deepflow 0.1.89 → 0.1.91

package/src/commands/df/consolidate.md

@@ -1,42 +0,0 @@
----
-name: df:consolidate
-description: Remove duplicates and superseded entries from decisions file, promote stale provisionals
----
-
-# /df:consolidate — Consolidate Decisions
-
-Remove duplicates, superseded entries, and promote stale provisionals. Keep decisions.md dense and useful.
-
-**NEVER:** use EnterPlanMode, ExitPlanMode
-
-## Behavior
-
-### 1. LOAD
-Read `.deepflow/decisions.md` via `` !`cat .deepflow/decisions.md 2>/dev/null || echo 'NOT_FOUND'` ``. If missing/empty, report and exit.
-
-### 2. ANALYZE (model-driven, not regex)
-- Identify duplicates (same meaning, different wording)
-- Identify superseded entries (later contradicts earlier)
-- Identify stale `[PROVISIONAL]` entries (>30 days old, no resolution)
-
-### 3. CONSOLIDATE
-- Remove duplicates (keep more precise wording)
-- Remove superseded entries (later decision wins)
-- Promote stale `[PROVISIONAL]` → `[DEBT]`
-- Preserve `[APPROACH]` unless superseded, `[ASSUMPTION]` unless invalidated
-- Target: 200-500 lines if currently longer
-- When in doubt, keep both entries (conservative)
-
-### 4. WRITE
-- Rewrite `.deepflow/decisions.md` with consolidated content
-- Write `{ "last_consolidated": "{ISO-8601}" }` to `.deepflow/last-consolidated.json`
-
-### 5. REPORT
-`✓ Consolidated: {before} → {after} lines, {n} removed, {n} promoted to [DEBT]`
-
-## Rules
-
-- Conservative: when in doubt, keep both entries
-- Never add new decisions — only remove, merge, or re-tag
-- `[DEBT]` is only produced by consolidation, never manually assigned
-- Preserve chronological ordering within sections

package/src/commands/df/note.md

@@ -1,73 +0,0 @@
----
-name: df:note
-description: Capture decisions that emerged during free conversations outside of deepflow commands
----
-
-# /df:note — Capture Decisions from Free Conversations
-
-## Orchestrator Role
-
-Scan conversation for candidate decisions, present for user confirmation, persist to `.deepflow/decisions.md`.
-
-**NEVER:** Spawn agents, use Task tool, use Glob/Grep on source code, run git, use TaskOutput, EnterPlanMode, ExitPlanMode
-
-**ONLY:** Read `.deepflow/decisions.md`, present candidates via `AskUserQuestion`, append confirmed decisions
-
-## Behavior
-
-### 1. EXTRACT CANDIDATES
-
-Scan prior messages for resolved choices, adopted approaches, or stated assumptions. Look for:
-- **Approaches chosen**: "we'll use X instead of Y"
-- **Provisional choices**: "for now we'll use X"
-- **Stated assumptions**: "assuming X is true"
-- **Constraints accepted**: "X is out of scope"
-- **Naming/structural choices**: "we'll call it X", "X goes in the Y layer"
-
-Extract **at most 4 candidates**. For each, determine:
-
-| Field | Value |
-|-------|-------|
-| Tag | `[APPROACH]` (deliberate choice), `[PROVISIONAL]` (revisit later), or `[ASSUMPTION]` (unvalidated) |
-| Decision | One concise line describing the choice |
-| Rationale | One sentence explaining why |
-
-If <2 clear candidates found, say so and exit.
-
-### 2. CHECK FOR CONTRADICTIONS
-
-Read `.deepflow/decisions.md` if it exists. If a candidate contradicts a prior entry: keep prior entry unchanged, amend candidate rationale to `was "X", now "Y" because Z`.
-
-### 3. PRESENT VIA AskUserQuestion
-
-Single multi-select call. Each option: `label` = tag + decision text, `description` = rationale.
-
-### 4. APPEND CONFIRMED DECISIONS
-
-For each selected option:
-1. Create `.deepflow/decisions.md` with `# Decisions` header if absent
-2. Append a dated section: `### YYYY-MM-DD — note`
-3. Group all confirmed decisions under one section: `- [TAG] Decision text — rationale`
-4. Never modify or delete prior entries
-
-### 5. CONFIRM
-
-Report: `Saved N decision(s) to .deepflow/decisions.md` or `No decisions saved.`
-
-## Decision Tags
-
-| Tag | Meaning | Source |
-|-----|---------|--------|
-| `[APPROACH]` | Firm decision | /df:note, auto-extraction |
-| `[PROVISIONAL]` | Revisit later | /df:note, auto-extraction |
-| `[ASSUMPTION]` | Unverified | /df:note, auto-extraction |
-| `[DEBT]` | Needs revisiting | /df:consolidate only, never manually assigned |
-
-## Rules
-
-- Max 4 candidates per invocation (AskUserQuestion tool limit)
-- multiSelect: true — user confirms any subset
-- Never invent decisions — only extract what was discussed and resolved
-- Never modify prior entries in `.deepflow/decisions.md`
-- Source is always `note`; date is today (YYYY-MM-DD)
-- One AskUserQuestion call — all candidates in a single call

package/src/commands/df/report.md

@@ -1,75 +0,0 @@
----
-name: df:report
-description: Generate session cost report with token usage, cache hit ratio, per-task costs, and quota impact
-allowed-tools: [Read, Write, Bash]
----
-
-# /df:report — Session Cost Report
-
-> **DEPRECATED:** Use `/df:dashboard` instead to view deepflow metrics and status.
-
-## Orchestrator Role
-
-Aggregate token usage data and produce a structured report.
-
-**NEVER:** Spawn agents, use Task tool, use AskUserQuestion, run git, EnterPlanMode, ExitPlanMode
-
-**ONLY:** Read data files, compute aggregates, write `.deepflow/report.json` and `.deepflow/report.md`
-
-## Behavior
-
-### 1. LOAD DATA SOURCES
-
-Read each source gracefully — missing files yield zero/empty values, never error out.
-
-| Source | Path | Shell injection | Key fields |
-|--------|------|-----------------|------------|
-| Token history | `.deepflow/token-history.jsonl` | `` !`cat .deepflow/token-history.jsonl 2>/dev/null \|\| echo ''` `` | `timestamp`, `input_tokens`, `cache_creation_input_tokens`, `cache_read_input_tokens`, `used_percentage`, `model`, `session_id` |
-| Quota history | `~/.claude/quota-history.jsonl` | `` !`tail -5 ~/.claude/quota-history.jsonl 2>/dev/null \|\| echo ''` `` | `timestamp`, `event`, API payload |
-| Task results | `.deepflow/results/T*.yaml` | `` !`ls .deepflow/results/T*.yaml 2>/dev/null \|\| echo ''` `` | `tokens` block: `start_percentage`, `end_percentage`, `delta_percentage`, `input_tokens`, `cache_creation_input_tokens`, `cache_read_input_tokens` |
-| Session metadata | `.deepflow/auto-memory.yaml` | `` !`cat .deepflow/auto-memory.yaml 2>/dev/null \|\| echo ''` `` | session_id, start time (optional) |
-
-### 2. COMPUTE AGGREGATES
-
-```
-total_input_tokens  = sum(input_tokens)
-total_cache_creation = sum(cache_creation_input_tokens)
-total_cache_read    = sum(cache_read_input_tokens)
-total_tokens_all    = total_input_tokens + total_cache_creation + total_cache_read
-cache_hit_ratio     = total_cache_read / total_tokens_all  (0 if denominator=0, clamp [0,1], round 4 decimals)
-peak_context_percentage = max(used_percentage)
-model               = most recent line's model
-```
-
-### 3. WRITE `.deepflow/report.json`
-
-Structure: `{ version: 1, generated: ISO-8601-UTC, session_summary: {total_input_tokens, total_cache_creation, total_cache_read, cache_hit_ratio, peak_context_percentage, model}, tasks: [{task_id, start_percentage, end_percentage, delta_percentage, input_tokens, cache_creation, cache_read}], quota: {available: bool, ...API fields if available} }`
-
-Rules: `version` always 1. `tasks` = `[]` if no results found. `quota.available` = false if missing. All token fields integers >= 0. `cache_hit_ratio` float in [0,1].
-
-### 4. WRITE `.deepflow/report.md`
-
-Required sections with exact headings:
-
-**## Session Summary** — Table: Model, Total Input Tokens, Cache Creation Tokens, Cache Read Tokens, Cache Hit Ratio (with %), Peak Context Usage %.
-
-**## Per-Task Costs** — Table: Task, Start %, End %, Delta %, Input Tokens, Cache Creation, Cache Read. Show `_(No task data available)_` if empty.
-
-**## Quota Impact** — Quota fields table if `quota.available=true`, else exactly: `Not available (non-macOS or no token)`.
-
-### 5. CONFIRM
-
-```
-Report generated:
-  .deepflow/report.json  — machine-readable (version=1)
-  .deepflow/report.md    — human-readable summary
-```
-
-List missing data sources as a note if any were absent.
-
-## Rules
-
-- Graceful degradation — missing files yield zero/empty, never error
-- No hallucination — only values from actual file contents; 0 for missing fields
-- Idempotent — re-running overwrites both files with fresh data
-- ISO 8601 UTC timestamps for `generated` field

package/src/commands/df/resume.md

@@ -1,47 +0,0 @@
----
-name: df:resume
-description: Synthesize project state into a briefing covering what happened, current decisions, and next steps
-allowed-tools: [Read, Grep, Glob, Bash]
----
-
-# /df:resume — Session Continuity Briefing
-
-## Orchestrator Role
-
-Read project state from multiple sources, produce a concise briefing for resuming work. Pure read-only.
-
-**NEVER:** Write/create/modify files, run git write ops, use AskUserQuestion, spawn agents, use TaskOutput, EnterPlanMode, ExitPlanMode
-
-**ONLY:** Read files (Bash read-only git commands, Read, Glob, Grep), write briefing to stdout
-
-## Behavior
-
-### 1. GATHER SOURCES (parallel, all reads)
-
-| Source | Command/Path | Purpose |
-|--------|-------------|---------|
-| Git timeline | `` !`git log --oneline -20` `` | What changed and when |
-| Decisions | `` !`cat .deepflow/decisions.md 2>/dev/null \|\| echo 'NOT_FOUND'` `` | Live [APPROACH], [PROVISIONAL], [ASSUMPTION] entries |
-| Plan | `` !`cat PLAN.md 2>/dev/null \|\| echo 'NOT_FOUND'` `` | Task status (checked vs unchecked) |
-| Spec headers | `` !`head -20 specs/doing-*.md 2>/dev/null \|\| echo 'NOT_FOUND'` `` | In-flight features |
-| Experiments | `` !`ls .deepflow/experiments/ 2>/dev/null \|\| echo 'NOT_FOUND'` `` | Validated/failed approaches |
-
-Token budget: ~2500 tokens input. Skip missing sources silently.
-
-### 2. SYNTHESIZE BRIEFING (200-500 words, 3 sections)
-
-**## Timeline** — 3-6 sentences: arc of work from git log + spec/PLAN state. What completed, in-flight, notable milestones. Reference dates/commits where informative.
-
-**## Live Decisions** — All `[APPROACH]`, `[PROVISIONAL]`, `[ASSUMPTION]` from `.deepflow/decisions.md` as bullets with tag + text + rationale. Show newest entry per topic if contradictions exist. State "No decisions recorded yet." if absent/empty.
-
-**## Next Steps** — From PLAN.md: unblocked `- [ ]` tasks first, then blocked tasks with blockers. If no PLAN.md: suggest `/df:plan`.
-
-### 3. OUTPUT
-
-Print briefing to stdout. No file writes.
-
-## Rules
-
-- Read sources in a single pass — no re-reads
-- Contradicted decisions: show newest per topic only
-- Token budget: ~2500 input tokens to produce ~500 words output