2025-12-24T10:02:36Z - 2026-06-24T09:02:36Z
Overview
9 releases published by 1 user
Tag
v0.7.0
Tag
v0.6.2
Release
v0.6.1
v0.6.1 — Source health grouping
Release
v0.6.0
v0.6.0
Tag
v0.5.0
Release
v0.4.0
v0.4.0 — Live Watch Mode
Release
v0.3.0
v0.3.0 — LLM Reasoning + Severity Overrides
Release
v0.2.0
v0.2.0 — Frictionless Incident Capture
Release
v0.1.0
v0.1.0 — Initial Release
5 pull requests merged by 1 user
Merged
#40 refactor: pipeline cleanup — 6 follow-up fixes (#33–#38)
Merged
#39 feat(diagnose): 5-stage multi-agent diagnose pipeline (#29)
Merged
#16 feat: live watch mode — tail journald/docker/podman continuously (#4)
Merged
#14 feat: LLM reasoning, severity overrides, dashboard freshness
Merged
#13 feat: frictionless incident capture
1 pull request proposed by 1 user
Proposed
#28 feat: SSH remote host glean (#22)
47 issues closed from 1 user
Closed
#12 feat: incident ticket automation — export incidents to Jira, Notion, and other trackers
Closed
#24 feat: SSH target manager — GUI editor for remote host configuration
Closed
#54 chore: enumerate log sources to harvest from example-node
Closed
#55 chore: enumerate log sources to harvest from huginn
Closed
#27 feat: Orchard branch auto-enrollment and submission anonymization
Closed
#23 feat: context-aware dynamic log discovery — scan /var/log and /opt ranked by problem context and reference corpus
Closed
#46 feat: synthetic log corpus generator for demo and testing
Closed
#11 feat: security alerts tab — UI view for IDS/antimalware hits
Closed
#6 feat: push-based log corpus export — periodic ERROR/CRITICAL batch push to Avocet
Closed
#57 feat: incident timeline visualizer — scrollable event stream with severity bands
Closed
#9 feat: HuggingFace cybersec model integration — pretrained classifier on ingested entries
Closed
#10 feat: anomaly scoring pipeline — score entries, persist results, surface high-confidence hits
Closed
#50 feat: multi-tenant source namespacing -- isolate log sources per deployment context
Closed
#42 Migrate from SQLite to PostgreSQL for multi-node write support
Closed
#65 Adopt cf_core.memory (mnemo) for persistent knowledge graph
Closed
#15 feat: hybrid BM25 + vector RAG for diagnose — pattern recognition and red herring suppression
Closed
#32 Domain-view mapping: cluster log patterns by service health domain in diagnose output
Closed
#60 DB write contention: FTS5 batch inserts starve incident API and watcher flushes
Closed
#41 feat(classifier): add Hybrid-BERT label mapping shim for krishnas4415/log-anomaly-detection-models
Closed
#53 feat: natural language source addition -- describe a log source in plain English
Closed
#52 feat: onboarding wizard -- guided first-run setup for new deployments
Closed
#51 feat: log bundle export with PII sanitization option
Closed
#48 chore: compliance audit checklist -- data isolation, audit logging, PII egress
Closed
#49 feat: API authentication -- bearer token / API key for all REST endpoints
Closed
#47 docs: air-gapped deployment guide
Closed
#45 feat: offline-first model bundling -- disable HuggingFace downloads at runtime
Closed
#21 feat: reference doc layer — ingest local structured docs (Markdown, PDF, DOCX) for context-aware diagnosis
Closed
#56 feat: technical-level post-processor for diagnosis output
Closed
#38 fix: coerce supporting_cluster_ids items to str in hypothesizer LLM response parsing
Closed
#36 feat: add per-stage error isolation in pipeline.py run_pipeline()
Closed
#34 fix: remove unreachable suppression branch in synthesizer._build_hypothesis_block
Closed
#35 refactor: extract shared _call_llm helper used by hypothesizer and synthesizer
Closed
#37 fix: move format_context_block() call inside legacy-only branch in diagnose/__init__.py
Closed
#33 refactor: make ClassifiedTimeline.cluster_severities immutable (MappingProxyType)
Closed
#30 Fingerprint-based incremental glean: skip unchanged log files on batch re-glean
Closed
#29 Multi-agent diagnose pipeline: specialize into timeline, root-cause, and false-positive-suppressor stages
Closed
#22 feat: SSH remote host ingest — pull logs from remote systems over SSH
Closed
#17 Add assignments.yaml entry to activate cf-orch task routing (already wired in llm.py)
Closed
#8 feat: cf-orch scheduled task — batch ingest + pattern-match run on cron
Closed
#5 feat: Podman harvester agent — lightweight container to collect and ship logs to Turnstone
Closed
#2 feat: corpus management tab — Vue view for source stats, reindex, delete
Closed
#3 feat: file upload / POST ingest endpoint — accept log files for remote harvester
Closed
#1 feat: incident tagging — DB schema + API to mark time windows with descriptions
Closed
#20 feat: rename CF_ORCH_URL → GPU_SERVER_URL for local-first clarity
Closed
#19 Rename CF_ORCH_URL to GPU_SERVER_URL for self-hoster clarity
Closed
#7 feat: Avocet — add Turnstone as a corpus data source
Closed
#4 feat: live watch mode — tail journald + docker log sources continuously
58 issues created by 1 user
Opened
#1 feat: incident tagging — DB schema + API to mark time windows with descriptions
Opened
#2 feat: corpus management tab — Vue view for source stats, reindex, delete
Opened
#5 feat: Podman harvester agent — lightweight container to collect and ship logs to Turnstone
Opened
#3 feat: file upload / POST ingest endpoint — accept log files for remote harvester
Opened
#4 feat: live watch mode — tail journald + docker log sources continuously
Opened
#6 feat: push-based log corpus export — periodic ERROR/CRITICAL batch push to Avocet
Opened
#7 feat: Avocet — add Turnstone as a corpus data source
Opened
#9 feat: HuggingFace cybersec model integration — pretrained classifier on ingested entries
Opened
#8 feat: cf-orch scheduled task — batch ingest + pattern-match run on cron
Opened
#10 feat: anomaly scoring pipeline — score entries, persist results, surface high-confidence hits
Opened
#11 feat: security alerts tab — UI view for IDS/antimalware hits
Opened
#12 feat: incident ticket automation — export incidents to Jira, Notion, and other trackers
Opened
#15 feat: hybrid BM25 + vector RAG for diagnose — pattern recognition and red herring suppression
Opened
#17 Add assignments.yaml entry to activate cf-orch task routing (already wired in llm.py)
Opened
#18 feat: evaluate Agent-ModernColBERT as semantic upgrade to FTS5 log search
Opened
#19 Rename CF_ORCH_URL to GPU_SERVER_URL for self-hoster clarity
Opened
#20 feat: rename CF_ORCH_URL → GPU_SERVER_URL for local-first clarity
Opened
#21 feat: reference doc layer — ingest local structured docs (Markdown, PDF, DOCX) for context-aware diagnosis
Opened
#22 feat: SSH remote host ingest — pull logs from remote systems over SSH
Opened
#23 feat: context-aware dynamic log discovery — scan /var/log and /opt ranked by problem context and reference corpus
Opened
#24 feat: SSH target manager — GUI editor for remote host configuration
Opened
#25 feat: strip display route — sysadmin profile
Opened
#26 feat: Tauri desktop companion — sysadmin tray app
Opened
#27 feat: Orchard branch auto-enrollment and submission anonymization
Opened
#29 Multi-agent diagnose pipeline: specialize into timeline, root-cause, and false-positive-suppressor stages
Opened
#31 Log causality graph: force-directed incident visualization (nodes=services, edges=correlated events)
Opened
#30 Fingerprint-based incremental glean: skip unchanged log files on batch re-glean
Opened
#32 Domain-view mapping: cluster log patterns by service health domain in diagnose output
Opened
#33 refactor: make ClassifiedTimeline.cluster_severities immutable (MappingProxyType)
Opened
#34 fix: remove unreachable suppression branch in synthesizer._build_hypothesis_block
Opened
#35 refactor: extract shared _call_llm helper used by hypothesizer and synthesizer
Opened
#37 fix: move format_context_block() call inside legacy-only branch in diagnose/__init__.py
Opened
#36 feat: add per-stage error isolation in pipeline.py run_pipeline()
Opened
#38 fix: coerce supporting_cluster_ids items to str in hypothesizer LLM response parsing
Opened
#41 feat(classifier): add Hybrid-BERT label mapping shim for krishnas4415/log-anomaly-detection-models
Opened
#42 Migrate from SQLite to PostgreSQL for multi-node write support
Opened
#43 feat: vendor device proprietary log format parser
Opened
#44 feat: vendor device structured error code pattern library
Opened
#45 feat: offline-first model bundling -- disable HuggingFace downloads at runtime
Opened
#46 feat: synthetic log corpus generator for demo and testing
Opened
#47 docs: air-gapped deployment guide
Opened
#48 chore: compliance audit checklist -- data isolation, audit logging, PII egress
Opened
#50 feat: multi-tenant source namespacing -- isolate log sources per deployment context
Opened
#49 feat: API authentication -- bearer token / API key for all REST endpoints
Opened
#51 feat: log bundle export with PII sanitization option
Opened
#52 feat: onboarding wizard -- guided first-run setup for new deployments
Opened
#53 feat: natural language source addition -- describe a log source in plain English
Opened
#54 chore: enumerate log sources to harvest from example-node
Opened
#55 chore: enumerate log sources to harvest from huginn
Opened
#56 feat: technical-level post-processor for diagnosis output
Opened
#57 feat: incident timeline visualizer — scrollable event stream with severity bands
Opened
#58 DMZ + honeypot for bot pattern capture
Opened
#59 Design ref: llama-conductor patterns for log retrieval cascade + provenance tracking
Opened
#60 DB write contention: FTS5 batch inserts starve incident API and watcher flushes
Opened
#65 Adopt cf_core.memory (mnemo) for persistent knowledge graph
Opened
#66 Evaluate RePlaya for session replay diagnostics
Opened
#67 feat: honeypot log ingestion — Cowrie, OpenCanary, T-Pot parsers + guaranteed-malicious alerting
Opened
#68 feat: AI-driven threat detection — behavioral analysis, external threat intel, prompt injection signatures