
- Add a project-local audit skill for checking IPO data completeness, sufficiency, and analysis self-consistency.
Changes:
- Create .codex/skills/audit/SKILL.md.
- Define audit scope across source integrity, stage data completeness, data sufficiency, and reasoning consistency.
- Separate responsibilities from archivist fact updates and analyst investment conclusions.
Verification:
- Reviewed the new skill body.
- Ran git diff --check.
- Confirmed the project-local skill list includes archivist, analyst, and audit.
Request:
- Remove wording that could imply batched HKEX document backfills.
Changes:
- Replace the remaining progressive-fill phrase in README with direct full-run wording.
Verification:
- Confirmed README, archivist skill, and archiver script contain no batch, small-batch, --limit 5, progressively, or 分批 wording.
- Ran git diff --check.
Request:
- Remove small-batch guidance and execute the HKEX document archiver across all open T0/T1 sync tasks in one run.
Changes:
- Make archive_hkex_documents.py process every open T0/T1 ticker by default when --limit is omitted.
- Add per-ticker progress output and keep full refreshes moving if one ticker fails.
- Suppress noisy pypdf warnings during large official document extraction.
- Update archivist and README instructions to show the full-run command without batch notes.
- Archive official HKEXnews prospectus and allotment-results PDFs under repo-relative data/raw paths.
- Refresh hk_ipo.sqlite and CSV snapshots for parsed T0/T1 fields, source_refs, sync_runs, sync_tasks, and ticker_sync_state.
Execution:
- Ran .venv/bin/python scripts/archive_hkex_documents.py --as-of 2026-06-15T09:00:00Z.
- Selected 284 open T0/T1 tickers, processed 210 tickers, and archived 398 source files.
- Left 74 tickers as missing target docs because title search did not return target prospectus/allotment documents for this pass.
Verification:
- Parsed archivist scripts with Python ast.
- Confirmed README, archivist skill, and archiver script no longer contain batch guidance.
- Ran git diff --check.
- Checked SQLite integrity and DB/snapshot row counts.
- Verified 706 source_refs use relative local paths, all files exist, and SHA256 hashes match.
Next useful context:
- Current source_refs count is 706 and ipo_demand count is 134.
- Sync ledger now reports 414 complete, 1595 pending_due, and 42 pending_not_due states.
Request:
Start progressively filling detailed information for recent HK IPO targets.
Changes:
- Add scripts/archive_hkex_documents.py to map tickers to HKEXnews stock IDs, select official prospectus and allotment-results PDFs, archive them under data/raw/{ticker}, parse high-confidence T0/T1 facts, export snapshots, and refresh sync state.
- Document the small-batch HKEX document backfill workflow in README.md and the archivist skill.
- Archive prospectus and allotment-results PDFs for 00901, 01081, 01779, 02290, 02553, and 03388.
- Fill T0 details including application dates, expected allotment date, board lot, minimum subscription amount, and offer-share counts for the six tickers.
- Fill T1 allotment-demand details including valid/successful applications, public subscription level, international placees, international subscription level, and final offer-share allocations.
- Refresh source_refs, ipo_master, offering_terms, ipo_demand, ticker_sync_state, and sync_tasks snapshots.
Verification:
- Ran archive_hkex_documents.py in a first small batch and re-ran corrected tickers after parser hardening.
- Parsed project Python scripts with ast.parse.
- Checked SQLite integrity and DB-to-snapshot row counts.
- Verified source_refs paths are repo-relative, source files exist, and SHA-256 hashes match.
- Confirmed batch field completeness for the six processed tickers.
- Ran git diff --check and git diff --cached --check.
- Checked for Python cache and SQLite transient files.
Next useful context:
- This batch added about 55MB of official HKEXnews PDFs.
- Sync state now has 16 complete stages, 1993 pending_due stages, and 42 pending_not_due stages.
- Continue with small --limit batches because HKEXnews title search can include historical or postponed offering documents for the same stock code.
Request:
Use the project archivist workflow to update IPO target coverage for the most recent three-year window.
Changes:
- Add scripts/update_recent_ipo_list.py to discover HKEXnews annual new listing reports, archive XLSX sources, parse subscription-relevant IPO rows, and update SQLite plus snapshots.
- Add new_listing_report_entries to preserve annual report row-level evidence.
- Archive 2023-2026 Main Board new listing reports and 2024-2026 GEM new listing reports.
- Seed 290 report-backed IPO targets for 2023-06-15 through 2026-06-15, skipping 10 non-IPO rows without numeric offer prices.
- Refresh ipo_master, missing offering_terms fields, source_refs, ticker_sync_state, and sync_tasks.
- Add openpyxl as the XLSX parser dependency and document the archivist refresh flow.
- Limit sync summary output while keeping the full queue in SQLite and CSV snapshots.
Verification:
- Ran update_recent_ipo_list.py for 2023-06-15 to 2026-06-15 with as-of 2026-06-15T07:30:00Z.
- Parsed project Python scripts with ast.parse.
- Checked SQLite integrity and DB-to-snapshot row counts.
- Verified source_refs paths are repo-relative, files exist, and SHA-256 hashes match.
- Ran git diff --check and git diff --cached --check.
- Checked for Python cache and SQLite transient files.
Next useful context:
- ipo_master now has 293 tickers; new_listing_report_entries has 290 report-backed targets.
- Current sync queue has 2005 open tasks and 42 waiting_until_due tasks for deeper per-ticker archival stages.
Request:
Add archivist support for remembering which IPO archive stages have already been synced and which stages should be updated next.
Changes:
- Add sync_runs, ticker_sync_state, sync_tasks, and price_performance tables to the archive schema.
- Add scripts/update_sync_state.py to derive per-ticker stage status and rebuild the next-sync task queue.
- Export the new sync-state tables as Git-friendly CSV snapshots.
- Document the incremental archive flow in the archivist skill and README.
Verification:
- Ran scripts/bootstrap_historical_data.py.
- Ran scripts/update_sync_state.py with a deterministic as-of timestamp.
- Checked SQLite integrity and DB-to-snapshot row counts with Python sqlite3.
- Parsed Python scripts with ast.parse.
- Ran git diff --check and checked for temporary SQLite/cache files.
Next useful context:
- Current derived queue has 2 open tasks for 06658 and 15 waiting_until_due tasks for future stages.
Request:
- Make AGENTS.md explicitly require automatic pushes to the remote after commits.
Changes:
- Add a Git Workflow rule to push the current branch to its configured upstream remote after a successful commit.
- Add a reporting rule for missing upstream configuration or failed pushes.
Verification:
- Reviewed the updated Git Workflow section.
- Ran git diff --check.
Request:
- Provide a way to install or develop a PDF extraction tool for archived HK IPO documents.
Changes:
- Add requirements.txt with pypdf as the lightweight PDF text extraction dependency.
- Add scripts/extract_pdf_text.py to extract text from PDF source_refs into repo-relative data/extracted_text files.
- Add extracted text outputs and an extracted_text_manifest snapshot for the six archived HKEXnews PDFs.
- Document the extraction workflow in README.md.
- Ignore .venv and keep generated SQLite/Python transient files out of git.
- Use extracted text to verify the 06106 full prospectus, update source_refs, remove the related data gap, and fill 06106 offering terms.
Verification:
- Installed python3.14-venv system support, created a local .venv, and installed requirements.txt.
- Re-ran scripts/bootstrap_historical_data.py and scripts/extract_pdf_text.py.
- Verified extracted text paths and hashes against data/snapshots/extracted_text_manifest.csv.
- Verified SQLite integrity and snapshot row counts.
- Ran git diff --cached --check and searched durable files for machine-specific absolute paths.
Request:
- Use the project archivist workflow to update historical IPO data.
Changes:
- Add an embedded SQLite archive at data/hk_ipo.sqlite.
- Add schema/hk_ipo.schema.sql and scripts/bootstrap_historical_data.py for reproducible archive generation.
- Archive HKEXnews source PDFs for 06658, 06675, and 06106 under repo-relative data/raw paths.
- Export Git-friendly snapshots for ipo_master, offering_terms, ipo_demand, source_refs, and data_gaps.
- Add .gitignore rules for Python cache and SQLite transient files.
Verification:
- Re-ran the bootstrap script successfully.
- Ran PRAGMA integrity_check on the SQLite database.
- Verified source_refs paths are repo-relative, files exist, and SHA-256 hashes match.
- Verified snapshot row counts match SQLite table counts.
- Ran git diff --check and searched generated durable files for machine-specific absolute paths.
Request:
- Delete the AGENTS.md rule that allowed pushing only when explicitly requested.
Changes:
- Remove the single Git Workflow bullet that restricted push behavior.
Verification:
- Reviewed the focused diff for AGENTS.md.
- Confirmed no remaining push-related text with rg.
Request:
- Write a README introducing the project.
Changes:
- Describe the HK IPO research feedback loop.
- Document the stage-based workflow, project-local skills, storage model, path rules, and Git discipline.
Verification:
- Reviewed README contents with sed.
- Ran rg for machine-specific absolute path patterns; none found.
- Ran git diff --check.
Request:
- Review the project agent instructions and make the Git workflow explicitly automatic.
- Commit the project-local modification into the repository.
Changes:
- Add AGENTS.md to the repo.
- Rename the Git workflow section to emphasize automatic commits.
- Clarify that completed repository changes should be committed before the final response.
- Clarify that related project-local files such as .codex skills, schema, scripts, snapshots, memos, and documentation belong in the focused commit.
Verification:
- Reviewed the updated Git Workflow section with sed.
- Confirmed the expected automatic-commit language with rg.
- Checked the staged diff includes only AGENTS.md.
Request:
- Keep the HK IPO workflow skills inside the repo so they travel with the project.
- Use concise names while preserving clear HK IPO scope and repo-relative path rules.
Changes:
- Add .codex/skills/archivist for source archiving, SQLite fact updates, hashes, and CSV snapshots.
- Add .codex/skills/analyst for T0/T1/T2 IPO decisions, prediction cards, reviews, and rule-change recommendations.
- Add agents/openai.yaml metadata for both skills.
Verification:
- Checked staged changes include only .codex skill files.
- Searched .codex for machine-specific absolute path patterns; none found.
Next useful context:
- AGENTS.md remains untracked and was not included in this commit.
geometrybase