feat(3081): auto-trim review prompts for small-context model reviewers (#3708)
* feat(3081): auto-trim review prompts for small-context model reviewers Adds review.max_prompt_tokens and review.max_prompt_tokens_per_reviewer config keys. When configured, the /gsd-review workflow deterministically trims the assembled prompt before sending to each reviewer (drop CONTEXT → RESEARCH → REQUIREMENTS; head-shrink PROJECT.md; tail-truncate PLANs proportionally; reserve disclosure-note tokens upfront). Trim metadata is recorded in REVIEWS.md frontmatter. Reviewer is skipped with a warning if even the minimum review set exceeds the budget. Closes #3081 * fix(3081): register prompt-budget in SDK query registry and update inventory manifest review.md references `gsd-sdk query prompt-budget` at three call sites, but the command had no handler in the SDK registry — failing the registry-integration drift-guard test on all 6 CI matrix legs. Added a native TypeScript SDK handler (sdk/src/query/prompt-budget.ts) that ports the applyBudget logic from the CJS module, registered it in DOMAIN_STATIC_CATALOG, and regenerated docs/INVENTORY-MANIFEST.json to include the new cli_modules/prompt-budget.cjs entry. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(3081): bump ws to 8.20.1 and allowlist prompt-budget sibling pair Two additional CI failures after the registry fix: 1. ws moderate CVE (GHSA-58qx-3vcg-4xpx, uninitialized memory disclosure): The advisory covers ws >=8.0.0 <8.20.1. Both root and sdk/package.json pinned ^8.20.0 which resolved to 8.20.0. Bumped both to 8.20.1 to clear the npm audit drift-guard test (bug-3588-npm-audit-clean.test.cjs). 2. lint-shared-module-handsync detected the new prompt-budget.ts / prompt-budget.cjs sibling pair without an allowlist entry. Added a cooperatingSiblings entry to scripts/shared-module-handsync-allowlist.json with classification and justification matching the established pattern. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(3081): align prompt-budget skip semantics across CJS and SDK dispatch paths Replace brittle `[ $EXIT -eq 2 ]` guards with `[ $EXIT -ne 0 ]` in all three local-reviewer blocks (Ollama, LM Studio, llama.cpp) in workflows/review.md. Any non-zero exit from prompt-budget now triggers a skip with a descriptive warning — exit 2/11 prints "budget too small", any other non-zero prints "unexpected exit code". This ensures the SDK bridge dispatch path (exit 11 via GSDError(Blocked)) triggers the same skip as the CJS path (exit 2). The SDK handler (sdk/src/query/prompt-budget.ts) already writes both metadata and prompt files before throwing, so no change needed there. The Ollama block also gains the missing OLLAMA_SKIP guard so the reviewer invocation is actually skipped (previously the block only suppressed the OLLAMA_PROMPT_FILE update but still ran the curl invocation). SDK integration path (hardFailed via GSDError(Blocked) → exit 11) is covered by handler unit tests in tests/prompt-budget.test.cjs; no gsd-sdk-*.test.cjs exercising the full bridge dispatch for this command exists yet — that gap remains and is documented here. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix prompt-budget trim ordering and review guard follow-ups * perf: optimize prompt-budget and dedup reviewer trim workflow * fix(3708): drop source-grep theater tests to satisfy lint-no-source-grep All four test files added in commit 2df566ed were pure source-grep theater: they read .cjs / .ts / .md source files and asserted that specific string literals were present or absent. None exercised runtime behaviour. Deleted: - tests/gsd-tools-memory-optimizer.test.cjs — 7 includes() on gsd-tools.cjs - tests/prompt-budget-hotpath-optimizer.test.cjs — includes() on prompt-budget.cjs + .ts - tests/prompt-budget-io-optimizer.test.cjs — includes() on prompt-budget.ts + gsd-tools.cjs - tests/review-workflow-budget-dedup.test.cjs — includes() on review.md Behavioural coverage for the prompt-budget feature already exists in tests/prompt-budget.test.cjs and tests/prompt-budget-cli.test.cjs (also added by this PR). No replacement tests needed. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(3708): correct budget-pressure threshold and minSet accounting Two bugs in applyBudget caused premature trimming and false hard-fails: 1. UNNEEDED_TRIM: budgetUnderPressure compared baseTokens against effectiveBudget - NOTE_RESERVE_TOKENS, triggering trim pressure 80 tokens before the budget was actually exceeded. Fix: compare against effectiveBudget directly; NOTE_RESERVE_TOKENS are still reserved in contentBudget once real pressure is confirmed. 2. FALSE_HARDFAIL: minSet included NOTE_RESERVE_TOKENS unconditionally, treating the note as mandatory even when no trim would occur and no note would be injected. Fix: exclude NOTE_RESERVE_TOKENS from minSet; a prompt that fits untrimmed needs no note and must not hard-fail. Both fixes applied in CJS and TypeScript implementations. Two regression tests added (cycles 11 and 12) that reproduce each case behaviorally. --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Tom Boucher
@@ -173,6 +173,39 @@ Output your review in markdown format.
|
||||
```
|
||||
|
||||
Write to a temp file: `/tmp/gsd-review-prompt-{phase}.md`
|
||||
|
||||
Also write individual section files so the budget tool can re-trim per reviewer:
|
||||
|
||||
```bash
|
||||
# Write individual section files for per-reviewer budget trimming
|
||||
# These are always written so reviewers with a budget can invoke prompt-budget
|
||||
cp "$INSTRUCTIONS_BLOCK_FILE" "/tmp/gsd-review-${PHASE}-instructions.md"
|
||||
cp "$ROADMAP_SECTION_FILE" "/tmp/gsd-review-${PHASE}-roadmap.md"
|
||||
|
||||
# Plan files: copy each PLAN.md to a predictable numbered path
|
||||
PLAN_INDEX=0
|
||||
for PLAN_FILE in "${PHASE_DIR}"/*-PLAN.md; do
|
||||
PADDED_IDX=$(printf '%02d' "$PLAN_INDEX")
|
||||
cp "$PLAN_FILE" "/tmp/gsd-review-${PHASE}-plan-${PADDED_IDX}.md"
|
||||
PLAN_INDEX=$((PLAN_INDEX + 1))
|
||||
done
|
||||
|
||||
# Optional section files (only if content was included in the combined prompt)
|
||||
if [ -f ".planning/PROJECT.md" ]; then
|
||||
cp .planning/PROJECT.md "/tmp/gsd-review-${PHASE}-project.md"
|
||||
fi
|
||||
if ls "${PHASE_DIR}/"*"-CONTEXT.md" >/dev/null 2>&1; then
|
||||
cat "${PHASE_DIR}/"*"-CONTEXT.md" > "/tmp/gsd-review-${PHASE}-context.md"
|
||||
fi
|
||||
if ls "${PHASE_DIR}/"*"-RESEARCH.md" >/dev/null 2>&1; then
|
||||
cat "${PHASE_DIR}/"*"-RESEARCH.md" > "/tmp/gsd-review-${PHASE}-research.md"
|
||||
fi
|
||||
if [ -f ".planning/REQUIREMENTS.md" ]; then
|
||||
cp .planning/REQUIREMENTS.md "/tmp/gsd-review-${PHASE}-requirements.md"
|
||||
fi
|
||||
```
|
||||
|
||||
Note: The variable names above (`INSTRUCTIONS_BLOCK_FILE`, `ROADMAP_SECTION_FILE`, `PHASE_DIR`, `PHASE`) reference the variables already established during prompt assembly. In practice the AI implementing this step writes the instruction and roadmap blocks to temp files while assembling the combined prompt, then copies those same temp files to the per-reviewer section paths. If the assembled prompt was built inline (string concatenation rather than file-by-file), write each section to the corresponding path after writing the combined file.
|
||||
</step>
|
||||
|
||||
<step name="invoke_reviewers">
|
||||
@@ -256,13 +289,74 @@ fi
|
||||
Read host and model from config. All three local backends share the same `/v1/chat/completions` endpoint — only host and model differ. Use `jq --rawfile` to safely encode the multi-line prompt as JSON without shell-escaping issues.
|
||||
|
||||
```bash
|
||||
# Shared helper: apply prompt-budget trimming for local reviewers
|
||||
prepare_trimmed_prompt_for_reviewer() {
|
||||
REVIEWER_KEY="$1"
|
||||
REVIEWER_BUDGET="$2"
|
||||
OUTPUT_PROMPT="$3"
|
||||
OUTPUT_META="$4"
|
||||
|
||||
[ -z "$REVIEWER_BUDGET" ] && return 0
|
||||
[ "$REVIEWER_BUDGET" = "null" ] && return 0
|
||||
[ "$REVIEWER_BUDGET" = "0" ] && return 0
|
||||
|
||||
PLAN_FILE_ARGS=""
|
||||
for p in /tmp/gsd-review-{phase}-plan-*.md; do
|
||||
[ -f "$p" ] && PLAN_FILE_ARGS="$PLAN_FILE_ARGS --plan-file $p"
|
||||
done
|
||||
PROJECT_ARG=""
|
||||
[ -f "/tmp/gsd-review-{phase}-project.md" ] && PROJECT_ARG="--project-file /tmp/gsd-review-{phase}-project.md"
|
||||
CONTEXT_ARG=""
|
||||
[ -f "/tmp/gsd-review-{phase}-context.md" ] && CONTEXT_ARG="--context-file /tmp/gsd-review-{phase}-context.md"
|
||||
RESEARCH_ARG=""
|
||||
[ -f "/tmp/gsd-review-{phase}-research.md" ] && RESEARCH_ARG="--research-file /tmp/gsd-review-{phase}-research.md"
|
||||
REQUIREMENTS_ARG=""
|
||||
[ -f "/tmp/gsd-review-{phase}-requirements.md" ] && REQUIREMENTS_ARG="--requirements-file /tmp/gsd-review-{phase}-requirements.md"
|
||||
|
||||
gsd-sdk query prompt-budget \
|
||||
--budget "$REVIEWER_BUDGET" \
|
||||
--instructions-file "/tmp/gsd-review-{phase}-instructions.md" \
|
||||
--roadmap-file "/tmp/gsd-review-{phase}-roadmap.md" \
|
||||
$PLAN_FILE_ARGS $PROJECT_ARG $CONTEXT_ARG $RESEARCH_ARG $REQUIREMENTS_ARG \
|
||||
--output-prompt "$OUTPUT_PROMPT" \
|
||||
--output-metadata "$OUTPUT_META"
|
||||
return $?
|
||||
}
|
||||
|
||||
# Resolve prompt budget for Ollama: per-reviewer override > global default > null
|
||||
OLLAMA_REVIEWER_BUDGET=$(gsd-sdk query config-get review.max_prompt_tokens_per_reviewer.ollama 2>/dev/null | jq -r '.' 2>/dev/null || echo "null")
|
||||
if [ -z "$OLLAMA_REVIEWER_BUDGET" ] || [ "$OLLAMA_REVIEWER_BUDGET" = "null" ]; then
|
||||
OLLAMA_REVIEWER_BUDGET=$(gsd-sdk query config-get review.max_prompt_tokens 2>/dev/null | jq -r '.' 2>/dev/null || echo "null")
|
||||
fi
|
||||
|
||||
# Apply budget trim for Ollama if a budget is configured
|
||||
OLLAMA_PROMPT_FILE="/tmp/gsd-review-prompt-{phase}.md"
|
||||
OLLAMA_SKIP=0
|
||||
if [ -n "$OLLAMA_REVIEWER_BUDGET" ] && [ "$OLLAMA_REVIEWER_BUDGET" != "null" ] && [ "$OLLAMA_REVIEWER_BUDGET" != "0" ]; then
|
||||
OLLAMA_TRIMMED_PROMPT="/tmp/gsd-review-prompt-{phase}-ollama.md"
|
||||
OLLAMA_TRIM_META="/tmp/gsd-review-prompt-{phase}-ollama.metadata.json"
|
||||
prepare_trimmed_prompt_for_reviewer "ollama" "$OLLAMA_REVIEWER_BUDGET" "$OLLAMA_TRIMMED_PROMPT" "$OLLAMA_TRIM_META"
|
||||
OLLAMA_EXIT=$?
|
||||
if [ $OLLAMA_EXIT -ne 0 ]; then
|
||||
if [ $OLLAMA_EXIT -eq 2 ] || [ $OLLAMA_EXIT -eq 11 ]; then
|
||||
echo "WARNING: prompt budget for ollama (${OLLAMA_REVIEWER_BUDGET} tokens) is too small for the minimum review set. Skipping Ollama reviewer." >&2
|
||||
else
|
||||
echo "WARNING: prompt-budget returned unexpected exit code ${OLLAMA_EXIT} for ollama. Skipping Ollama reviewer." >&2
|
||||
fi
|
||||
OLLAMA_SKIP=1
|
||||
else
|
||||
OLLAMA_PROMPT_FILE="$OLLAMA_TRIMMED_PROMPT"
|
||||
fi
|
||||
fi
|
||||
|
||||
if [ "$OLLAMA_SKIP" != "1" ]; then
|
||||
OLLAMA_HOST=$(gsd-sdk query config-get review.ollama_host 2>/dev/null | jq -r '.' 2>/dev/null || echo "")
|
||||
if [ -z "$OLLAMA_HOST" ] || [ "$OLLAMA_HOST" = "null" ]; then OLLAMA_HOST="http://localhost:11434"; fi
|
||||
OLLAMA_MODEL=$(gsd-sdk query config-get review.models.ollama 2>/dev/null | jq -r '.' 2>/dev/null || echo "")
|
||||
if [ -z "$OLLAMA_MODEL" ] || [ "$OLLAMA_MODEL" = "null" ]; then
|
||||
OLLAMA_MODEL=$(curl -s --max-time 2 "${OLLAMA_HOST}/v1/models" 2>/dev/null | jq -r '.data[0].id // "llama3"' 2>/dev/null || echo "llama3")
|
||||
fi
|
||||
jq -n --rawfile content /tmp/gsd-review-prompt-{phase}.md \
|
||||
jq -n --rawfile content "$OLLAMA_PROMPT_FILE" \
|
||||
--arg model "$OLLAMA_MODEL" \
|
||||
'{model: $model, messages: [{role: "user", content: $content}]}' | \
|
||||
curl -s --max-time 120 -X POST "${OLLAMA_HOST}/v1/chat/completions" \
|
||||
@@ -272,17 +366,45 @@ jq -n --rawfile content /tmp/gsd-review-prompt-{phase}.md \
|
||||
if [ ! -s /tmp/gsd-review-ollama-{phase}.md ]; then
|
||||
echo "Ollama review failed or returned empty output." > /tmp/gsd-review-ollama-{phase}.md
|
||||
fi
|
||||
fi
|
||||
```
|
||||
|
||||
**LM Studio (local, OpenAI-compatible):**
|
||||
```bash
|
||||
# Resolve prompt budget for LM Studio: per-reviewer override > global default > null
|
||||
LM_STUDIO_REVIEWER_BUDGET=$(gsd-sdk query config-get review.max_prompt_tokens_per_reviewer.lm_studio 2>/dev/null | jq -r '.' 2>/dev/null || echo "null")
|
||||
if [ -z "$LM_STUDIO_REVIEWER_BUDGET" ] || [ "$LM_STUDIO_REVIEWER_BUDGET" = "null" ]; then
|
||||
LM_STUDIO_REVIEWER_BUDGET=$(gsd-sdk query config-get review.max_prompt_tokens 2>/dev/null | jq -r '.' 2>/dev/null || echo "null")
|
||||
fi
|
||||
|
||||
# Apply budget trim for LM Studio if a budget is configured
|
||||
LM_STUDIO_PROMPT_FILE="/tmp/gsd-review-prompt-{phase}.md"
|
||||
LM_STUDIO_SKIP=0
|
||||
if [ -n "$LM_STUDIO_REVIEWER_BUDGET" ] && [ "$LM_STUDIO_REVIEWER_BUDGET" != "null" ] && [ "$LM_STUDIO_REVIEWER_BUDGET" != "0" ]; then
|
||||
LM_STUDIO_TRIMMED_PROMPT="/tmp/gsd-review-prompt-{phase}-lm_studio.md"
|
||||
LM_STUDIO_TRIM_META="/tmp/gsd-review-prompt-{phase}-lm_studio.metadata.json"
|
||||
prepare_trimmed_prompt_for_reviewer "lm_studio" "$LM_STUDIO_REVIEWER_BUDGET" "$LM_STUDIO_TRIMMED_PROMPT" "$LM_STUDIO_TRIM_META"
|
||||
LM_STUDIO_EXIT=$?
|
||||
if [ $LM_STUDIO_EXIT -ne 0 ]; then
|
||||
if [ $LM_STUDIO_EXIT -eq 2 ] || [ $LM_STUDIO_EXIT -eq 11 ]; then
|
||||
echo "WARNING: prompt budget for lm_studio (${LM_STUDIO_REVIEWER_BUDGET} tokens) is too small for the minimum review set. Skipping LM Studio reviewer." >&2
|
||||
else
|
||||
echo "WARNING: prompt-budget returned unexpected exit code ${LM_STUDIO_EXIT} for lm_studio. Skipping LM Studio reviewer." >&2
|
||||
fi
|
||||
LM_STUDIO_SKIP=1
|
||||
else
|
||||
LM_STUDIO_PROMPT_FILE="$LM_STUDIO_TRIMMED_PROMPT"
|
||||
fi
|
||||
fi
|
||||
|
||||
if [ "$LM_STUDIO_SKIP" != "1" ]; then
|
||||
LM_STUDIO_HOST=$(gsd-sdk query config-get review.lm_studio_host 2>/dev/null | jq -r '.' 2>/dev/null || echo "")
|
||||
if [ -z "$LM_STUDIO_HOST" ] || [ "$LM_STUDIO_HOST" = "null" ]; then LM_STUDIO_HOST="http://localhost:1234"; fi
|
||||
LM_STUDIO_MODEL=$(gsd-sdk query config-get review.models.lm_studio 2>/dev/null | jq -r '.' 2>/dev/null || echo "")
|
||||
if [ -z "$LM_STUDIO_MODEL" ] || [ "$LM_STUDIO_MODEL" = "null" ]; then
|
||||
LM_STUDIO_MODEL=$(curl -s --max-time 2 "${LM_STUDIO_HOST}/v1/models" 2>/dev/null | jq -r '.data[0].id // "local-model"' 2>/dev/null || echo "local-model")
|
||||
fi
|
||||
LM_STUDIO_RESPONSE=$(jq -n --rawfile content /tmp/gsd-review-prompt-{phase}.md \
|
||||
LM_STUDIO_RESPONSE=$(jq -n --rawfile content "$LM_STUDIO_PROMPT_FILE" \
|
||||
--arg model "$LM_STUDIO_MODEL" \
|
||||
'{model: $model, messages: [{role: "user", content: $content}]}' | \
|
||||
curl -s --max-time 120 -X POST "${LM_STUDIO_HOST}/v1/chat/completions" \
|
||||
@@ -297,17 +419,45 @@ if [ -n "$LM_STUDIO_CONTENT" ]; then
|
||||
else
|
||||
echo "Warning: LM Studio returned empty content — skipping review." >&2
|
||||
fi
|
||||
fi
|
||||
```
|
||||
|
||||
**llama.cpp (local, OpenAI-compatible):**
|
||||
```bash
|
||||
# Resolve prompt budget for llama.cpp: per-reviewer override > global default > null
|
||||
LLAMA_CPP_REVIEWER_BUDGET=$(gsd-sdk query config-get review.max_prompt_tokens_per_reviewer.llama_cpp 2>/dev/null | jq -r '.' 2>/dev/null || echo "null")
|
||||
if [ -z "$LLAMA_CPP_REVIEWER_BUDGET" ] || [ "$LLAMA_CPP_REVIEWER_BUDGET" = "null" ]; then
|
||||
LLAMA_CPP_REVIEWER_BUDGET=$(gsd-sdk query config-get review.max_prompt_tokens 2>/dev/null | jq -r '.' 2>/dev/null || echo "null")
|
||||
fi
|
||||
|
||||
# Apply budget trim for llama.cpp if a budget is configured
|
||||
LLAMA_CPP_PROMPT_FILE="/tmp/gsd-review-prompt-{phase}.md"
|
||||
LLAMA_CPP_SKIP=0
|
||||
if [ -n "$LLAMA_CPP_REVIEWER_BUDGET" ] && [ "$LLAMA_CPP_REVIEWER_BUDGET" != "null" ] && [ "$LLAMA_CPP_REVIEWER_BUDGET" != "0" ]; then
|
||||
LLAMA_CPP_TRIMMED_PROMPT="/tmp/gsd-review-prompt-{phase}-llama_cpp.md"
|
||||
LLAMA_CPP_TRIM_META="/tmp/gsd-review-prompt-{phase}-llama_cpp.metadata.json"
|
||||
prepare_trimmed_prompt_for_reviewer "llama_cpp" "$LLAMA_CPP_REVIEWER_BUDGET" "$LLAMA_CPP_TRIMMED_PROMPT" "$LLAMA_CPP_TRIM_META"
|
||||
LLAMA_CPP_EXIT=$?
|
||||
if [ $LLAMA_CPP_EXIT -ne 0 ]; then
|
||||
if [ $LLAMA_CPP_EXIT -eq 2 ] || [ $LLAMA_CPP_EXIT -eq 11 ]; then
|
||||
echo "WARNING: prompt budget for llama_cpp (${LLAMA_CPP_REVIEWER_BUDGET} tokens) is too small for the minimum review set. Skipping llama.cpp reviewer." >&2
|
||||
else
|
||||
echo "WARNING: prompt-budget returned unexpected exit code ${LLAMA_CPP_EXIT} for llama_cpp. Skipping llama.cpp reviewer." >&2
|
||||
fi
|
||||
LLAMA_CPP_SKIP=1
|
||||
else
|
||||
LLAMA_CPP_PROMPT_FILE="$LLAMA_CPP_TRIMMED_PROMPT"
|
||||
fi
|
||||
fi
|
||||
|
||||
if [ "$LLAMA_CPP_SKIP" != "1" ]; then
|
||||
LLAMA_CPP_HOST=$(gsd-sdk query config-get review.llama_cpp_host 2>/dev/null | jq -r '.' 2>/dev/null || echo "")
|
||||
if [ -z "$LLAMA_CPP_HOST" ] || [ "$LLAMA_CPP_HOST" = "null" ]; then LLAMA_CPP_HOST="http://localhost:8080"; fi
|
||||
LLAMA_CPP_MODEL=$(gsd-sdk query config-get review.models.llama_cpp 2>/dev/null | jq -r '.' 2>/dev/null || echo "")
|
||||
if [ -z "$LLAMA_CPP_MODEL" ] || [ "$LLAMA_CPP_MODEL" = "null" ]; then
|
||||
LLAMA_CPP_MODEL=$(curl -s --max-time 2 "${LLAMA_CPP_HOST}/v1/models" 2>/dev/null | jq -r '.data[0].id // "local-model"' 2>/dev/null || echo "local-model")
|
||||
fi
|
||||
LLAMA_CPP_CONTENT=$(jq -n --rawfile content /tmp/gsd-review-prompt-{phase}.md \
|
||||
LLAMA_CPP_CONTENT=$(jq -n --rawfile content "$LLAMA_CPP_PROMPT_FILE" \
|
||||
--arg model "$LLAMA_CPP_MODEL" \
|
||||
'{model: $model, messages: [{role: "user", content: $content}]}' | \
|
||||
curl -s --max-time 120 -X POST "${LLAMA_CPP_HOST}/v1/chat/completions" \
|
||||
@@ -318,6 +468,7 @@ if [ -n "$LLAMA_CPP_CONTENT" ]; then
|
||||
else
|
||||
echo "Warning: llama.cpp returned empty content — skipping review." >&2
|
||||
fi
|
||||
fi
|
||||
```
|
||||
|
||||
If a CLI or local server fails, log the error and continue with remaining reviewers.
|
||||
@@ -336,12 +487,24 @@ Display progress:
|
||||
<step name="write_reviews">
|
||||
Combine all review responses into `{phase_dir}/{padded_phase}-REVIEWS.md`:
|
||||
|
||||
After all reviewers complete, collect trim metadata files written during the run. For each reviewer that was trimmed (i.e. a `.metadata.json` file exists and `hardFailed` or `omitted` is non-empty, or `projectMdShrunk` is true, or `planTruncationPct > 0`), include a `trimmed_reviewers` block in the frontmatter. Omit the key entirely if no reviewer was trimmed.
|
||||
|
||||
```markdown
|
||||
---
|
||||
phase: {N}
|
||||
reviewers: [gemini, claude, codex, coderabbit, opencode, qwen, cursor, ollama, lm_studio, llama_cpp] # populate at runtime with only the reviewers actually invoked
|
||||
reviewed_at: {ISO timestamp}
|
||||
plans_reviewed: [{list of PLAN.md files}]
|
||||
trimmed_reviewers: # only present if at least one reviewer was trimmed
|
||||
ollama:
|
||||
budget: 6000
|
||||
effective_budget: 5400
|
||||
estimated_tokens: 5380
|
||||
omitted: [context, research]
|
||||
project_md_shrunk: true
|
||||
plan_truncation_pct: 22
|
||||
hard_failed: false
|
||||
note_injected: true
|
||||
---
|
||||
|
||||
# Cross-AI Plan Review — Phase {N}
|
||||
|
||||
Reference in New Issue
Block a user