docs(roadmap): TEA plugin shipped (experimental)#2
Conversation
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
WalkthroughThe ChangesTEA Roadmap Entry Update
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
🤖 Augment PR SummarySummary: Updates the roadmap’s TEA/testarch item to reflect that the experimental opt-in 🤖 Was this summary useful? React with 👍 or 👎 |
| **Status:** exploring · **Foundation:** experimental opt-in `tea` plugin landed (v0.5.1) | ||
|
|
||
| The bundled, **experimental** `tea` plugin (`[plugins] enabled = ["tea"]`, see the | ||
| [TEA plugin guide](tea-plugin-guide.md)) now wires the BMAD Test Architect (TEA) suite — |
There was a problem hiding this comment.
docs/ROADMAP.md:61 This section calls it the “BMAD Test Architect (TEA)” suite, but the TEA plugin guide/changelog use “Test Architect Enterprise (TEA)”; consider aligning terminology so readers don’t think this is a different module.
Severity: low
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
|
|
||
| The bundled, **experimental** `tea` plugin (`[plugins] enabled = ["tea"]`, see the | ||
| [TEA plugin guide](tea-plugin-guide.md)) now wires the BMAD Test Architect (TEA) suite — | ||
| `bmad-testarch-test-design`, `-automate`, `-atdd`, `-nfr`, `-trace`, `-test-review`, and the |
There was a problem hiding this comment.
docs/ROADMAP.md:62 The workflow list mixes a full name (bmad-testarch-test-design) with shorthand entries like -automate/-atdd; consider spelling out the full workflow names to avoid readers interpreting the hyphen items as flags/options (and to match the TEA plugin guide’s table).
Severity: low
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/ROADMAP.md`:
- Around line 61-65: The enumerated TEA workflow commands in lines 62-63 of the
ROADMAP.md file are incorrectly listed with incomplete naming. Replace the
abbreviated command references (prefixed with just hyphens like `-automate`,
`-atdd`, `-nfr`, `-trace`, `-test-review`) with the correct full skill names
following the `bmad-testarch-` prefix pattern to match the actual plugin
configuration (e.g., `bmad-testarch-atdd`, `bmad-testarch-automate`,
`bmad-testarch-trace`, `bmad-testarch-nfr`, `bmad-testarch-test-review`). Also
remove the reference to the non-existent "bmad-tea agent" and ensure the list
accurately reflects only the actual workflows defined in the TEA plugin
configuration.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
| [TEA plugin guide](tea-plugin-guide.md)) now wires the BMAD Test Architect (TEA) suite — | ||
| `bmad-testarch-test-design`, `-automate`, `-atdd`, `-nfr`, `-trace`, `-test-review`, and the | ||
| `bmad-tea` agent — into every run and sweep as **advisory-by-default** quality steps (the three | ||
| gate steps can be flipped to blocking). It's experimental: the workflows ride the generic | ||
| `[workflows.<name>]` session-injection layer rather than being first-class orchestrated runs. |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Search for TEA plugin definition, gate step configuration, or plugin version reference.
# Expected: Find plugin.toml, pyproject.toml, or other config that defines TEA v0.5.1, its commands, and gate steps.
rg -nC3 'tea.*plugin|gate.*step|bmad-testarch|bmad-tea' \
--glob '*plugin*' --glob '*pyproject*' --glob '*setup*' --glob '*tea*' \
| head -100Repository: bmad-code-org/bmad-auto
Length of output: 8752
🏁 Script executed:
cat -n src/automator/data/plugins/tea/plugin.toml | tail -50Repository: bmad-code-org/bmad-auto
Length of output: 3138
🏁 Script executed:
grep -n "review_enabled\|bmad-tea\|bmad-testarch-" src/automator/data/plugins/tea/plugin.tomlRepository: bmad-code-org/bmad-auto
Length of output: 2622
Correct the enumerated TEA commands to match the actual skill names.
The GATE_STEPS configuration correctly defines three gate steps (trace, nfr, review), but the command enumeration in lines 62–63 is inaccurate. The actual TEA workflows are named bmad-testarch-test-design, bmad-testarch-atdd, bmad-testarch-automate, bmad-testarch-trace, bmad-testarch-nfr, and bmad-testarch-test-review. The review comment incorrectly lists them with hyphens (-automate, -atdd, -nfr, -trace, -test-review) and references a "bmad-tea agent" that does not correspond to any workflow defined in the plugin configuration. Update lines 62–63 to use the correct skill names.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@docs/ROADMAP.md` around lines 61 - 65, The enumerated TEA workflow commands
in lines 62-63 of the ROADMAP.md file are incorrectly listed with incomplete
naming. Replace the abbreviated command references (prefixed with just hyphens
like `-automate`, `-atdd`, `-nfr`, `-trace`, `-test-review`) with the correct
full skill names following the `bmad-testarch-` prefix pattern to match the
actual plugin configuration (e.g., `bmad-testarch-atdd`,
`bmad-testarch-automate`, `bmad-testarch-trace`, `bmad-testarch-nfr`,
`bmad-testarch-test-review`). Also remove the reference to the non-existent
"bmad-tea agent" and ensure the list accurately reflects only the actual
workflows defined in the TEA plugin configuration.
redact_home mapped backslash, forward-slash, case-variant, git-bash and cygwin spellings of the Windows home dir but not the WSL /mnt/<drive>/Users/<user>/ spelling. Add it so probe display fidelity is preserved for WSL-origin paths (the username was already stripped — this is display-fidelity, not a PII fix). Refs: _bmad-output/implementation-artifacts/deferred-work.md (deferred-work.md, Windows test-suite greening residuals bmad-code-org#2) Claude-Session: https://claude.ai/code/session_019ohWeC44Mto4upsYNNaVh8
…findings (#276) A second-model adversarial review of PR #277 surfaced 7 valid findings. This lands the fixes for six of them (the 7th, a repo-wide policy-coercion consistency issue, is deferred to a follow-up): - #1 (High) M2 transition now outranks the M1 hash gate. A clean review that round-trips done->in-review->done back to byte-identical launch bytes while omitting its marker no longer false-refuses; the hash gate refuses only when no transition was observed. Safe: the dead-window false positive never records a transition (status never leaves `done`). - #2 (High) The stories-mode folder+id read-back now applies the same launch-snapshot gate, closing the identical false completion it previously bypassed (it accepted on the mtime floor alone). Inert on a dev leg (no snapshot). - #3 (High) The three in-place spec rewriters (append/strip/reset) now write atomically (temp + atomic_replace), so an interrupted/disk-full repair leaves the original spec intact instead of truncated. - #4 (Med) Adds engine-level coverage of the synthesized-REVIEW repair path (including a follow-up review that rewrites the spec) plus regressions for #1/#2/#3/#5/#7 and a _snapshot_verdict truth-table. - #5 (Low) Snapshot/candidate identity is now by resolved filesystem path (_same_spec), not raw string spelling, so a `..`/symlink/case alias can't disable M1/M2. - #7 (Low) A spec ending in a bare `\r` no longer receives an invisible heading (completed to CRLF so the scan's `^` regex sees it). #1 and #2 share a single `_snapshot_verdict` helper so the "M2 outranks M1" rule can't drift between the two paths. All edits sit on `_DevSynthesisMixin`, covering both the tmux and OpenCode adapters.
Updates the TEA / testarch roadmap item to reflect that the experimental
teaplugin shipped in 0.5.1.The section described the TEA suite as something "the orchestrator doesn't yet use" — now stale. It's reframed to mirror the sibling Unity roadmap item's
**Foundation:** … landed+ "remaining work" pattern: the experimental opt-in plugin now injects the TEA workflows as advisory-by-default steps, while first-class orchestratedtestruns remain the open "exploring" work.Docs-only; no version change.
🤖 Generated with Claude Code
Summary by CodeRabbit