Bound Codex-Session Context Intake (#4280)

[Trecek]

Summary

Codex-backend sessions (gpt-5.6-sol, code_mode_only) repeatedly exhaust their context window through aggressive file intake because upstream Codex removed its read-chunking guidance and honors model-declared max_output_tokens unclamped. This plan bounds Codex context intake on four fronts:

1. Numeric intake-discipline instructions — a new CODEX_INTAKE_DISCIPLINE_DIGEST constant carrying the issue's numeric rules (at most 2 files per exec command; never read a file end-to-end; never pass max_output_tokens above 10000; open at most 2 files after a directory listing; AGENTS.md package tables are an index) plus the sub-agent spawn rules (fresh context via explicit fork_turns "none"). The digest is injected into every fresh-launch Codex delivery surface through the existing prompt-injector chain and developer_instructions composition points. Claude Code sessions never receive it.
2. AGENTS.md section 5 edit — the root package-table preamble is rewritten to state the table is an index, not required reading.
3. Per-repo output-ceiling documentation — docs/configuration.md and ADR-0005 document the two lower-ceiling launch paths for non-autoskillit repos, capping casual reads at ~40 KB.
4. Codex-cli upgrade tracking — a CODEX_LIMITS_LAST_VERIFIED_VERSION = (0, 144, 1) pin and doctor Check 39 (codex_limits_verified) that WARNs when the installed CLI is newer than the pin.

Requirements

REQ-RD-001: Codex sessions must receive a numeric instruction limiting file reads to at most 2 files per exec command.
REQ-RD-002: Codex sessions must be instructed to never read a file end-to-end, using ranged reads (rg -n with context, or sed -n ranges of at most 250 lines) instead.
REQ-RD-003: Codex sessions must be instructed to never pass max_output_tokens above 10000.
REQ-RD-004: Codex sessions must be instructed to open at most 2 of the files returned by a preceding directory listing.
REQ-RD-005: The AGENTS.md package table must be documented as an index rather than required reading, with per-package AGENTS.md consulted only for packages being modified.
REQ-SUB-001: Codex sessions must be instructed to spawn sub-agents with fresh context rather than fork_turns:"all".
REQ-SUB-002: Sub-agent spawn instructions must require an explicit narrow brief per sub-agent and specify that only a summary is returned to the parent.
REQ-CFG-001: A lower-ceiling launch path (per-project CODEX_HOME, or a -c tool_output_token_limit=N override) must be documented for non-autoskillit repos.
REQ-CFG-002: The documented per-repo ceiling must cap casual reads at approximately 40KB of output, down from the ~218KB produced by the autoskillit-sized default.
REQ-DEP-001: The codex-cli upgrade path must be tracked to capture the larger upstream gpt-5.6-sol context window (372,000 tokens vs. 258,400 tokens in the cli 0.144.1 registry).
REQ-DEP-002: Autoskillit's derived constants (CODEX_TOOL_OUTPUT_TOKEN_LIMIT, the auto-compact sentinel) must be verified consistent with the upstream registry after any codex-cli upgrade.

Closes #4280

Implementation Plan

Plan file: /home/talon/projects/generic_automation_mcp/.autoskillit/temp/make-plan/codex_context_intake_plan_2026-07-17_183300.md

🤖 Generated with Claude Code via AutoSkillit

[Trecek]

AutoSkillit PR Review — Verdict: approved_with_comments

[Trecek]

AutoSkillit review: warning-only findings detected. See inline comments — no blocking changes required.