Enforce prompt window and trim transcripts deterministically

[heusalagroupbot]

Summary

• Add TrimMessagesToFit to fit prompts within model window while preserving system/dev, dropping oldest non‑pinned, and truncating pinned content as needed.
• Add PromptTokenBudget and use it to reserve space for the completion.
• Enforce trimming in both pre‑stage and main agent request paths.
• Add unit tests covering trimming policies and edge cases.

Context

Addresses Input tokens exceed the configured limit of 272000 tokens error in #75 by ensuring requests respect model context limits with a clear, deterministic policy.

Scope

• Code only; no config changes required. Default window remains conservative.

Test plan

• go test ./... passes locally.
• New tests in internal/oai/trim_test.go validate behavior.

Closes #75.

[Copilot]

Pull Request Overview

This PR implements deterministic prompt trimming to prevent token limit exceeded errors by adding a systematic approach to fit conversation transcripts within model context windows while preserving critical messages.

• Introduces TrimMessagesToFit function with a clear policy: pin system/developer messages, drop oldest non-pinned messages first, and truncate content proportionally when needed
• Adds PromptTokenBudget to calculate safe prompt limits considering completion token reservations
• Enforces trimming in both main agent and pre-stage request paths to prevent API errors

Reviewed Changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
internal/oai/trim.go	Core trimming implementation with deterministic policy for message preservation and content truncation
internal/oai/trim_test.go	Comprehensive unit tests covering trimming behavior, edge cases, and policy validation
internal/oai/context_window.go	Utility function to calculate prompt token budget with safety margins
cmd/agentcli/run_agent.go	Integration of trimming logic in main agent request path
cmd/agentcli/prestage.go	Integration of trimming logic in pre-stage request path

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[heusalagroupbot]

Status: Rebased on latest main, tests are green locally. Proceeding with review follow-ups if any.

[thejhh]

Check out the review comment from copilot and implement it, @heusalagroupbot

[thejhh]

Check out the review comment from copilot and implement it, @heusalagroupbot

[heusalagroupbot]

Rebase: rebased cleanly onto origin/main; pushed: no; tests: passed.

[thejhh]

Try again @heusalagroupbot. Check out the review comment from copilot review and implement it.

[thejhh]

Looks fine

[Copilot]

Copilot encountered an error and was unable to review this pull request. You can try again by re-requesting a review.