b1ef6a85d6
fix(pitch-deck): dynamic VERSIONS-ISOLATION and Kernbotschaft from version data
...
Build pitch-deck / build-push-deploy (push) Successful in 1m17s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 35s
CI / test-python-voice (push) Successful in 36s
CI / test-bqas (push) Successful in 35s
Removes all hardcoded version-specific numbers from SYSTEM_PROMPT (200k,
40k/160k L-Bank split, 195 Kunden, 3.3 Mio, 9 MA). These are now generated
at runtime from the investor's assigned pitch_version_data: funding amount,
instrument, fm_scenarios name, and 2030 financials (customers, revenue,
employees).
loadPitchContext() now returns { contextString, meta } so the POST handler
can build correct isolation and Kernbotschaft strings for any version —
Wandeldarlehen 200k, 1 Mio, or any future scenario.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-23 22:44:41 +02:00
a795794f94
fix(pitch-deck): FAQ version-data priority override in chat system prompt
...
Build pitch-deck / build-push-deploy (push) Successful in 1m10s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 35s
CI / test-python-voice (push) Successful in 36s
CI / test-bqas (push) Has been cancelled
FAQ entries contain hardcoded financial numbers written for specific scenarios
(e.g. 470k Liquidität 2027, 200k/40k WD amounts). When an investor is on a
different version, those FAQ numbers would override the correct version-specific
context already injected from pitch_version_data.
Added an explicit priority instruction: version-specific Unternehmensdaten
always override FAQ content for any conflicting numbers.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-23 22:40:07 +02:00
4e27e05512
fix(pitch-deck): chat agent now uses investor's assigned version scenario
...
Build pitch-deck / build-push-deploy (push) Successful in 1m25s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 33s
CI / test-python-voice (push) Successful in 35s
CI / test-bqas (push) Successful in 31s
loadPitchContext() now accepts a versionId and loads data from
pitch_version_data instead of hardcoded base table queries, matching
the pattern used by /api/data and /api/financial-model.
Also pulls fp_liquiditaet yearly summaries (LIQUIDITÄT, Summe ERTRÄGE,
etc.) for the matching fp_scenario so the agent quotes the correct
finanzplan numbers. Falls back to base tables when no version is assigned.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-23 22:24:13 +02:00
71b6f8f181
fix(pitch-deck): fix Liquidität engine label mismatches + MilestonesSlide types
...
Build pitch-deck / build-push-deploy (push) Successful in 1m38s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 38s
CI / test-python-voice (push) Successful in 36s
CI / test-bqas (push) Successful in 33s
Engine now uses dynamic row_type-based summation instead of hardcoded label
strings that differed between scenarios (e.g. 'Summe ERTRÄGE' vs
'Summe EINZAHLUNGEN'), fixing stale 9.2M value in Wandeldarlehen scenarios.
Rolling balance now includes all financing cash flows via ÜBERSCHUSS chain.
MilestonesSlide: widen Theme type to union so t.key comparisons compile.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-23 22:07:38 +02:00
38684dd903
feat(control-pipeline): add Assessment Layer to Applicability Engine
...
Adds confidence scoring, escalation detection, and reasoning to the
deterministic filter. All assessment is deterministic (no LLM).
Confidence scoring (0.0-1.0):
- +0.25 industry specified
- +0.15 company size specified
- +0.20-0.30 scope signals provided
- +0.15 controls found
- +0.15 no contradictions
- Capped at 0.75 for escalation cases
Escalation triggers:
- Contradictory signals (holds_client_funds without operates_payment_service)
- Ambiguous signals (provides_embedded_connectivity)
- Financial signals without explicit payment service declaration
- Incomplete profile (no industry, size, or signals)
Reasoning: template-based, includes active signals, control count,
scope-condition descriptions, and warnings.
Response now includes "assessment" field with confidence, escalation_flag,
escalation_reason, inferred_signals, reasoning, and warnings.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-23 20:36:11 +02:00
716bc651c4
fix(control-pipeline): remove fictional demo packages, add real DB integration tests
...
Deleted 3 packages that were copied without validation:
- applicability_demo/ (fictional control IDs, wrong API schema)
- applicability_demo_sdk/ (wrong endpoint URL, fictional request format)
- applicability_demo_ci/ (GitHub Actions instead of Gitea, duplicated code)
Replaced with real integration in test_applicability_use_cases.py:
- TestApplicabilityIntegration calls real get_applicable_controls()
- Checks source_citation->source and control_id domain prefixes
- Runs against actual DB when DATABASE_URL is set
- 128 structure/acceptance tests pass, 24 integration tests skip without DB
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-23 19:59:56 +02:00
27f12e4659
feat(control-pipeline): add CI regression suite for applicability tests
...
Makefile + pytest + GitHub Actions workflow for automated regression:
- make install / make eval / make test
- pytest integration with demo_cases.yaml
- Golden outputs for 6 priority cases
- Report generation (JSON + Markdown)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-23 19:12:44 +02:00
a7c6ffe4dd
feat(control-pipeline): add SDK endpoint demo package for applicability tests
...
Request payloads + response contract + api_runner.py for 6 priority cases.
Can be run directly against /v1/applicability/evaluate endpoint.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-23 19:11:44 +02:00
ae5c5c24eb
feat(control-pipeline): add applicability demo test package with evaluator
...
6 priority demo cases with golden outputs, evaluator.py and run_demo.py:
- CASE-001: Webshop+Stripe (anti-PSD2 false positive)
- CASE-002: Bank+TAN-Generator (scope override for batteries)
- CASE-004: FinTech Wallet (true positive PSD2/AML)
- CASE-006: SaaS+SMS Gateway (anti-TKG false positive)
- CASE-008: Software→IoT Hardware (multi-regime scope)
- CASE-011: Embedded Finance (escalation case)
Self-test passes 6/6 against golden outputs.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-23 19:08:31 +02:00
e8ec50e0fc
feat(control-pipeline): 24 demo test cases for applicability engine
...
YAML-based test package with 4 categories (6 each):
- Standard sector cases (Telko, SaaS, Energie, Automotive, Health, Law)
- Scope-beats-sector (Bank+Battery, KI-Recruiting, White-Label, Payments)
- False friends (Stripe!=PSD2, Hotline!=TKG, Repo-signals!=regulation)
- Escalation (IoT-SIM, FinTech unclear, Treuhand, KI-Diagnose)
Enforces 5 acceptance rules: no false certainty, scope>sector,
repo signals insufficient, standard first, 40%+ negative tests.
Scoring framework: must_include + must_not_include + reasoning + escalation.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-23 17:42:38 +02:00
1f8667c7da
feat(control-pipeline): replace similarity-only dedup with LLM-verified dedup in pipeline
...
Stage 4 (Harmonization) now uses two-tier approach:
- Score >= 0.92: auto-duplicate (embedding only, fast)
- Score 0.85-0.92: LLM verification via local qwen3.5 (think=false, ~3s)
- Score < 0.85: not a duplicate
This eliminates ~44% false positives from pure embedding similarity.
LLM_DEDUP_ENABLED env var controls the feature (default: true).
Also adds 10 applicability use case tests (bank+TAN, webshop+Stripe,
SaaS startup, energy provider, health app, automotive, law firm, etc.)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-23 16:57:37 +02:00
bed41dcbdf
feat(control-pipeline): add applicability backfill endpoint (Phase 5/C3)
...
POST /v1/canonical/generate/backfill-applicability enriches controls
with applicable_industries, applicable_company_size, scope_conditions
via Anthropic API. Targets ~26k controls from pipeline version < 3.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-23 16:25:50 +02:00
6694ab84a1
chore: trigger rebuild
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 47s
CI / test-python-voice (push) Successful in 43s
CI / test-bqas (push) Successful in 33s
2026-04-23 12:43:55 +02:00
f721e97ff1
chore: diagnose WD liquiditaet sums
CI / go-lint (push) Has been cancelled
CI / python-lint (push) Has been cancelled
CI / nodejs-lint (push) Has been cancelled
CI / test-go-consent (push) Has been cancelled
CI / test-python-voice (push) Has been cancelled
CI / test-bqas (push) Has been cancelled
Build pitch-deck / build-push-deploy (push) Successful in 1m27s
2026-04-23 12:39:20 +02:00
d9f9fa0743
security: re-secure fp-patch
Build pitch-deck / build-push-deploy (push) Has been cancelled
CI / nodejs-lint (push) Has been cancelled
CI / go-lint (push) Has been cancelled
CI / python-lint (push) Has been cancelled
CI / test-go-consent (push) Has been cancelled
CI / test-python-voice (push) Has been cancelled
CI / test-bqas (push) Has been cancelled
2026-04-23 12:30:23 +02:00
7b72fac679
chore: trigger deploy
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 49s
CI / test-bqas (push) Has been cancelled
CI / test-python-voice (push) Has started running
2026-04-23 12:23:32 +02:00
726c780416
chore: recompute WD scenario
CI / go-lint (push) Has been cancelled
CI / python-lint (push) Has been cancelled
CI / nodejs-lint (push) Has been cancelled
CI / test-go-consent (push) Has been cancelled
CI / test-python-voice (push) Has been cancelled
CI / test-bqas (push) Has been cancelled
Build pitch-deck / build-push-deploy (push) Successful in 1m45s
2026-04-23 12:16:10 +02:00
69effa446a
security: re-secure fp-patch
Build pitch-deck / build-push-deploy (push) Successful in 1m5s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 36s
CI / test-python-voice (push) Successful in 31s
CI / test-bqas (push) Successful in 33s
2026-04-23 11:49:29 +02:00
c5bca9db44
chore: increase Marketing-Agentur 2027+100k, 2028+125k
Build pitch-deck / build-push-deploy (push) Successful in 1m29s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 40s
CI / test-python-voice (push) Successful in 33s
CI / test-bqas (push) Successful in 28s
2026-04-23 11:45:55 +02:00
6565538b3b
security: re-secure fp-patch
Build pitch-deck / build-push-deploy (push) Successful in 1m21s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 33s
CI / test-python-voice (push) Successful in 32s
CI / test-bqas (push) Successful in 31s
2026-04-23 10:50:12 +02:00
ecb704f24e
CRITICAL(pitch-deck): Liquidität tab — use DB values for all sum/balance rows
...
CI / go-lint (push) Has been cancelled
CI / python-lint (push) Has been cancelled
CI / nodejs-lint (push) Has been cancelled
CI / test-go-consent (push) Has been cancelled
Build pitch-deck / build-push-deploy (push) Has been cancelled
CI / test-python-voice (push) Has been cancelled
CI / test-bqas (push) Has been cancelled
Frontend was recalculating Summe EINZAHLUNGEN including funding (1M),
which made liquidity appear as ~1M throughout. Now all Liquidität
sum/balance rows (Summe, ÜBERSCHUSS, Kontostand, LIQUIDITÄT) come
directly from the engine-computed DB values.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-23 10:49:04 +02:00
86532f5e08
chore: temp open fp-patch
Build pitch-deck / build-push-deploy (push) Successful in 1m22s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 46s
CI / test-python-voice (push) Successful in 33s
CI / test-bqas (push) Successful in 33s
2026-04-23 10:44:25 +02:00
5c60d44283
chore: diagnose liquiditaet data
Build pitch-deck / build-push-deploy (push) Successful in 1m13s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 45s
CI / test-python-voice (push) Successful in 33s
CI / test-bqas (push) Has been cancelled
2026-04-23 10:41:16 +02:00
3eacb7e580
security: re-secure fp-patch
Build pitch-deck / build-push-deploy (push) Successful in 1m11s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 36s
CI / test-python-voice (push) Successful in 36s
CI / test-bqas (push) Successful in 36s
2026-04-23 10:26:16 +02:00
4151098c12
CRITICAL: fix version fm_scenarios to point to correct Base Case ID
Build pitch-deck / build-push-deploy (push) Successful in 1m7s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 33s
CI / test-python-voice (push) Successful in 35s
CI / test-bqas (push) Has been cancelled
2026-04-23 10:23:34 +02:00
93f8e85568
chore: diagnose scenario ID mismatch
Build pitch-deck / build-push-deploy (push) Successful in 1m15s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 29s
CI / test-python-voice (push) Successful in 32s
CI / test-bqas (push) Has been cancelled
2026-04-23 10:21:02 +02:00
92c272bbea
chore: reduce Beratung 2027 + Marketing-Agentur 2027/2028
Build pitch-deck / build-push-deploy (push) Successful in 1m3s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 31s
CI / test-python-voice (push) Successful in 29s
CI / test-bqas (push) Successful in 30s
2026-04-23 10:07:32 +02:00
ed4e41f7dc
security: re-secure fp-patch — 1M liquidity Dec28 at ~0
Build pitch-deck / build-push-deploy (push) Successful in 1m0s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 28s
CI / test-python-voice (push) Successful in 26s
CI / test-bqas (push) Successful in 27s
2026-04-23 09:56:28 +02:00
d7d77769ff
chore: Marketing-Agentur v3 — 35k/mo in 2028 for channel launch
Build pitch-deck / build-push-deploy (push) Successful in 1m1s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 29s
CI / test-python-voice (push) Successful in 27s
CI / test-bqas (push) Successful in 28s
2026-04-23 09:53:45 +02:00
362df8f766
chore: increase Marketing-Agentur v2
Build pitch-deck / build-push-deploy (push) Successful in 1m2s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 27s
CI / test-python-voice (push) Successful in 29s
CI / test-bqas (push) Successful in 27s
2026-04-23 09:50:52 +02:00
43f0f3d092
chore: increase 1M Marketing-Agentur to burn liquidity to ~0 by Dec 2028
Build pitch-deck / build-push-deploy (push) Successful in 1m2s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 28s
CI / test-python-voice (push) Successful in 31s
CI / test-bqas (push) Has been cancelled
2026-04-23 09:48:18 +02:00
ff851db5d1
security: re-secure fp-patch
Build pitch-deck / build-push-deploy (push) Successful in 1m8s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 27s
CI / test-python-voice (push) Successful in 30s
CI / test-bqas (push) Successful in 28s
2026-04-23 09:35:57 +02:00
b4bfa4ba49
chore: import 1M realistic customer curve
Build pitch-deck / build-push-deploy (push) Successful in 1m0s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 27s
CI / test-python-voice (push) Successful in 28s
CI / test-bqas (push) Successful in 34s
2026-04-23 09:29:02 +02:00
dacbb5f15e
security: re-secure fp-patch
Build pitch-deck / build-push-deploy (push) Successful in 1m7s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 30s
CI / test-python-voice (push) Successful in 31s
CI / test-bqas (push) Successful in 29s
2026-04-23 08:59:28 +02:00
34b7957132
chore: import 1M exponential customer data
Build pitch-deck / build-push-deploy (push) Successful in 1m31s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 41s
CI / test-python-voice (push) Successful in 29s
CI / test-bqas (push) Successful in 26s
2026-04-23 08:55:39 +02:00
cc46a389e7
security: re-secure fp-patch
Build pitch-deck / build-push-deploy (push) Successful in 1m22s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 34s
CI / test-python-voice (push) Successful in 28s
CI / test-bqas (push) Successful in 27s
2026-04-23 08:20:38 +02:00
9dc39d06af
fix: invest laptop-only 1500/person + GWG peripherals for both scenarios
Build pitch-deck / build-push-deploy (push) Successful in 1m28s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 37s
CI / test-python-voice (push) Successful in 31s
CI / test-bqas (push) Successful in 30s
2026-04-23 08:17:13 +02:00
43c4c5102a
security: re-secure fp-patch after 1M data import
Build pitch-deck / build-push-deploy (push) Successful in 1m7s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 33s
CI / test-python-voice (push) Successful in 28s
CI / test-bqas (push) Successful in 25s
2026-04-22 22:42:07 +02:00
0992c73842
chore: import 1M betriebliche + fix founders start
Build pitch-deck / build-push-deploy (push) Successful in 1m5s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 31s
CI / test-python-voice (push) Successful in 38s
CI / test-bqas (push) Successful in 32s
2026-04-22 22:36:24 +02:00
0808853d45
chore: diagnose all scenarios + add missing invest rows
Build pitch-deck / build-push-deploy (push) Has been cancelled
CI / go-lint (push) Has been cancelled
CI / python-lint (push) Has been cancelled
CI / nodejs-lint (push) Has been cancelled
CI / test-go-consent (push) Has been cancelled
CI / test-python-voice (push) Has been cancelled
CI / test-bqas (push) Has been cancelled
2026-04-22 22:30:55 +02:00
f071e89fc2
fix: add Mac Studio 13k + Markenanmeldung 5k to both scenarios
Build pitch-deck / build-push-deploy (push) Has been cancelled
CI / test-bqas (push) Has been cancelled
CI / go-lint (push) Has been cancelled
CI / python-lint (push) Has been cancelled
CI / nodejs-lint (push) Has been cancelled
CI / test-go-consent (push) Has been cancelled
CI / test-python-voice (push) Has been cancelled
2026-04-22 22:28:21 +02:00
b546ae3759
security: re-secure fp-patch
Build pitch-deck / build-push-deploy (push) Has been cancelled
CI / go-lint (push) Has been cancelled
CI / python-lint (push) Has been cancelled
CI / nodejs-lint (push) Has been cancelled
CI / test-go-consent (push) Has been cancelled
CI / test-python-voice (push) Has been cancelled
CI / test-bqas (push) Has been cancelled
2026-04-22 22:21:17 +02:00
a2fb1f38ee
chore: fp-patch — import 1M materialaufwand + investitionen
Build pitch-deck / build-push-deploy (push) Successful in 1m20s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 39s
CI / test-bqas (push) Has been cancelled
CI / test-python-voice (push) Has been cancelled
2026-04-22 22:18:35 +02:00
2195ccfa1a
security: re-secure fp-patch
Build pitch-deck / build-push-deploy (push) Successful in 1m11s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 35s
CI / test-python-voice (push) Successful in 37s
CI / test-bqas (push) Successful in 33s
2026-04-22 20:37:51 +02:00
b28f266cbe
chore: fp-patch — import 1M kunden/umsatz + recompute Base Case
Build pitch-deck / build-push-deploy (push) Successful in 1m25s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 44s
CI / test-python-voice (push) Successful in 34s
CI / test-bqas (push) Successful in 35s
2026-04-22 20:33:23 +02:00
736ddf647d
fix(llm-dedup): use think:false instead of /no_think, restore 30s timeout
...
Ollama API supports "think": false to disable extended thinking mode
on qwen3.5. Reduces response time from 95s to ~3s per comparison.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-22 20:31:13 +02:00
2188d6645e
fix(llm-dedup): increase timeout to 120s, add /no_think, limit output to 200 tokens
...
qwen3.5 uses extended thinking by default which causes 95s+ responses
and 30s timeouts. Add /no_think to system prompt and num_predict=200
to keep responses short.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-22 20:27:58 +02:00
151bf3d322
chore: diagnose 1M version data on production
Build pitch-deck / build-push-deploy (push) Successful in 1m32s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 40s
CI / test-python-voice (push) Successful in 39s
CI / test-bqas (push) Successful in 27s
2026-04-22 20:18:24 +02:00
076a6cd567
feat(control-pipeline): add LLM dedup endpoint for borderline review queue
...
POST /v1/canonical/generate/llm-dedup uses local Ollama (qwen3.5:35b-a3b)
to verify borderline duplicate matches (score 0.85-0.91). More accurate
than embedding similarity for compliance controls with subtle scope
differences (e.g. "documented" vs "implemented").
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-22 20:15:46 +02:00
c93796554a
fix: remove L-Bank compatibility note from BAFA INVEST card
Build pitch-deck / build-push-deploy (push) Successful in 1m25s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 35s
CI / test-python-voice (push) Successful in 29s
CI / test-bqas (push) Successful in 32s
2026-04-22 16:32:01 +02:00
Sharang Parnerkar