Fix DFanso#113 : add token count, cost estimation, and processing time to dry run mode

[adeeshperera]

• Add estimated token counts for input/output in dry run display
• Include cost estimation based on selected LLM provider pricing
• Show processing time estimates for each provider type

$ go run cmd/commit-msg/main.go . --dry-run

Summary by CodeRabbit

• New Features

  • Displays estimated input, output, and total tokens in dry-run and detailed prompts.
  • Shows optional cost estimates and processing time ranges when available, with per-provider calculations.
  • Provides clearer usage metrics replacing the previous single token estimate.

• Refactor

  • Revamped dry-run Changes Summary to include token metrics, conditional cost, and processing time.

[coderabbitai]

Walkthrough

Adds LLM usage estimation to dry-run output in cmd/cli/createMsg.go: computes token counts, estimates cost (non-Ollama only), and processing time; introduces estimateCost and estimateProcessingTime helpers; updates DRY RUN summary fields; retains commit message length validation.

Changes

Cohort / File(s)	Summary
Dry-run estimation and output update cmd/cli/createMsg.go	Added input/output/total token estimation, provider-based cost/time estimates, new helpers estimateCost and estimateProcessingTime, and revised DRY RUN summary to display token metrics, conditional cost (non-Ollama), and min/max processing time; preserved commit length validation.

Sequence Diagram(s)

sequenceDiagram
  autonumber
  actor User
  participant CLI as CLI createMsg
  participant Est as Estimation Helpers
  participant Provider as Provider Config

  User->>CLI: run dry-run
  CLI->>Est: compute input tokens from prompt
  Est-->>CLI: inputTokens
  CLI->>Est: estimate output tokens (fixed)
  Est-->>CLI: outputTokens
  CLI->>CLI: totalTokens = input + output

  CLI->>Provider: check provider type
  alt provider != Ollama
    CLI->>Est: estimateCost(provider, totalTokens)
    Est-->>CLI: cost
  else Ollama
    Note over CLI: Cost omitted for Ollama
  end

  CLI->>Est: estimateProcessingTime(provider, tokens)
  Est-->>CLI: min/max time

  CLI-->>User: DRY RUN summary (tokens, optional cost, time)

Loading

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Possibly related issues

• [FEATURE] Add token count and cost estimation to dry run mode #113 — Adds token-count, cost, and processing-time metrics to dry-run output, matching the changes here.

Possibly related PRs

• Feature: Dry-Run Added #96 — Modifies cmd/cli/createMsg.go dry-run/display logic with token estimation; this PR extends it with cost and processing-time helpers.

Suggested labels

enhancement, go

Suggested reviewers

• DFanso

Poem

I thump my paws and count each token,
Burrows of bytes, neatly spoken.
Costs hop in (unless it’s Ollama),
Time estimates—no drama.
With carrots tall and output tight,
My dry-run shines in moonlit night. 🥕✨

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title Check	✅ Passed	The title clearly summarizes the primary change by stating that token counting, cost estimation, and processing time have been added to dry-run mode, which aligns directly with the pull request’s modifications.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

✨ Finishing touches

• 📝 Generate docstrings

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (1)

cmd/cli/createMsg.go (1)

625-637: Consider adding a disclaimer about processing time variability.

The fixed time ranges are reasonable rough estimates for dry-run previews, but actual processing time can vary significantly based on input size, specific model selection, network latency, and system load. Consider adding a comment or adjusting the display text to indicate these are approximate ranges.

For example, you could update line 569 to be more explicit:

-	statsData = append(statsData, []string{"Estimated Processing Time", fmt.Sprintf("%d-%d seconds", minTime, maxTime)})
+	statsData = append(statsData, []string{"Estimated Processing Time", fmt.Sprintf("~%d-%d seconds (approximate)", minTime, maxTime)})

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 3d2e536 and 4a824ad.

📒 Files selected for processing (1)

• cmd/cli/createMsg.go (2 hunks)

🧰 Additional context used

🧬 Code graph analysis (1)

cmd/cli/createMsg.go (2)

pkg/types/types.go (7)

• ProviderOllama (13-13)
• LLMProvider (5-5)
• ProviderOpenAI (8-8)
• ProviderClaude (9-9)
• ProviderGemini (10-10)
• ProviderGrok (11-11)
• ProviderGroq (12-12)

cmd/cli/store/store.go (1)

• LLMProvider (33-36)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)

• GitHub Check: Test Build
• GitHub Check: Build Go Binary (windows-latest)

🔇 Additional comments (2)

cmd/cli/createMsg.go (2)

551-571: LGTM! Well-structured dry-run enhancements.

The token estimation and conditional cost display logic is correct and appropriate for a dry-run preview. The separation of input, output, and total tokens provides clear visibility, and excluding cost for Ollama (local provider) is a thoughtful detail.

---

598-623: Unable to verify current pricing; please confirm updated API rates.

Pricing rates for GPT-4o, Claude Sonnet, Gemini Pro, Grok, and Groq may have changed since 2024. Please verify the current per-million-token input/output costs as of October 2025 and clarify which specific model tiers these estimates cover.

[DFanso]

LGTM 🎊