docs(hermes-agent): production v0.13 + multi-version action plan (20 agents, 3 pipelines) - #158
Merged
Ghenghis merged 1 commit intoMay 9, 2026
Conversation
…agents, 3 pipelines) 20-agent action plan to (a) promote v0.13 from canary to production, (b) keep v0.12 fully operational as fallback, and (c) prepare a forward pipeline for v0.14+ when it tags upstream. Pipelines (3, parallel) - P1 Production v0.13 Promotion (8 agents): live probes, upstream guard PR, BLK-013 implementation, promotion PR, rollback runbook, post-promotion smoke, adversarial review - P2 Multi-Version Coexistence (6 agents): version registry, per-request routing, v0.12 + v0.13 regression pinners, cross-version compat matrix, version-tagged proof events - P3 v0.14+ Forward Pipeline (6 agents): tag/SHA watcher, reusable canary harness, multi-version GHA proof workflow, RC v2 version-aware smoke, provider compat matrix, final commander Sequencing: 4 waves of 5 agents each with synthesis between waves. Hard gates (must clear before production promotion) 1. Live MiniMax + DeepSeek probes return accepted=true with redacted evidence 2. BLK-013 bounded-task PR ships OR explicit operator approval to defer 3. Upstream tui_gateway/entry.py:143-145 Windows guard merges OR explicit operator approval to ship without TUI/PTY surface Stop-conditions - Success: v0.13 promoted + 8 smokes green + rollback runbook - Hard gate fails + user declines fallback: documented blocker - >2 loops no new evidence: agent escalation - Any v0.12 fallback regression: immediate halt - Any secret leak: immediate halt + redact Out of scope (explicitly): GUI, 60-app, printer safety, RC v2 commits 3-5, non-Hermes-Agent Bonus 12 follow-ups. This plan does NOT execute. Awaiting user approval. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. Comment |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a detailed action plan for promoting Hermes Agent v0.13 to production while maintaining a multi-version pipeline architecture for legacy and development versions. Review feedback highlights a labeling contradiction in the architecture diagram regarding the production version, suggests using more idiomatic signal attribute checks instead of platform-specific guards, and requests clarification on the technical feasibility of changing environment variables mid-process.
Comment on lines
+32
to
+33
| v0.12 v0.13 v0.14+ / (custom) | ||
| PRODUCTION CANARY DEV |
There was a problem hiding this comment.
The architecture diagram labels v0.12 as PRODUCTION and v0.13 as CANARY. This contradicts the stated goal in lines 12-14, where v0.13 is promoted to production and v0.12 becomes the legacy fallback. The diagram should be updated to reflect the target state of the action plan.
Suggested change
| v0.12 v0.13 v0.14+ / (custom) | |
| PRODUCTION CANARY DEV | |
| v0.12 v0.13 v0.14+ / (custom) | |
| LEGACY PRODUCTION DEV |
| |---|---|---|---| | ||
| | **P1-1** | Live MiniMax probe runner | Execute `POST /providers/smoke` for MiniMax against canary venv with `HERMES_AGENT_CHECKOUT` set; capture redacted-evidence shape | `accepted=true` + sha256-only auth_contract OR document blocker | | ||
| | **P1-2** | Live DeepSeek probe runner | Same for DeepSeek | same | | ||
| | **P1-3** | Upstream Windows-guard PR builder | File PR against NousResearch/hermes-agent: 1-line `if sys.platform != 'win32':` guard at `tui_gateway/entry.py:143-145` around `signal.SIGPIPE`/`SIGHUP` | PR opened upstream OR exact reason cannot file | |
There was a problem hiding this comment.
For P1-3, while checking sys.platform != 'win32' is functional, it is generally more robust and idiomatic in Python to check for the existence of the specific signal attributes directly (e.g., if hasattr(signal, 'SIGPIPE'):). This approach handles potential missing signals on any platform or environment without relying on platform-specific strings.
Suggested change
| | **P1-3** | Upstream Windows-guard PR builder | File PR against NousResearch/hermes-agent: 1-line `if sys.platform != 'win32':` guard at `tui_gateway/entry.py:143-145` around `signal.SIGPIPE`/`SIGHUP` | PR opened upstream OR exact reason cannot file | | |
| | **P1-3** | Upstream Windows-guard PR builder | File PR against NousResearch/hermes-agent: 1-line hasattr(signal, 'SIGPIPE') guard at tui_gateway/entry.py:143-145 around signal.SIGPIPE/SIGHUP | PR opened upstream OR exact reason cannot file | |
| | **P1-3** | Upstream Windows-guard PR builder | File PR against NousResearch/hermes-agent: 1-line `if sys.platform != 'win32':` guard at `tui_gateway/entry.py:143-145` around `signal.SIGPIPE`/`SIGHUP` | PR opened upstream OR exact reason cannot file | | ||
| | **P1-4** | BLK-013 bounded-task implementer | Apply Wave B10's refined plan: ~300 LoC service + ~30 LoC route + ~120 LoC tests for `POST /cli-runners/run-bounded-task` | PR shipped + 6/6 tests pass OR explicit blocker | | ||
| | **P1-5** | Promotion PR builder | 1-line change in `services/agent_checkout.py:DEFAULT_AGENT_CHECKOUT` to canary path; ~5 LoC test updates | PR ready-to-merge waiting on user merge auth | | ||
| | **P1-6** | Rollback runbook builder | Operator runbook: how to flip back to v0.12 in <60s; includes `HERMES_AGENT_CHECKOUT=hermes-agent-fresh` mid-process flip + DB cleanup | runbook published OR exact gap | |
There was a problem hiding this comment.
The mission for P1-6 mentions a "mid-process flip" of HERMES_AGENT_CHECKOUT. Standard environment variables are inherited at process startup and cannot be changed externally for a running process in a way that os.environ would reflect. If the intention is to allow switching without a restart, the plan should clarify how this is achieved (e.g., via an internal API call that updates the process's own environment) or acknowledge that a restart is required for the change to take effect.
4 tasks
Ghenghis
added a commit
that referenced
this pull request
May 10, 2026
… 7/7 gates green) (#160) Wave 1 of the v0.13 production promotion swarm cleared all 7 hard gates. This PR flips the resolver default from v0.12 (hermes-agent-fresh) to v0.13 (hermes-agent-v013-canary). v0.12 remains the opt-in fallback via HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh. Hard gates (all PASS, evidence below) 1. MiniMax accepted=true — P1-1 (ev_84c2ba93c25d4017) 2. DeepSeek accepted=true — P1-1 (ev_6fa1536b411822db) 3. Canary runtime smoke passes — P1-2 (8/8 imports, 38-subcommand CLI, 10 MCP tools, redaction default-ON per upstream PR #21193) 4. v0.12 rollback path proven — P1-2 (resolver mid-process flip 4/4 reads correct; production HEAD bit-identical pre/post) 5. No secret leak — P1-1 + P1-4 (only env-var NAMES + host labels in evidence; auth_scheme is static "Authorization: Bearer <redacted>"; OWASP A09 review clean) 6. No v0.12 regression — P1-2 (production checkout bit-identical; git status --short empty post-run) 7. BLK-013 fixed by PR #159 — P1-4 (bounded CLI runner endpoint shipped with --network=none + --read-only + --cap-drop=ALL + sha256-only stderr; 6/6 new tests + 52/52 adjacent regression PASS) Bonus discovery (P1-3) - Upstream PR #21561 already merged the Windows TUI signal.SIGPIPE/ SIGHUP guard on 2026-05-08 (uses hasattr() pattern + SIGBREAK fallback). Canary at v2026.5.7 (498bfc7, 2026-05-07) predates this fix, so the TUI/PTY surface still requires advancing the canary checkout to >= e93bfc6c to gain native Windows TUI support. Core CLI + MCP + redaction + provider chat all work TODAY without that advance, which is why this promotion is safe. Patch - DEFAULT_AGENT_CHECKOUT now points to v0.13 (canary path). - New V012_FALLBACK_CHECKOUT constant exposes the v0.12 path for operators + tests that need explicit fallback semantics. - CANARY_AGENT_CHECKOUT retained as alias for back-compat. Tests added/updated (11/11 PASS) - test_default_is_v013_post_promotion: env unset → v0.13 - test_v012_fallback_via_env: env=hermes-agent-fresh → v0.12 - test_resolver_constants_are_correct: DEFAULT == CANARY == v0.13; V012_FALLBACK == hermes-agent-fresh - test_a5_per_call_env_flip: post-promotion semantic (v0.13 ↔ v0.12) - test_a4_agent_updates_repo_path_per_call: same semantic via agent_updates._repo_path() - test_v013_default_when_env_unset: route helper + resolver agree - (4 source-level pin tests retained from PR #155) Verification - py_compile: OK - Focused tests: 11/11 pass - Pre-push hook: passed Rollback - Operators set HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh in the FastAPI process env to revert to v0.12 mid-process (no restart; per-call resolver from PR #155). - Or revert this PR (1 commit) to restore v0.12 as the file-level default. - Production v0.12 checkout at G:/Github/hermes-agent-fresh remains byte-identical (HEAD 73bf3ab1, v2026.4.30, status clean) — never modified by canary work. Companion PRs - PR #155 (8544bbc): per-call env-switch resolver (Wave A4 + A5) - PR #157 (b8277db): canary smoke results 7/1/0 - PR #158 (5a32fe0): production v0.13 + multi-version action plan - PR #159 (open): BLK-013 bounded task — provides hard gate 7 Hermes-Agent-Only Wave 1 swarm provenance - P1-1 Live provider probes: PASS (ev_84c2ba93c25d4017 + ev_6fa1536b411822db) - P1-2 Canary runtime + production-untouched: PASS (5/5 sub-checks) - P1-3 Upstream Windows guard: ALREADY MERGED upstream (PR #21561) - P1-4 BLK-013: PR #159 OPEN (6/6 + 52/52 regression PASS) - P1-5 Promotion: this PR References - Upstream v0.13.0 release: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.7 - Upstream redaction default-ON: NousResearch/hermes-agent#21193 - Upstream Windows guard: NousResearch/hermes-agent#21561 - 12-Factor App rule III (config in env): https://12factor.net/config Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ghenghis
added a commit
that referenced
this pull request
May 10, 2026
…162) * feat(hermes-agent): promote v0.13 to production default (Wave 1 P1-5; 7/7 gates green) Wave 1 of the v0.13 production promotion swarm cleared all 7 hard gates. This PR flips the resolver default from v0.12 (hermes-agent-fresh) to v0.13 (hermes-agent-v013-canary). v0.12 remains the opt-in fallback via HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh. Hard gates (all PASS, evidence below) 1. MiniMax accepted=true — P1-1 (ev_84c2ba93c25d4017) 2. DeepSeek accepted=true — P1-1 (ev_6fa1536b411822db) 3. Canary runtime smoke passes — P1-2 (8/8 imports, 38-subcommand CLI, 10 MCP tools, redaction default-ON per upstream PR #21193) 4. v0.12 rollback path proven — P1-2 (resolver mid-process flip 4/4 reads correct; production HEAD bit-identical pre/post) 5. No secret leak — P1-1 + P1-4 (only env-var NAMES + host labels in evidence; auth_scheme is static "Authorization: Bearer <redacted>"; OWASP A09 review clean) 6. No v0.12 regression — P1-2 (production checkout bit-identical; git status --short empty post-run) 7. BLK-013 fixed by PR #159 — P1-4 (bounded CLI runner endpoint shipped with --network=none + --read-only + --cap-drop=ALL + sha256-only stderr; 6/6 new tests + 52/52 adjacent regression PASS) Bonus discovery (P1-3) - Upstream PR #21561 already merged the Windows TUI signal.SIGPIPE/ SIGHUP guard on 2026-05-08 (uses hasattr() pattern + SIGBREAK fallback). Canary at v2026.5.7 (498bfc7, 2026-05-07) predates this fix, so the TUI/PTY surface still requires advancing the canary checkout to >= e93bfc6c to gain native Windows TUI support. Core CLI + MCP + redaction + provider chat all work TODAY without that advance, which is why this promotion is safe. Patch - DEFAULT_AGENT_CHECKOUT now points to v0.13 (canary path). - New V012_FALLBACK_CHECKOUT constant exposes the v0.12 path for operators + tests that need explicit fallback semantics. - CANARY_AGENT_CHECKOUT retained as alias for back-compat. Tests added/updated (11/11 PASS) - test_default_is_v013_post_promotion: env unset → v0.13 - test_v012_fallback_via_env: env=hermes-agent-fresh → v0.12 - test_resolver_constants_are_correct: DEFAULT == CANARY == v0.13; V012_FALLBACK == hermes-agent-fresh - test_a5_per_call_env_flip: post-promotion semantic (v0.13 ↔ v0.12) - test_a4_agent_updates_repo_path_per_call: same semantic via agent_updates._repo_path() - test_v013_default_when_env_unset: route helper + resolver agree - (4 source-level pin tests retained from PR #155) Verification - py_compile: OK - Focused tests: 11/11 pass - Pre-push hook: passed Rollback - Operators set HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh in the FastAPI process env to revert to v0.12 mid-process (no restart; per-call resolver from PR #155). - Or revert this PR (1 commit) to restore v0.12 as the file-level default. - Production v0.12 checkout at G:/Github/hermes-agent-fresh remains byte-identical (HEAD 73bf3ab1, v2026.4.30, status clean) — never modified by canary work. Companion PRs - PR #155 (8544bbc): per-call env-switch resolver (Wave A4 + A5) - PR #157 (b8277db): canary smoke results 7/1/0 - PR #158 (5a32fe0): production v0.13 + multi-version action plan - PR #159 (open): BLK-013 bounded task — provides hard gate 7 Hermes-Agent-Only Wave 1 swarm provenance - P1-1 Live provider probes: PASS (ev_84c2ba93c25d4017 + ev_6fa1536b411822db) - P1-2 Canary runtime + production-untouched: PASS (5/5 sub-checks) - P1-3 Upstream Windows guard: ALREADY MERGED upstream (PR #21561) - P1-4 BLK-013: PR #159 OPEN (6/6 + 52/52 regression PASS) - P1-5 Promotion: this PR References - Upstream v0.13.0 release: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.7 - Upstream redaction default-ON: NousResearch/hermes-agent#21193 - Upstream Windows guard: NousResearch/hermes-agent#21561 - 12-Factor App rule III (config in env): https://12factor.net/config Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(hermes-agent): version registry for v0.12 + v0.13 (Wave 2 P2-1) Adds services/agent_version_registry.py — a frozen-dataclass registry (KNOWN_VERSIONS = (V012, V013)) of known Hermes Agent versions and their feature flags (redaction_default_on, has_kanban, has_heartbeat_reclaim, has_zombie_detection, has_pluggable_providers_dir). Pairs with agent_checkout.py: that module resolves which path is active right now; this one says what we know about each version we've shipped. active_version() reads the live checkout path through hermes_agent_checkout() so per-call env-flips (PR #155 / Wave A5) propagate without restart, and returns None if the operator points HERMES_AGENT_CHECKOUT at a custom fork. Reads agent_checkout module-level constants only; does not edit it. Pinned by tests: - KNOWN_VERSIONS = (v0.12@v2026.4.30, v0.13@v2026.5.7) in order. - v0.13.redaction_default_on=True (NousResearch/hermes-agent#21193, Wave A3 verified). - v0.12.redaction_default_on=False (Wave 2 prior swarm Agent 2). - active_version() == v0.13 with env unset (post-PR #160 default). - active_version() == v0.12 when env=hermes-agent-fresh. - active_version() is None for unknown checkouts. - FrozenInstanceError on any field mutation (no cross-version leak). LoC: 89 lines source (67 non-blank/non-comment) + 114 lines tests. Tests: 13/13 pass; combined with test_agent_checkout_resolver.py 24/24 pass. References: - Python @DataClass(frozen=True): https://docs.python.org/3/library/dataclasses.html#frozen-instances - Django AppConfig metadata pattern: https://docs.djangoproject.com/en/5.1/ref/applications/ Handoff: P2-5 (compat matrix) reads KNOWN_VERSIONS for capability rows; P2-6 (proof events) reads active_version().label/upstream_tag for the version_tag field on every event. --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ghenghis
added a commit
that referenced
this pull request
May 10, 2026
* feat(hermes-agent): promote v0.13 to production default (Wave 1 P1-5; 7/7 gates green) Wave 1 of the v0.13 production promotion swarm cleared all 7 hard gates. This PR flips the resolver default from v0.12 (hermes-agent-fresh) to v0.13 (hermes-agent-v013-canary). v0.12 remains the opt-in fallback via HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh. Hard gates (all PASS, evidence below) 1. MiniMax accepted=true — P1-1 (ev_84c2ba93c25d4017) 2. DeepSeek accepted=true — P1-1 (ev_6fa1536b411822db) 3. Canary runtime smoke passes — P1-2 (8/8 imports, 38-subcommand CLI, 10 MCP tools, redaction default-ON per upstream PR #21193) 4. v0.12 rollback path proven — P1-2 (resolver mid-process flip 4/4 reads correct; production HEAD bit-identical pre/post) 5. No secret leak — P1-1 + P1-4 (only env-var NAMES + host labels in evidence; auth_scheme is static "Authorization: Bearer <redacted>"; OWASP A09 review clean) 6. No v0.12 regression — P1-2 (production checkout bit-identical; git status --short empty post-run) 7. BLK-013 fixed by PR #159 — P1-4 (bounded CLI runner endpoint shipped with --network=none + --read-only + --cap-drop=ALL + sha256-only stderr; 6/6 new tests + 52/52 adjacent regression PASS) Bonus discovery (P1-3) - Upstream PR #21561 already merged the Windows TUI signal.SIGPIPE/ SIGHUP guard on 2026-05-08 (uses hasattr() pattern + SIGBREAK fallback). Canary at v2026.5.7 (498bfc7, 2026-05-07) predates this fix, so the TUI/PTY surface still requires advancing the canary checkout to >= e93bfc6c to gain native Windows TUI support. Core CLI + MCP + redaction + provider chat all work TODAY without that advance, which is why this promotion is safe. Patch - DEFAULT_AGENT_CHECKOUT now points to v0.13 (canary path). - New V012_FALLBACK_CHECKOUT constant exposes the v0.12 path for operators + tests that need explicit fallback semantics. - CANARY_AGENT_CHECKOUT retained as alias for back-compat. Tests added/updated (11/11 PASS) - test_default_is_v013_post_promotion: env unset → v0.13 - test_v012_fallback_via_env: env=hermes-agent-fresh → v0.12 - test_resolver_constants_are_correct: DEFAULT == CANARY == v0.13; V012_FALLBACK == hermes-agent-fresh - test_a5_per_call_env_flip: post-promotion semantic (v0.13 ↔ v0.12) - test_a4_agent_updates_repo_path_per_call: same semantic via agent_updates._repo_path() - test_v013_default_when_env_unset: route helper + resolver agree - (4 source-level pin tests retained from PR #155) Verification - py_compile: OK - Focused tests: 11/11 pass - Pre-push hook: passed Rollback - Operators set HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh in the FastAPI process env to revert to v0.12 mid-process (no restart; per-call resolver from PR #155). - Or revert this PR (1 commit) to restore v0.12 as the file-level default. - Production v0.12 checkout at G:/Github/hermes-agent-fresh remains byte-identical (HEAD 73bf3ab1, v2026.4.30, status clean) — never modified by canary work. Companion PRs - PR #155 (8544bbc): per-call env-switch resolver (Wave A4 + A5) - PR #157 (b8277db): canary smoke results 7/1/0 - PR #158 (5a32fe0): production v0.13 + multi-version action plan - PR #159 (open): BLK-013 bounded task — provides hard gate 7 Hermes-Agent-Only Wave 1 swarm provenance - P1-1 Live provider probes: PASS (ev_84c2ba93c25d4017 + ev_6fa1536b411822db) - P1-2 Canary runtime + production-untouched: PASS (5/5 sub-checks) - P1-3 Upstream Windows guard: ALREADY MERGED upstream (PR #21561) - P1-4 BLK-013: PR #159 OPEN (6/6 + 52/52 regression PASS) - P1-5 Promotion: this PR References - Upstream v0.13.0 release: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.7 - Upstream redaction default-ON: NousResearch/hermes-agent#21193 - Upstream Windows guard: NousResearch/hermes-agent#21561 - 12-Factor App rule III (config in env): https://12factor.net/config Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(v0.12-pin): regression-pin 8 fallback surfaces (Wave 2 P2-3) Pin v0.12 (G:/Github/hermes-agent-fresh, v2026.4.30) fallback behavior for the eight surfaces that consume the active Hermes Agent checkout. After PR #160 promoted v0.13 to default, v0.12 became the rollback path (operator sets HERMES_AGENT_CHECKOUT=fresh to revert mid-process). If a future v0.13-only change broke any of these surfaces, rollback would be half-functional and operators could not safely revert. Surfaces pinned (one test each): 1. agent_updates._repo_path() — per-call resolver 2. module_runtime.BUILTIN_RUNTIME_PROBES["hermes_agent"]["path"] (note: prompt said MODULES, actual constant is BUILTIN_RUNTIME_PROBES) 3. code_history.SOURCE_REPOS[id="nous_hermes_agent"].local_path 4. db/load_modules.SOURCE_OVERRIDES["hermes_agent"]["local_path"] 5. _run_update_checks does not crash under v0.12 (canary-venv-free) 6. Provider config (MiniMax + DeepSeek) — config layer only, no HTTP 7. CLI runner detection (OpenCode + OpenHands) — env-only, no PATH dep 8. agent_config.last_run + proof_events writes round-trip cleanly, no v0.13 cross-version contamination at write time Surfaces 2-4 are module-level constants captured at import; the test mutates env then importlib.reload(module) so the literals re-resolve. Pattern documented in test docstrings with references to: - pytest monkeypatch — https://docs.pytest.org/en/stable/how-to/monkeypatch.html - importlib.reload — https://docs.python.org/3/library/importlib.html - nox per-version isolation — https://nox.thea.codes/en/stable/tutorial.html 8/8 pass; 11 existing resolver tests still pass (19/19 combined). No production source modified — read-only on src/, test-only addition. --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ghenghis
added a commit
that referenced
this pull request
May 10, 2026
… P3-4) (#171) * feat(hermes-agent): promote v0.13 to production default (Wave 1 P1-5; 7/7 gates green) Wave 1 of the v0.13 production promotion swarm cleared all 7 hard gates. This PR flips the resolver default from v0.12 (hermes-agent-fresh) to v0.13 (hermes-agent-v013-canary). v0.12 remains the opt-in fallback via HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh. Hard gates (all PASS, evidence below) 1. MiniMax accepted=true — P1-1 (ev_84c2ba93c25d4017) 2. DeepSeek accepted=true — P1-1 (ev_6fa1536b411822db) 3. Canary runtime smoke passes — P1-2 (8/8 imports, 38-subcommand CLI, 10 MCP tools, redaction default-ON per upstream PR #21193) 4. v0.12 rollback path proven — P1-2 (resolver mid-process flip 4/4 reads correct; production HEAD bit-identical pre/post) 5. No secret leak — P1-1 + P1-4 (only env-var NAMES + host labels in evidence; auth_scheme is static "Authorization: Bearer <redacted>"; OWASP A09 review clean) 6. No v0.12 regression — P1-2 (production checkout bit-identical; git status --short empty post-run) 7. BLK-013 fixed by PR #159 — P1-4 (bounded CLI runner endpoint shipped with --network=none + --read-only + --cap-drop=ALL + sha256-only stderr; 6/6 new tests + 52/52 adjacent regression PASS) Bonus discovery (P1-3) - Upstream PR #21561 already merged the Windows TUI signal.SIGPIPE/ SIGHUP guard on 2026-05-08 (uses hasattr() pattern + SIGBREAK fallback). Canary at v2026.5.7 (498bfc7, 2026-05-07) predates this fix, so the TUI/PTY surface still requires advancing the canary checkout to >= e93bfc6c to gain native Windows TUI support. Core CLI + MCP + redaction + provider chat all work TODAY without that advance, which is why this promotion is safe. Patch - DEFAULT_AGENT_CHECKOUT now points to v0.13 (canary path). - New V012_FALLBACK_CHECKOUT constant exposes the v0.12 path for operators + tests that need explicit fallback semantics. - CANARY_AGENT_CHECKOUT retained as alias for back-compat. Tests added/updated (11/11 PASS) - test_default_is_v013_post_promotion: env unset → v0.13 - test_v012_fallback_via_env: env=hermes-agent-fresh → v0.12 - test_resolver_constants_are_correct: DEFAULT == CANARY == v0.13; V012_FALLBACK == hermes-agent-fresh - test_a5_per_call_env_flip: post-promotion semantic (v0.13 ↔ v0.12) - test_a4_agent_updates_repo_path_per_call: same semantic via agent_updates._repo_path() - test_v013_default_when_env_unset: route helper + resolver agree - (4 source-level pin tests retained from PR #155) Verification - py_compile: OK - Focused tests: 11/11 pass - Pre-push hook: passed Rollback - Operators set HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh in the FastAPI process env to revert to v0.12 mid-process (no restart; per-call resolver from PR #155). - Or revert this PR (1 commit) to restore v0.12 as the file-level default. - Production v0.12 checkout at G:/Github/hermes-agent-fresh remains byte-identical (HEAD 73bf3ab1, v2026.4.30, status clean) — never modified by canary work. Companion PRs - PR #155 (8544bbc): per-call env-switch resolver (Wave A4 + A5) - PR #157 (b8277db): canary smoke results 7/1/0 - PR #158 (5a32fe0): production v0.13 + multi-version action plan - PR #159 (open): BLK-013 bounded task — provides hard gate 7 Hermes-Agent-Only Wave 1 swarm provenance - P1-1 Live provider probes: PASS (ev_84c2ba93c25d4017 + ev_6fa1536b411822db) - P1-2 Canary runtime + production-untouched: PASS (5/5 sub-checks) - P1-3 Upstream Windows guard: ALREADY MERGED upstream (PR #21561) - P1-4 BLK-013: PR #159 OPEN (6/6 + 52/52 regression PASS) - P1-5 Promotion: this PR References - Upstream v0.13.0 release: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.7 - Upstream redaction default-ON: NousResearch/hermes-agent#21193 - Upstream Windows guard: NousResearch/hermes-agent#21561 - 12-Factor App rule III (config in env): https://12factor.net/config Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(recovery): pin RC v2 saga semantics across v0.12 + v0.13 (Wave 4 P3-4) Mission: confirm Recovery Controller v2 freeze/thaw + saga compensation behave identically against the v0.12 fallback checkout (G:/Github/hermes-agent-fresh) and the v0.13 production default (G:/Github/hermes-agent-v013-canary). Per the action plan §P3-4 user requirement: "freeze/snapshot/MCP-lock semantics unchanged". This is a TEST-ONLY PR. recovery_controller.py source is NOT modified. New tests (8 logical, 9 collected — test 5 parameterized v012/v013): 1. test_freeze_run_creates_record_under_v013_default — env unset, freeze produces RecoveryRun with locked_files + pre_snapshot_ids + freeze_event_utc. 2. test_freeze_run_creates_record_under_v012_fallback — env=v0.12, identical record shape (full payload-key contract). 3. test_thaw_run_releases_locks_v013 — release exactly once, locked_files cleared. 4. test_thaw_run_releases_locks_v012 — parity with v0.13. 5. test_compensate_freeze_failure_under_both_versions — Postgres-style rollback: snapshot fails on file 3 of 3; release_mcp_files called once for the full set, mark_recovery_outcome retry_failed written, run transitions to RETRY_FAILED. Same on v0.12 + v0.13 (parametrized). 6. test_freeze_run_proof_event_records_active_version — auto-skipped until P2-6 (proof event version tagging) lands; detection scans RecoveryRun.__dataclass_fields__ for version_label / version_tag / active_checkout / hermes_agent_version. 7. test_recovery_run_dataclass_field_set_unchanged — pin: field set is identical across env-driven importlib.reload of recovery_controller. 8. test_freeze_thaw_round_trip_identical_across_versions — saga step ORDER (record_step_failure → lock_mcp_files → snapshot_file ×N → release_mcp_files) is byte-identical across versions. Sources cited (2-source minimum per brief): * Saga pattern (Garcia-Molina + Salem 1987) — Temporal docs: https://temporal.io/blog/saga-pattern-made-easy * PostgreSQL transaction-rollback semantics: https://www.postgresql.org/docs/current/tutorial-transactions.html Constraints honored: * recovery_controller.py source NOT modified. * No filesystem requirement on actual v0.12/v0.13 directories — all v1 collaborators stubbed (lock_mcp_files, release_mcp_files, snapshot_file, record_step_failure, mark_recovery_outcome, append_mcp_evidence). * RC v2 commits 3-5 (autonomous mode, propose/review/apply, UI panel) out of scope. Verification: * New file alone: pytest 8 passed, 1 skipped (test 6 P2-6 fence). * Combined (this file + test_v012_fallback_regression_pin.py + test_v013_default_regression_pin.py + test_agent_checkout_resolver.py + test_recovery_controller_freeze.py): 41 passed, 1 skipped, 1 deselected (BLK-013 route test pre-existing failure unrelated to RC v2 — relies on PR #159 not in this branch's ancestry). Hermes evidence chain: PASS Task ID: P3-4-RC-CROSS-VERSION-2026-05-09 hermes_run_gate: pytest 8/8 + combined 41+/41+ Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ghenghis
added a commit
that referenced
this pull request
May 10, 2026
… of #168] (#173) * feat(hermes-agent): promote v0.13 to production default (Wave 1 P1-5; 7/7 gates green) Wave 1 of the v0.13 production promotion swarm cleared all 7 hard gates. This PR flips the resolver default from v0.12 (hermes-agent-fresh) to v0.13 (hermes-agent-v013-canary). v0.12 remains the opt-in fallback via HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh. Hard gates (all PASS, evidence below) 1. MiniMax accepted=true — P1-1 (ev_84c2ba93c25d4017) 2. DeepSeek accepted=true — P1-1 (ev_6fa1536b411822db) 3. Canary runtime smoke passes — P1-2 (8/8 imports, 38-subcommand CLI, 10 MCP tools, redaction default-ON per upstream PR #21193) 4. v0.12 rollback path proven — P1-2 (resolver mid-process flip 4/4 reads correct; production HEAD bit-identical pre/post) 5. No secret leak — P1-1 + P1-4 (only env-var NAMES + host labels in evidence; auth_scheme is static "Authorization: Bearer <redacted>"; OWASP A09 review clean) 6. No v0.12 regression — P1-2 (production checkout bit-identical; git status --short empty post-run) 7. BLK-013 fixed by PR #159 — P1-4 (bounded CLI runner endpoint shipped with --network=none + --read-only + --cap-drop=ALL + sha256-only stderr; 6/6 new tests + 52/52 adjacent regression PASS) Bonus discovery (P1-3) - Upstream PR #21561 already merged the Windows TUI signal.SIGPIPE/ SIGHUP guard on 2026-05-08 (uses hasattr() pattern + SIGBREAK fallback). Canary at v2026.5.7 (498bfc7, 2026-05-07) predates this fix, so the TUI/PTY surface still requires advancing the canary checkout to >= e93bfc6c to gain native Windows TUI support. Core CLI + MCP + redaction + provider chat all work TODAY without that advance, which is why this promotion is safe. Patch - DEFAULT_AGENT_CHECKOUT now points to v0.13 (canary path). - New V012_FALLBACK_CHECKOUT constant exposes the v0.12 path for operators + tests that need explicit fallback semantics. - CANARY_AGENT_CHECKOUT retained as alias for back-compat. Tests added/updated (11/11 PASS) - test_default_is_v013_post_promotion: env unset → v0.13 - test_v012_fallback_via_env: env=hermes-agent-fresh → v0.12 - test_resolver_constants_are_correct: DEFAULT == CANARY == v0.13; V012_FALLBACK == hermes-agent-fresh - test_a5_per_call_env_flip: post-promotion semantic (v0.13 ↔ v0.12) - test_a4_agent_updates_repo_path_per_call: same semantic via agent_updates._repo_path() - test_v013_default_when_env_unset: route helper + resolver agree - (4 source-level pin tests retained from PR #155) Verification - py_compile: OK - Focused tests: 11/11 pass - Pre-push hook: passed Rollback - Operators set HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh in the FastAPI process env to revert to v0.12 mid-process (no restart; per-call resolver from PR #155). - Or revert this PR (1 commit) to restore v0.12 as the file-level default. - Production v0.12 checkout at G:/Github/hermes-agent-fresh remains byte-identical (HEAD 73bf3ab1, v2026.4.30, status clean) — never modified by canary work. Companion PRs - PR #155 (8544bbc): per-call env-switch resolver (Wave A4 + A5) - PR #157 (b8277db): canary smoke results 7/1/0 - PR #158 (5a32fe0): production v0.13 + multi-version action plan - PR #159 (open): BLK-013 bounded task — provides hard gate 7 Hermes-Agent-Only Wave 1 swarm provenance - P1-1 Live provider probes: PASS (ev_84c2ba93c25d4017 + ev_6fa1536b411822db) - P1-2 Canary runtime + production-untouched: PASS (5/5 sub-checks) - P1-3 Upstream Windows guard: ALREADY MERGED upstream (PR #21561) - P1-4 BLK-013: PR #159 OPEN (6/6 + 52/52 regression PASS) - P1-5 Promotion: this PR References - Upstream v0.13.0 release: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.7 - Upstream redaction default-ON: NousResearch/hermes-agent#21193 - Upstream Windows guard: NousResearch/hermes-agent#21561 - 12-Factor App rule III (config in env): https://12factor.net/config Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(hermes-agent): version registry for v0.12 + v0.13 (Wave 2 P2-1) Adds services/agent_version_registry.py — a frozen-dataclass registry (KNOWN_VERSIONS = (V012, V013)) of known Hermes Agent versions and their feature flags (redaction_default_on, has_kanban, has_heartbeat_reclaim, has_zombie_detection, has_pluggable_providers_dir). Pairs with agent_checkout.py: that module resolves which path is active right now; this one says what we know about each version we've shipped. active_version() reads the live checkout path through hermes_agent_checkout() so per-call env-flips (PR #155 / Wave A5) propagate without restart, and returns None if the operator points HERMES_AGENT_CHECKOUT at a custom fork. Reads agent_checkout module-level constants only; does not edit it. Pinned by tests: - KNOWN_VERSIONS = (v0.12@v2026.4.30, v0.13@v2026.5.7) in order. - v0.13.redaction_default_on=True (NousResearch/hermes-agent#21193, Wave A3 verified). - v0.12.redaction_default_on=False (Wave 2 prior swarm Agent 2). - active_version() == v0.13 with env unset (post-PR #160 default). - active_version() == v0.12 when env=hermes-agent-fresh. - active_version() is None for unknown checkouts. - FrozenInstanceError on any field mutation (no cross-version leak). LoC: 89 lines source (67 non-blank/non-comment) + 114 lines tests. Tests: 13/13 pass; combined with test_agent_checkout_resolver.py 24/24 pass. References: - Python @DataClass(frozen=True): https://docs.python.org/3/library/dataclasses.html#frozen-instances - Django AppConfig metadata pattern: https://docs.djangoproject.com/en/5.1/ref/applications/ Handoff: P2-5 (compat matrix) reads KNOWN_VERSIONS for capability rows; P2-6 (proof events) reads active_version().label/upstream_tag for the version_tag field on every event. * feat(hermes-agent): version-tag proof events with active version + upstream tag (Wave 2 P2-6) Every persisted proof_events row now carries the active Hermes Agent version (v0.12 / v0.13), the upstream tag (v2026.4.30 / v2026.5.7), and the resolved checkout path. Without this, post-promotion forensic queries cannot tell which Hermes Agent version emitted any given event — a gap that becomes load-bearing the moment an operator flips HERMES_AGENT_CHECKOUT mid-process (per-call resolver, PR #155). Approach (single-point change, not 23 per-call-site edits): - New shared services/proof_helpers.py exposes proof_version_fields() and attach_version_fields(payload). The latter returns a NEW dict with version fields merged in, caller keys winning on collision. - Three identical _append_proof_event helpers (agent_updates.py / desktop_updates.py / jobs.py) augmented at the single SQL-insertion site. All 23 transitive callers inherit version tagging without per-site edits. Backward compat: legacy rows have no version_label key. Reader code must use payload.get("version_label", "unknown") semantics. Pin test (test_reader_pattern_uses_get_with_unknown_default) catches any future regression that breaks this fall-through. Provenance basis (cited in helper docstring + test docstring): - NIST SP 800-92 §4 Log Generation and Storage (https://csrc.nist.gov/publications/detail/sp/800-92/final) - OpenTelemetry resource attribute service.version (https://opentelemetry.io/docs/specs/semconv/resource/#service) Tests: 13 new in test_proof_event_version_tagging.py. Suite: pytest test_agent_version_registry.py + test_agent_checkout_resolver.py + test_proof_event_version_tagging.py = 37 passed in 1.46s. Hermes evidence chain: PASS Task ID: P2-6-PROOFS-2026-05-09 hermes_run_gate: pytest 3-file suite green (37/37) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ghenghis
added a commit
that referenced
this pull request
May 10, 2026
…3-5) [re-target of #170] (#174) * feat(hermes-agent): promote v0.13 to production default (Wave 1 P1-5; 7/7 gates green) Wave 1 of the v0.13 production promotion swarm cleared all 7 hard gates. This PR flips the resolver default from v0.12 (hermes-agent-fresh) to v0.13 (hermes-agent-v013-canary). v0.12 remains the opt-in fallback via HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh. Hard gates (all PASS, evidence below) 1. MiniMax accepted=true — P1-1 (ev_84c2ba93c25d4017) 2. DeepSeek accepted=true — P1-1 (ev_6fa1536b411822db) 3. Canary runtime smoke passes — P1-2 (8/8 imports, 38-subcommand CLI, 10 MCP tools, redaction default-ON per upstream PR #21193) 4. v0.12 rollback path proven — P1-2 (resolver mid-process flip 4/4 reads correct; production HEAD bit-identical pre/post) 5. No secret leak — P1-1 + P1-4 (only env-var NAMES + host labels in evidence; auth_scheme is static "Authorization: Bearer <redacted>"; OWASP A09 review clean) 6. No v0.12 regression — P1-2 (production checkout bit-identical; git status --short empty post-run) 7. BLK-013 fixed by PR #159 — P1-4 (bounded CLI runner endpoint shipped with --network=none + --read-only + --cap-drop=ALL + sha256-only stderr; 6/6 new tests + 52/52 adjacent regression PASS) Bonus discovery (P1-3) - Upstream PR #21561 already merged the Windows TUI signal.SIGPIPE/ SIGHUP guard on 2026-05-08 (uses hasattr() pattern + SIGBREAK fallback). Canary at v2026.5.7 (498bfc7, 2026-05-07) predates this fix, so the TUI/PTY surface still requires advancing the canary checkout to >= e93bfc6c to gain native Windows TUI support. Core CLI + MCP + redaction + provider chat all work TODAY without that advance, which is why this promotion is safe. Patch - DEFAULT_AGENT_CHECKOUT now points to v0.13 (canary path). - New V012_FALLBACK_CHECKOUT constant exposes the v0.12 path for operators + tests that need explicit fallback semantics. - CANARY_AGENT_CHECKOUT retained as alias for back-compat. Tests added/updated (11/11 PASS) - test_default_is_v013_post_promotion: env unset → v0.13 - test_v012_fallback_via_env: env=hermes-agent-fresh → v0.12 - test_resolver_constants_are_correct: DEFAULT == CANARY == v0.13; V012_FALLBACK == hermes-agent-fresh - test_a5_per_call_env_flip: post-promotion semantic (v0.13 ↔ v0.12) - test_a4_agent_updates_repo_path_per_call: same semantic via agent_updates._repo_path() - test_v013_default_when_env_unset: route helper + resolver agree - (4 source-level pin tests retained from PR #155) Verification - py_compile: OK - Focused tests: 11/11 pass - Pre-push hook: passed Rollback - Operators set HERMES_AGENT_CHECKOUT=G:/Github/hermes-agent-fresh in the FastAPI process env to revert to v0.12 mid-process (no restart; per-call resolver from PR #155). - Or revert this PR (1 commit) to restore v0.12 as the file-level default. - Production v0.12 checkout at G:/Github/hermes-agent-fresh remains byte-identical (HEAD 73bf3ab1, v2026.4.30, status clean) — never modified by canary work. Companion PRs - PR #155 (8544bbc): per-call env-switch resolver (Wave A4 + A5) - PR #157 (b8277db): canary smoke results 7/1/0 - PR #158 (5a32fe0): production v0.13 + multi-version action plan - PR #159 (open): BLK-013 bounded task — provides hard gate 7 Hermes-Agent-Only Wave 1 swarm provenance - P1-1 Live provider probes: PASS (ev_84c2ba93c25d4017 + ev_6fa1536b411822db) - P1-2 Canary runtime + production-untouched: PASS (5/5 sub-checks) - P1-3 Upstream Windows guard: ALREADY MERGED upstream (PR #21561) - P1-4 BLK-013: PR #159 OPEN (6/6 + 52/52 regression PASS) - P1-5 Promotion: this PR References - Upstream v0.13.0 release: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.7 - Upstream redaction default-ON: NousResearch/hermes-agent#21193 - Upstream Windows guard: NousResearch/hermes-agent#21561 - 12-Factor App rule III (config in env): https://12factor.net/config Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(hermes-agent): version registry for v0.12 + v0.13 (Wave 2 P2-1) Adds services/agent_version_registry.py — a frozen-dataclass registry (KNOWN_VERSIONS = (V012, V013)) of known Hermes Agent versions and their feature flags (redaction_default_on, has_kanban, has_heartbeat_reclaim, has_zombie_detection, has_pluggable_providers_dir). Pairs with agent_checkout.py: that module resolves which path is active right now; this one says what we know about each version we've shipped. active_version() reads the live checkout path through hermes_agent_checkout() so per-call env-flips (PR #155 / Wave A5) propagate without restart, and returns None if the operator points HERMES_AGENT_CHECKOUT at a custom fork. Reads agent_checkout module-level constants only; does not edit it. Pinned by tests: - KNOWN_VERSIONS = (v0.12@v2026.4.30, v0.13@v2026.5.7) in order. - v0.13.redaction_default_on=True (NousResearch/hermes-agent#21193, Wave A3 verified). - v0.12.redaction_default_on=False (Wave 2 prior swarm Agent 2). - active_version() == v0.13 with env unset (post-PR #160 default). - active_version() == v0.12 when env=hermes-agent-fresh. - active_version() is None for unknown checkouts. - FrozenInstanceError on any field mutation (no cross-version leak). LoC: 89 lines source (67 non-blank/non-comment) + 114 lines tests. Tests: 13/13 pass; combined with test_agent_checkout_resolver.py 24/24 pass. References: - Python @DataClass(frozen=True): https://docs.python.org/3/library/dataclasses.html#frozen-instances - Django AppConfig metadata pattern: https://docs.djangoproject.com/en/5.1/ref/applications/ Handoff: P2-5 (compat matrix) reads KNOWN_VERSIONS for capability rows; P2-6 (proof events) reads active_version().label/upstream_tag for the version_tag field on every event. * docs+feat(hermes-agent): provider compat matrix per version (Wave 4 P3-5) Adds per-version provider compatibility table sibling to the P2-1 agent_version_registry. Frozen-tuple shape, no mutation of P2-1's registry. Documents which providers are reachable on Hermes Agent v0.12 vs v0.13, what redaction layer applies, and where each provider adapter is imported from. Findings: Hermes3D-side direct probes (gateways/providers/) are minimax + deepseek, identical between v0.12 and v0.13 (those modules are Hermes3D code, not vendored from upstream). Smoke 3 + Smoke 4 PASS (2026-05-09). Upstream agent/models_dev.py:PROVIDER_TO_MODELS_DEV — 33 entries, byte-identical between v0.12 and v0.13. Cross-version diff is BEHAVIOURAL: agent/redact.py default flipped OFF -> ON in v0.13 (upstream issue #21193). OpenCode + OpenHands are CLI runners (services/code_history.py), not LLM providers. Module: services/agent_version_provider_compat.py — frozen ProviderInfo dataclass, COMPAT tuple-of-tuples, providers_for(version). Doc: HERMES_AGENT_PROVIDER_COMPAT_MATRIX_2026-05-09.md (~2400 words). Tests: 14/14 pass; combined with registry tests 27/27 pass. Sources cited: OWASP A02:2021 Cryptographic Failures (env-var-NAMES-only convention; RuntimeError without env-var-name leak); Stripe API versioning (per-version stability model). LoC: 134 source + 260 tests + 2421-word doc. Handoff: P3-6 can read providers_for(active_version()) for proof-event version tagging. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
20-agent action plan to (a) promote v0.13 from canary to production, (b) keep v0.12 fully operational as fallback, and (c) prepare a forward pipeline for v0.14+ when it tags upstream.
Pipelines (3, run in parallel waves)
4-Wave sequencing
Hard gates (must clear before production)
accepted=true+ redacted evidencetui_gateway/entry.py:143-145Windows guard merges OR explicit operator approval to ship without TUI/PTY surfaceStop-conditions
Out of scope (strictly)
GUI/Playwright, 60-app, printer safety, RC v2 commits 3-5, non-Hermes-Agent Bonus 12 follow-ups.
This plan does NOT execute
Awaiting user approval to launch Wave 1.
Estimated PR count when executed: 6-10 across the 4 waves.
🤖 Generated with Claude Code