@syntesseraai/opencode-feature-factory 0.6.6 → 0.6.7

package/README.md

@@ -46,6 +46,7 @@ It also updates `~/.config/opencode/opencode.json` non-destructively by merging
 - `/pipeline/planning/run`, `/pipeline/planning/run-opus`, `/pipeline/planning/run-gemini`, `/pipeline/planning/run-codex`, `/pipeline/planning/synthesize`, `/pipeline/planning/gate`
 - `/pipeline/building/run`, `/pipeline/building/breakdown`, `/pipeline/building/validate-batch`, `/pipeline/building/implement-batch`
 - `/pipeline/reviewing/run`, `/pipeline/reviewing/triage`, `/pipeline/reviewing/run-opus`, `/pipeline/reviewing/run-gemini`, `/pipeline/reviewing/run-codex`, `/pipeline/reviewing/synthesize`, `/pipeline/reviewing/gate`
+- `/pipeline/documentation/run`, `/pipeline/documentation/run-codex`, `/pipeline/documentation/run-gemini`, `/pipeline/documentation/gate`
 - `/pipeline/complete`
 
 ## Model Split
@@ -55,11 +56,14 @@ It also updates `~/.config/opencode/opencode.json` non-destructively by merging
 - Implementation: Codex only
 - Review (with architecture validation): Codex, Gemini, and Opus
 - Rework path: `/pipeline/reviewing/run` re-enters implementation via `/pipeline/building/implement-batch` when gate status is `REWORK`
+- Documentation stage: Codex updates documentation, Gemini reviews docs, and ChatGPT 5.4 supervises a bounded loop until approved
+- Documentation stage skill usage: Codex loads `ff-context-tracking`, `ff-todo-management`, `ff-mini-plan`; Gemini loads `ff-report-templates` and `ff-severity-classification`
 
 ## Quality Gates
 
 - Planning approval: `>=75%` consensus.
 - Review approval: `>=95%` confidence and zero unresolved issues.
+- Documentation approval: Gemini verdict `APPROVED` with zero unresolved documentation issues.
 - Planning loop confirmation: after 5 unsuccessful planning iterations, pipeline asks user whether to continue.
 
 ## Related Docs

package/agents/pipeline.md

@@ -51,6 +51,7 @@ Do not keep orchestration logic in this file. The workflow lives in:
 - `/pipeline/planning/*`
 - `/pipeline/building/*`
 - `/pipeline/reviewing/*`
+- `/pipeline/documentation/*`
 - `/pipeline/complete`
 
 ## Required Intake Flow
@@ -76,6 +77,7 @@ When confirmed, execute:
 - Enforce quality gates from command files:
   - Planning approval: `>=75%` consensus.
   - Review approval: `>=95%` confidence and zero unresolved issues.
+  - Documentation approval: Gemini must return `APPROVED` with zero unresolved documentation issues.
 
 ## Progress Updates
 
@@ -92,4 +94,5 @@ When `/pipeline/complete` finishes, return a concise execution summary with:
 - accepted plan
 - implemented task groups
 - review outcomes
+- documentation outcomes
 - assumptions made

package/commands/pipeline/documentation/gate.md

@@ -0,0 +1,19 @@
+---
+description: Apply documentation approval gate
+subtask: true
+model: openai/gpt-5.4
+---
+
+Read the latest Gemini documentation review and apply gate exactly:
+
+Skill requirements:
+
+- ChatGPT gate supervisor must load `ff-context-tracking` before persisting gate decisions.
+
+- APPROVED when verdict is `APPROVED` and unresolved documentation issues count is `0`
+- REWORK when verdict is `REWORK_REQUIRED` and iteration < 5
+- ESCALATE when iteration == 5 and still not approved
+
+Persist gate decision in pipeline context and output one status line:
+
+`DOCUMENTATION_GATE=APPROVED|REWORK|ESCALATE`

package/commands/pipeline/documentation/run-codex.md

@@ -0,0 +1,23 @@
+---
+description: Codex documentation implementation pass
+subtask: true
+agent: ff-building-codex
+model: openai/gpt-5.3-codex
+---
+
+Document the approved code changes and update repository documentation.
+
+Before writing docs, load these skills:
+
+- `ff-context-tracking`
+- `ff-todo-management`
+- `ff-mini-plan`
+
+Requirements:
+
+1. Use the latest approved review outputs and implementation artifacts as source of truth.
+2. Update all affected docs so behavior and operational steps match shipped code.
+3. If this is a rework iteration, incorporate Gemini feedback from the previous documentation review.
+4. Summarize what docs were changed and why.
+
+Persist to `.feature-factory/agents/ff-documentation-codex-{UUID}-T{N}-iter{I}.md`.

package/commands/pipeline/documentation/run-gemini.md

@@ -0,0 +1,21 @@
+---
+description: Gemini documentation review
+subtask: true
+agent: ff-reviewing-gemini
+---
+
+Review the latest Codex documentation pass for completeness, correctness, and repository doc consistency.
+
+Before reviewing docs, load these skills:
+
+- `ff-report-templates`
+- `ff-severity-classification`
+
+Required output:
+
+1. verdict `APPROVED` or `REWORK_REQUIRED`
+2. unresolved documentation issues (if any)
+3. explicit rework instructions
+4. confidence score (0-100)
+
+Persist to `.feature-factory/agents/ff-documentation-gemini-{UUID}-T{N}-iter{I}.md`.

package/commands/pipeline/documentation/run.md

@@ -0,0 +1,27 @@
+---
+description: Run documentation loop after review approval
+subtask: true
+model: openai/gpt-5.4
+loop:
+  max: 5
+  until: documentation updates are approved by Gemini with zero unresolved documentation issues
+return:
+  - /pipeline/documentation/run-codex
+  - /pipeline/documentation/run-gemini
+  - /pipeline/documentation/gate
+  - If `DOCUMENTATION_GATE=REWORK`, continue loop with Gemini feedback for the next Codex pass.
+---
+
+Execute the documentation stage for the current approved implementation.
+
+Skill requirements:
+
+1. ChatGPT supervisor must load `ff-context-tracking` to track loop state and artifact lineage.
+2. ChatGPT supervisor must load `ff-todo-management` to track documentation actions and rework items per iteration.
+3. Gemini reviewer should use `ff-severity-classification` when reporting documentation issues.
+
+Stop criteria:
+
+- approve when Gemini confirms documentation is complete, accurate, and repository docs are updated
+- continue loop while unresolved documentation issues exist and iteration < 5
+- escalate to user when iteration reaches 5 without approval

package/commands/pipeline/start.md

@@ -6,6 +6,7 @@ return:
   - /pipeline/planning/run {loop:5 && until:planning gate is APPROVED or planning gate is BLOCKED and waiting for user confirmation}
   - If planning is BLOCKED or loop max was reached, stop and ask the user whether to continue planning iterations. Otherwise continue.
   - /pipeline/building/run
+  - /pipeline/documentation/run
   - /pipeline/complete
 ---
 
@@ -18,4 +19,4 @@ Execution requirements:
 1. Create a pipeline UUID and persist orchestrator state in `.feature-factory/agents/pipeline-{UUID}.md` via `ff-agents-update`.
 2. Keep all phase artifacts in `.feature-factory/plans/` and `.feature-factory/reviews/`.
 3. Use command chaining, parallel fan-out, and loop gates from the `/pipeline/...` command tree.
-4. Do not skip planning and review gates.
+4. Do not skip planning, review, and documentation gates.

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@syntesseraai/opencode-feature-factory",
-  "version": "0.6.6",
+  "version": "0.6.7",
   "type": "module",
   "description": "OpenCode plugin for Feature Factory agents - provides sub-agents and skills for validation, review, security, and architecture assessment",
   "license": "MIT",