Dev/hermes upgrade t 16bbffad by solovision24 · Pull Request #76853 · NousResearch/hermes-agent

solovision24 · 2026-08-02T14:58:04Z

What does this PR do?

Related Issue

Fixes #

Type of Change

🐛 Bug fix (non-breaking change that fixes an issue)
✨ New feature (non-breaking change that adds functionality)
🔒 Security fix
📝 Documentation update
✅ Tests (adding or improving test coverage)
♻️ Refactor (no behavior change)
🎯 New skill (bundled or hub)

Changes Made

How to Test

Checklist

Code

I've read the Contributing Guide
My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
I searched for existing PRs to make sure this isn't a duplicate
My PR contains only changes related to this fix/feature (no unrelated commits)
I've run pytest tests/ -q and all tests pass
I've added tests for my changes (required for bug fixes, strongly encouraged for features)
I've tested on my platform:

Documentation & Housekeeping

I've updated relevant documentation (README, docs/, docstrings) — or N/A
I've updated cli-config.yaml.example if I added/changed config keys — or N/A
I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A
I've considered cross-platform impact (Windows, macOS) per the compatibility guide — or N/A
I've updated tool descriptions/schemas if I changed tool behavior — or N/A

For New Skills

This skill is broadly useful to most users (if bundled) — see Contributing Guide
SKILL.md follows the standard format (frontmatter, trigger conditions, steps, pitfalls)
No external dependencies that aren't already available (prefer stdlib, curl, existing Hermes tools)
I've tested the skill end-to-end: hermes --toolsets skills -q "Use the X skill to do Y"

Screenshots / Logs

…026.7.20 upgrade - agent/conversation_loop.py: prioritise structured reasoning fields over inline-think content for tool_progress_callback relay - ui-tui appLayout.tsx: drop stale inputHeight box sizing (auto-size from rendered content instead) - ui-tui textInput.tsx: cancel pending fast-echo parent update on submit

Merged after independent verification: 54 focused lifecycle/tool/core tests passed, compileall and git diff --check passed, and the PR is limited to the upstream-compatible Hermes baseline.

* fix(kanban): allow requeued review workers past PR guard * fix(kanban): preserve review routing after crash requeue * fix(kanban): preserve native review lane on crash * fix(kanban): apply retry guards to native reviews * fix(kanban): guard native review respawns during cooldown --------- Co-authored-by: SoLo <solo@SoLoBot>

Co-authored-by: SoLo <solo@SoLoBot>

* fix(kanban): restore native GitHub PR ingest * fix(kanban): restore GitHub PR lifecycle safeguards --------- Co-authored-by: SoLo <solo@SoLoBot>

* feat(kanban): enforce native review lifecycle * fix(kanban): authorize review changes from active review runs --------- Co-authored-by: SoLo <solo@SoLoBot>

* feat(kanban): enforce native review lifecycle * fix(kanban): authorize review changes from active review runs * ci: scope contributor checks to the PR base --------- Co-authored-by: SoLo <solo@SoLoBot>

teknium1

Thanks for preserving several local fixes and adding focused tests. Two changes need resolution before the bundle is reviewable.

Problems

agent/auxiliary_client.py:605-611 on current main intentionally skips kimi-coding for automatic vision routing; commit ff687c019e documents that the Coding Plan endpoint lacks image input and the fallback avoids 404s. This PR removes that safeguard while its revised test mocks vision support rather than exercising the actual transport.
agent/prompt_builder.py:2020 adds root AGENTS.md inheritance for named profiles. AGENTS.md:147-153 explicitly defines profiles as independent islands and identifies --clone as the supported copy-at-creation mechanism.

Suggested changes

Retain the Kimi auto-routing fallback unless an end-to-end Coding Plan image request verifies the new behavior.
Remove or separately discuss the profile-policy inheritance change.
Split the unrelated agent, OAuth, Kanban, TUI, CI, and test-runner changes into focused PRs with current-main repro and verification details.

Automated hermes-sweeper review.

teknium1 · 2026-08-02T15:08:45Z

-# describe as having no image_in capability. Vision lives on the separate
-# Kimi Platform (api.moonshot.ai, OpenAI-wire, pay-as-you-go).  See #17076.
+# NOTE: kimi-coding is intentionally NOT listed here. Kimi K3 on
+# api.kimi.com/coding/v1 accepts OpenAI-style image_url content and models.dev


Current main intentionally keeps kimi-coding in _PROVIDERS_WITHOUT_VISION because the Coding Plan transport lacks image input; ff687c019e added the fallback after real 404s. Please retain that guard unless an end-to-end request against this exact transport proves image support.

teknium1 · 2026-08-02T15:08:45Z

@@ -2013,6 +2020,49 @@ def load_soul_md(context_length: Optional[int] = None) -> Optional[str]:
        return None


This introduces live root-to-named-profile policy inheritance. AGENTS.md:147-153 explicitly defines profiles as independent islands and points to --clone for copy-at-creation; please remove this change unless maintainers approve a deliberate change to that isolation contract.

* fix(kanban): replay native review convergence on current base * fix(kanban): restore same-card review remediation lifecycle * fix(kanban): replay webhook review convergence on approved base --------- Co-authored-by: SoLo <solo@SoLoBot>

* fix(kanban): finalize claimed webhook review runs * fix(kanban): correct native review handoff comment --------- Co-authored-by: SoLo <solo@SoLoBot>

* fix(kanban): hard-gate changes-required review completion * fix(kanban): harden review remediation gates * fix(kanban): bind review approval to immutable head * fix(kanban): expose ready review remediation handoff * fix(kanban): authorize remediation dependency exception * fix(kanban): secure remediation handoff identity * fix(kanban): harden remediation key contract * fix(kanban): reject pre-seeded remediation keys --------- Co-authored-by: SoLo <solo@SoLoBot>

* fix(kanban): repair same-card review branch base * fix(kanban): ignore archived prior review remediation keys --------- Co-authored-by: SoLo <solo@SoLoBot>

solovision24 and others added 11 commits July 31, 2026 08:14

fix: allow kimi k3 vision auto-routing

9dd48cf

fix(prompt): apply root policy to named profiles

5b4d9a4

chore: reconcile local Hermes changes with v2026.7.30

2ad3448

feat(kanban): route implementation handoffs through review

8902b34

feat(kanban): route implementation handoffs through review

945333b

Merged after independent verification: 54 focused lifecycle/tool/core tests passed, compileall and git diff --check passed, and the PR is limited to the upstream-compatible Hermes baseline.

fix(kanban): expose native review initial status (#7)

ebd978b

Co-authored-by: SoLo <solo@SoLoBot>

fix(kanban): restore native GitHub PR ingest (#8)

b4d2878

* fix(kanban): restore native GitHub PR ingest * fix(kanban): restore GitHub PR lifecycle safeguards --------- Co-authored-by: SoLo <solo@SoLoBot>

feat(kanban): enforce native review lifecycle (#11)

21458a4

* feat(kanban): enforce native review lifecycle * fix(kanban): authorize review changes from active review runs --------- Co-authored-by: SoLo <solo@SoLoBot>

fix(kanban): close native review lifecycle remediation gaps (#12)

5743832

* feat(kanban): enforce native review lifecycle * fix(kanban): authorize review changes from active review runs * ci: scope contributor checks to the PR base --------- Co-authored-by: SoLo <solo@SoLoBot>

teknium1 reviewed Aug 2, 2026

View reviewed changes

solovision24 and others added 4 commits August 2, 2026 12:53

fix(kanban): preserve native card during webhook convergence (#16)

09aed9b

* fix(kanban): finalize claimed webhook review runs * fix(kanban): correct native review handoff comment --------- Co-authored-by: SoLo <solo@SoLoBot>

fix(kanban): requeue review changes on same card (#17)

6be3c48

* fix(kanban): repair same-card review branch base * fix(kanban): ignore archived prior review remediation keys --------- Co-authored-by: SoLo <solo@SoLoBot>

briandevans mentioned this pull request Aug 4, 2026

fix(cli): make profile.yaml and skin writes atomic to stop silent field loss (supersedes #51808) #78301

Closed

19 tasks

Navigation Menu

Uh oh!

Dev/hermes upgrade t 16bbffad - #76853

Dev/hermes upgrade t 16bbffad#76853
solovision24 wants to merge 15 commits into
NousResearch:mainfrom
solovision24:dev/hermes-upgrade-t_16bbffad

solovision24 commented Aug 2, 2026

Uh oh!

teknium1 left a comment

Uh oh!

teknium1 Aug 2, 2026

Uh oh!

teknium1 Aug 2, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

		@@ -2013,6 +2020,49 @@ def load_soul_md(context_length: Optional[int] = None) -> Optional[str]:
		return None

Uh oh!

Conversation

solovision24 commented Aug 2, 2026

What does this PR do?

Related Issue

Type of Change

Changes Made

How to Test

Checklist

Code

Documentation & Housekeeping

For New Skills

Screenshots / Logs

Uh oh!

teknium1 left a comment

Choose a reason for hiding this comment

Problems

Suggested changes

Uh oh!

teknium1 Aug 2, 2026

Choose a reason for hiding this comment

Uh oh!

teknium1 Aug 2, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants