## Summary

Adds shadow-mode AI advisor dispatch to the autorevert lambda. When a
clean failure partition is detected (2+ failures, 1+ success, no unknown
gap), the lambda dispatches the `claude-autorevert-advisor.yml` workflow
([pytorch/pytorch#177404](pytorch/pytorch#177404))
for AI-powered failure analysis.

Shadow mode: verdicts are not consumed — dispatch is fire-and-forget for
accuracy data collection.

## Changes

- `DispatchAdvisor` dataclass emitted from
`process_valid_autorevert_pattern()` (pure functional)
- `SignalActionProcessor.dispatch_advisors()` — shuffled dispatch with
per-signal dedup and cap (8 per workflow+commit)
- `AdvisorAction` enum (skip/log/run), CLI `--advisor-action`, env
`ADVISOR_ACTION`
- Logged to `misc.autorevert_events_v2` as `action='advisor'`
- Signal pattern JSON written to `/tmp/advisor-patterns/` for debugging
- HUD: "AI" badge on outcome cells + advisor dispatch summary table
- State JSON: optional `advisor_dispatches` key (forward/backward
compatible)
- Default: `AdvisorAction.RUN` (lambda dispatches advisors on deploy, no
gha-infra changes needed)

## Test plan

- [x] 122 tests passing (19 new covering DispatchAdvisor,
execute_advisor, dispatch_advisors, signal pattern JSON, cap/dedup)
- [ ] Deploy and monitor shadow-mode dispatches via ClickHouse + HUD

PR #177404 added the claude-autorevert-advisor workflow but missed the
`allowed_bots` input on the `anthropics/claude-code-action@v1` step.
Without this, the action rejects runs triggered by
`pytorch-auto-revert[bot]`, which is the bot that dispatches this
workflow.

Add `allowed_bots: "pytorch-auto-revert[bot]"` so the action accepts
these bot-triggered runs.

## Summary

Adds a `workflow_dispatch` workflow that the autorevert system can trigger when it detects an early failure pattern. Claude Opus 4.6 analyzes the suspect commit's diff, failed job logs, and PyTorch source code to determine whether the commit actually caused the CI failures.

Returns a structured JSON verdict as an artifact:
- **revert** — causal chain found, proceed to revert immediately
- **unsure** — inconclusive, continue with restart-to-confirm (default behavior unchanged)
- **not_related** — failures unrelated to the change, ignore this signal
- **garbage** — signal is unreliable (infra flake, driver crash), suppress for ~2 hours

Design doc: https://docs.google.com/document/d/1BA9B7cIIKiapI37fSFGDD7D0F-VwMyRKJW0PoS0KkbY/edit

## Evaluation Results (13/13 correct verdicts)

Prototyped and tested on [pytorch/ciforge](https://github.com/pytorch/ciforge). Results across diverse failure types:

### Round 1 (2026-03-12) — 4/4 correct

| Test Case | PR | Failure | Expected | Actual | Job |
|-----------|-----|---------|----------|--------|-----|
| Doc-only change | pytorch#177288 | pca_lowrank stride mismatch | not_related | **not_related @ 0.99** | [job](https://github.com/pytorch/ciforge/actions/runs/23016718498) |
| Dynamo einops fix | pytorch#177165 | detectron2 graph_breaks + test_is_nonzero_mps | not_related | **not_related @ 0.93** | [job](https://github.com/pytorch/ciforge/actions/runs/23016730498) |
| MPS cdouble guard | pytorch#176985 | test_is_nonzero_mps + pca_lowrank | revert | **revert @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23016740133) |
| Lint missing import | pytorch#176613 | Lint / lintrunner-noclang-all | revert | **revert @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23013529685) |

### Round 2 (2026-03-13, automated hourly loop) — 9/9 correct (1 cancelled)

| Timestamp | PR | Signal Key | Expected | Actual | Job |
|-----------|-----|-----------|----------|--------|-----|
| 03:12Z | pytorch#176613 | Lint / lintrunner-noclang-all | revert | **revert @ 0.98** | [job](https://github.com/pytorch/ciforge/actions/runs/23034497618) |
| 03:12Z | pytorch#176613 | fsdp/test_fully_shard_comm (test exec) | revert | **revert @ 0.98** | [job](https://github.com/pytorch/ciforge/actions/runs/23034499988) |
| 09:11Z | pytorch#177273 | test-timeout-270min (infra) | — | *cancelled* | [job](https://github.com/pytorch/ciforge/actions/runs/23043982417) |
| 10:12Z | pytorch#176019 | AllenaiLongformerBase fail_to_run (periodic) | garbage | **garbage @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23046142800) |
| 10:12Z | pytorch#176019 | detectron2_fcos IMPROVED (periodic) | not_related | **not_related @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23046144261) |
| 11:10Z | pytorch#176019 | functorch_dp_cifar10 fail_accuracy (periodic) | not_related | **not_related @ 0.93** | [job](https://github.com/pytorch/ciforge/actions/runs/23048173319) |
| 11:10Z | pytorch#176019 | basic_gnn_edgecnn IMPROVED (periodic) | not_related | **not_related @ 0.92** | [job](https://github.com/pytorch/ciforge/actions/runs/23048174698) |
| 15:09Z | pytorch#177096 | S3 PutObject IAM denied - ROCm gfx950 (infra) | garbage | **garbage @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23057146500) |
| 16:09Z | pytorch#176019 | vit_base_patch16_siglip_256 fail_to_run (periodic) | not_related | **not_related @ 0.97** | [job](https://github.com/pytorch/ciforge/actions/runs/23059634364) |
| 16:09Z | pytorch#176019 | shufflenet_v2_x1_0 fail_accuracy (periodic) | not_related | **not_related @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23059635765) |

### Summary by verdict type

| Verdict | Count | Correct | Avg Confidence |
|---------|-------|---------|----------------|
| revert | 4 | 4/4 | 0.97 |
| garbage | 2 | 2/2 | 0.95 |
| not_related | 7 | 7/7 | 0.94 |

## Test plan

- [x] Prototyped and tested on pytorch/ciforge with 13 real trunk failure cases
- [x] Verified structured JSON output matches schema
- [x] Verified verdict artifact uploads correctly
- [ ] Trigger via GitHub UI with `workflow_dispatch` on pytorch/pytorch to validate bedrock environment works
- [ ] Integrate dispatch call into autorevert lambda (follow-up)
Pull Request resolved: pytorch#177404
Approved by: https://github.com/wdvr

## Summary

- Adds `'advisor' = 3` to the `action` Enum8 column in
`misc.autorevert_events_v2`

The autorevert AI advisor lambda ([pytorch/pytorch PR
#177404](pytorch/pytorch#177404)) writes
`action='advisor'` when logging dispatch events to ClickHouse. However,
the table's Enum8 only accepted `none`, `restart`, `revert` — causing
ClickHouse to silently store advisor rows as `action='none'`.

This broke `prior_advisor_exists()` and `advisor_count_for_commit()`
which query `WHERE action = 'advisor'` — they always returned false/0,
so the lambda re-dispatched the advisor workflow for the same (commit,
signal) every ~5 minutes indefinitely.

Already applied live:
```sql
ALTER TABLE misc.autorevert_events_v2
  MODIFY COLUMN `action` Enum8('none' = 0, 'restart' = 1, 'revert' = 2, 'advisor' = 3)
```

## Test plan
- [x] Verify schema file matches expected Enum values
- [x] Apply ALTER TABLE on the live ClickHouse instance
- [ ] Confirm subsequent advisor dispatches create rows with
`action='advisor'`
- [ ] Confirm `prior_advisor_exists()` returns true after first
dispatch, preventing duplicates

PR #177404 added the claude-autorevert-advisor workflow but missed the
`allowed_bots` input on the `anthropics/claude-code-action@v1` step.
Without this, the action rejects runs triggered by
`pytorch-auto-revert[bot]`, which is the bot that dispatches this
workflow.

Add `allowed_bots: "pytorch-auto-revert[bot]"` so the action accepts
these bot-triggered runs.

Co-authored-by: Xia-Weiwen <12522207+Xia-Weiwen@users.noreply.github.com>

## Summary

Adds shadow-mode AI advisor dispatch to the autorevert lambda. When a
clean failure partition is detected (2+ failures, 1+ success, no unknown
gap), the lambda dispatches the `claude-autorevert-advisor.yml` workflow
([pytorch/pytorch#177404](pytorch/pytorch#177404))
for AI-powered failure analysis.

Shadow mode: verdicts are not consumed — dispatch is fire-and-forget for
accuracy data collection.

## Changes

- `DispatchAdvisor` dataclass emitted from
`process_valid_autorevert_pattern()` (pure functional)
- `SignalActionProcessor.dispatch_advisors()` — shuffled dispatch with
per-signal dedup and cap (8 per workflow+commit)
- `AdvisorAction` enum (skip/log/run), CLI `--advisor-action`, env
`ADVISOR_ACTION`
- Logged to `misc.autorevert_events_v2` as `action='advisor'`
- Signal pattern JSON written to `/tmp/advisor-patterns/` for debugging
- HUD: "AI" badge on outcome cells + advisor dispatch summary table
- State JSON: optional `advisor_dispatches` key (forward/backward
compatible)
- Default: `AdvisorAction.RUN` (lambda dispatches advisors on deploy, no
gha-infra changes needed)

## Test plan

- [x] 122 tests passing (19 new covering DispatchAdvisor,
execute_advisor, dispatch_advisors, signal pattern JSON, cap/dedup)
- [ ] Deploy and monitor shadow-mode dispatches via ClickHouse + HUD

## Summary

- Adds `'advisor' = 3` to the `action` Enum8 column in
`misc.autorevert_events_v2`

The autorevert AI advisor lambda ([pytorch/pytorch PR
#177404](pytorch/pytorch#177404)) writes
`action='advisor'` when logging dispatch events to ClickHouse. However,
the table's Enum8 only accepted `none`, `restart`, `revert` — causing
ClickHouse to silently store advisor rows as `action='none'`.

This broke `prior_advisor_exists()` and `advisor_count_for_commit()`
which query `WHERE action = 'advisor'` — they always returned false/0,
so the lambda re-dispatched the advisor workflow for the same (commit,
signal) every ~5 minutes indefinitely.

Already applied live:
```sql
ALTER TABLE misc.autorevert_events_v2
  MODIFY COLUMN `action` Enum8('none' = 0, 'restart' = 1, 'revert' = 2, 'advisor' = 3)
```

## Test plan
- [x] Verify schema file matches expected Enum values
- [x] Apply ALTER TABLE on the live ClickHouse instance
- [ ] Confirm subsequent advisor dispatches create rows with
`action='advisor'`
- [ ] Confirm `prior_advisor_exists()` returns true after first
dispatch, preventing duplicates

## Summary

Adds a `workflow_dispatch` workflow that the autorevert system can trigger when it detects an early failure pattern. Claude Opus 4.6 analyzes the suspect commit's diff, failed job logs, and PyTorch source code to determine whether the commit actually caused the CI failures.

Returns a structured JSON verdict as an artifact:
- **revert** — causal chain found, proceed to revert immediately
- **unsure** — inconclusive, continue with restart-to-confirm (default behavior unchanged)
- **not_related** — failures unrelated to the change, ignore this signal
- **garbage** — signal is unreliable (infra flake, driver crash), suppress for ~2 hours

Design doc: https://docs.google.com/document/d/1BA9B7cIIKiapI37fSFGDD7D0F-VwMyRKJW0PoS0KkbY/edit

## Evaluation Results (13/13 correct verdicts)

Prototyped and tested on [pytorch/ciforge](https://github.com/pytorch/ciforge). Results across diverse failure types:

### Round 1 (2026-03-12) — 4/4 correct

| Test Case | PR | Failure | Expected | Actual | Job |
|-----------|-----|---------|----------|--------|-----|
| Doc-only change | pytorch#177288 | pca_lowrank stride mismatch | not_related | **not_related @ 0.99** | [job](https://github.com/pytorch/ciforge/actions/runs/23016718498) |
| Dynamo einops fix | pytorch#177165 | detectron2 graph_breaks + test_is_nonzero_mps | not_related | **not_related @ 0.93** | [job](https://github.com/pytorch/ciforge/actions/runs/23016730498) |
| MPS cdouble guard | pytorch#176985 | test_is_nonzero_mps + pca_lowrank | revert | **revert @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23016740133) |
| Lint missing import | pytorch#176613 | Lint / lintrunner-noclang-all | revert | **revert @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23013529685) |

### Round 2 (2026-03-13, automated hourly loop) — 9/9 correct (1 cancelled)

| Timestamp | PR | Signal Key | Expected | Actual | Job |
|-----------|-----|-----------|----------|--------|-----|
| 03:12Z | pytorch#176613 | Lint / lintrunner-noclang-all | revert | **revert @ 0.98** | [job](https://github.com/pytorch/ciforge/actions/runs/23034497618) |
| 03:12Z | pytorch#176613 | fsdp/test_fully_shard_comm (test exec) | revert | **revert @ 0.98** | [job](https://github.com/pytorch/ciforge/actions/runs/23034499988) |
| 09:11Z | pytorch#177273 | test-timeout-270min (infra) | — | *cancelled* | [job](https://github.com/pytorch/ciforge/actions/runs/23043982417) |
| 10:12Z | pytorch#176019 | AllenaiLongformerBase fail_to_run (periodic) | garbage | **garbage @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23046142800) |
| 10:12Z | pytorch#176019 | detectron2_fcos IMPROVED (periodic) | not_related | **not_related @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23046144261) |
| 11:10Z | pytorch#176019 | functorch_dp_cifar10 fail_accuracy (periodic) | not_related | **not_related @ 0.93** | [job](https://github.com/pytorch/ciforge/actions/runs/23048173319) |
| 11:10Z | pytorch#176019 | basic_gnn_edgecnn IMPROVED (periodic) | not_related | **not_related @ 0.92** | [job](https://github.com/pytorch/ciforge/actions/runs/23048174698) |
| 15:09Z | pytorch#177096 | S3 PutObject IAM denied - ROCm gfx950 (infra) | garbage | **garbage @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23057146500) |
| 16:09Z | pytorch#176019 | vit_base_patch16_siglip_256 fail_to_run (periodic) | not_related | **not_related @ 0.97** | [job](https://github.com/pytorch/ciforge/actions/runs/23059634364) |
| 16:09Z | pytorch#176019 | shufflenet_v2_x1_0 fail_accuracy (periodic) | not_related | **not_related @ 0.95** | [job](https://github.com/pytorch/ciforge/actions/runs/23059635765) |

### Summary by verdict type

| Verdict | Count | Correct | Avg Confidence |
|---------|-------|---------|----------------|
| revert | 4 | 4/4 | 0.97 |
| garbage | 2 | 2/2 | 0.95 |
| not_related | 7 | 7/7 | 0.94 |

## Test plan

- [x] Prototyped and tested on pytorch/ciforge with 13 real trunk failure cases
- [x] Verified structured JSON output matches schema
- [x] Verified verdict artifact uploads correctly
- [ ] Trigger via GitHub UI with `workflow_dispatch` on pytorch/pytorch to validate bedrock environment works
- [ ] Integrate dispatch call into autorevert lambda (follow-up)
Pull Request resolved: pytorch#177404
Approved by: https://github.com/wdvr

PR pytorch#177404 added the claude-autorevert-advisor workflow but missed the
`allowed_bots` input on the `anthropics/claude-code-action@v1` step.
Without this, the action rejects runs triggered by
`pytorch-auto-revert[bot]`, which is the bot that dispatches this
workflow.

Add `allowed_bots: "pytorch-auto-revert[bot]"` so the action accepts
these bot-triggered runs.

PR pytorch#177404 added the claude-autorevert-advisor workflow but missed the
`allowed_bots` input on the `anthropics/claude-code-action@v1` step.
Without this, the action rejects runs triggered by
`pytorch-auto-revert[bot]`, which is the bot that dispatches this
workflow.

Add `allowed_bots: "pytorch-auto-revert[bot]"` so the action accepts
these bot-triggered runs.

PR pytorch#177404 added the claude-autorevert-advisor workflow but missed the
`allowed_bots` input on the `anthropics/claude-code-action@v1` step.
Without this, the action rejects runs triggered by
`pytorch-auto-revert[bot]`, which is the bot that dispatches this
workflow.

Add `allowed_bots: "pytorch-auto-revert[bot]"` so the action accepts
these bot-triggered runs.