Skip to content

Due Diligence Agents

v1.9.0 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agents anthropic claude compliance contract-analysis corp-dev
+14 more
security document-analysis due-diligence fintech knowledge-graph legal-tech llm mergers-and-acquisitions multi-agent neurosymbolic pdf-extraction private-equity python risk-analysis

Summary

AI summary

Updates Changes since v1.8.0, prompts, and v1.9.0 across a mixed release.

Changes in this release

Feature Low

Extract all built-in agent prompts into editable markdown files.

Extract all built-in agent prompts into editable markdown files.

Source: llm_adapter@2026-06-03

Confidence: high

Deprecation Low

Remove historical docs/plan/ design specifications.

Remove historical docs/plan/ design specifications.

Source: llm_adapter@2026-06-03

Confidence: high

Bugfix Medium

Enforce agent timeout_seconds; stalled SDK stream no longer hangs.

Enforce agent timeout_seconds; stalled SDK stream no longer hangs.

Source: llm_adapter@2026-06-03

Confidence: low

Bugfix Medium

Address adversarial audit by hardening editable surface to fail-closed.

Address adversarial audit by hardening editable surface to fail-closed.

Source: llm_adapter@2026-06-03

Confidence: low

Bugfix Low

Fix 'sample report' links to point at /sample-report/ path.

Fix 'sample report' links to point at /sample-report/ path.

Source: llm_adapter@2026-06-03

Confidence: high

Full changelog

Changes since v1.8.0

  • v1.9.0: editable markdown agent prompts + agent timeout enforcement
  • fix(agents): enforce agent timeout_seconds — stalled SDK stream no longer hangs
  • test(prompts): make golden snapshots environment-independent (fix CI)
  • fix(prompts): address adversarial audit — fail-closed hardening of the editable surface
  • docs(prompts): introspection footer + CLAUDE.md/agent-customization updates
  • feat(prompts): Phase 3 — extract synthesis + auto-config prompts to markdown
  • feat(prompts): Phase 2 — extract search-column templates to markdown
  • feat(prompts): Phase 1 — extract 9 specialists' prose to editable markdown
  • feat(prompts): Phase 0 — golden-master gate + markdown prompt loader (no prose moved)
  • Update README.md
  • docs: embed the walkthrough deck in the README as a clickable thumbnail
  • docs: refresh marketing presentation to current codebase state
  • docs: fix 'sample report' links to point at /sample-report/
  • docs: remove the historical docs/plan/ design specs
  • docs: close 3 residuals from final corpus verification
  • docs+test: PLAN.md count polish + guard that plan specs stay banner-marked
  • docs: strengthen plan-spec banners + cut drift-bait code listings
  • docs: reduce 03-project-structure.md to its durable design contracts
  • docs: consolidate agent-prompt design docs into one
  • docs: scrub de-identified production data from plan/knowledge docs (Sensitive Data Policy)
  • docs: address adversarial review (round 3) — close two drift-guard false negatives
  • docs: address adversarial review (round 2) — tighten guards, add gate count, polish
  • docs: address adversarial review (round 1) — strengthen drift guard, fix residual count drift
  • docs: full audit — fix drift, re-frame historical specs, add CI drift guard
  • docs: bump DOCKERHUB.md tag example to 1.8.0
  • Update Homebrew formula to 1.8.0

Install

pip install dd-agents==1.9.0

Docker

docker pull zoharbabin/due-diligence-agents:1.9.0

What's Changed

  • docs: full audit — fix drift, re-frame historical specs, add CI drift guard by @zoharbabin in https://github.com/zoharbabin/due-diligence-agents/pull/203
  • docs: remove historical docs/plan/ specs + fix sample-report links by @zoharbabin in https://github.com/zoharbabin/due-diligence-agents/pull/204
  • docs: refresh marketing presentation to current codebase state by @zoharbabin in https://github.com/zoharbabin/due-diligence-agents/pull/205
  • docs: embed walkthrough deck in README as clickable thumbnail by @zoharbabin in https://github.com/zoharbabin/due-diligence-agents/pull/206
  • feat(prompts): extract all built-in agent prompts into editable markdown by @zoharbabin in https://github.com/zoharbabin/due-diligence-agents/pull/207

Full Changelog: https://github.com/zoharbabin/due-diligence-agents/compare/v1.8.0...v1.9.0

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track Due Diligence Agents

Get notified when new releases ship.

Sign up free

About Due Diligence Agents

All releases →

Related context

Beta — feedback welcome: [email protected]