Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
fix(codex): retag threads on init so Codex Desktop history stays visible (#961) (#1349)
Ben Younese6bbc40b115b
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex b9fa7396b..a3e7cc53b 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -30,6 +30,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0### Bug Fixes+* **codex:** retag existing Codex threads when `headroom init` injects the `headroom` provider, so Codex Desktop history stays visible. Codex filters its sidebar/search by the active `model_provider`; the init path set `model_provider = "headroom"` without retagging, so existing native `openai` threads disappeared from the menu (data was never deleted, only hidden). `_ensure_codex_provider` now reconciles thread tags openai→headroom, matching what the install and `wrap` paths already do; `headroom unwrap codex` handles the revert direction ([#961](https://github.com/chopratejas/headroom/issues/961)).* **install:** stop duplicating the container ENTRYPOINT in the `persistent-docker` runtime command. The published image already runs `headroom proxy` as its ENTRYPOINT, but `build_runtime_command` re-added `headroom proxy` after the image name, so the container ran `headroom proxy headroom proxy --host 0.0.0.0 …` and Click aborted with "Got unexpected extra arguments (headroom proxy)" — the deployment never became ready and rollback left nothing running. The runtime command now appends only the proxy flags ([#833](https://github.com/chopratejas/headroom/issues/833)).* **code:** keep Python `from __future__` imports before executable code during AST compression and validate compressed Python with `compile(..., "exec")` so compile-time syntax rules are enforced ([#1233](https://github.com/chopratejas/headroom/issues/1233)).* **proxy:** report real input tokens on the streaming `message_start` event for LiteLLM/Bedrock-backed requests. LiteLLM streaming never surfaces prompt tokens mid-stream, so `message_start.usage.input_tokens` was always `0`; Anthropic clients (e.g. Claude Code) read input-token metrics from that event, underreporting token usage by ~99% in OTel/CloudWatch dashboards. The Bedrock streamer now backfills `input_tokens` with the count Headroom actually sent upstream when the backend leaves it unset, preserving any non-zero value the backend genuinely reports ([#1132](https://github.com/chopratejas/headroom/issues/1132)).diff --git a/headroom/cli/init.py b/headroom/cli/init.pyindex 59e241400..2c68f1faf 100644--- a/headroom/cli/init.py+++ b/headroom/cli/init.py@@ -42,6 +42,7 @@ from headroom.install.state import load_manifest, save_manifestfrom headroom.install.supervisors import start_supervisorfrom headroom.providers.claude import TOOL_SEARCH_DEFAULT, TOOL_SEARCH_ENVfrom headroom.providers.codex.install import codex_uses_chatgpt_auth+from headroom.providers.codex.threads import retag_to_headroomfrom .main import main@@ -333,6 +334,12 @@ def _ensure_codex_provider(path: Path, port: int) -> None:)path.parent.mkdir(parents=True, exist_ok=True)path.write_text(content, encoding="utf-8")+ # Codex filters its history menu by the active model_provider, so existing+ # native threads vanish once we switch to "headroom". Retag them to match the+ # active provider so the history stays whole (#961), mirroring the install+ # (providers.codex.install) and wrap (cli.wrap) paths. The revert direction is+ # handled by `headroom unwrap codex`.+ retag_to_headroom(path.parent)def _codex_feature_block() -> str:diff --git a/tests/test_cli/test_init_cli.py b/tests/test_cli/test_init_cli.pyindex f94d293fd..72cc7210f 100644--- a/tests/test_cli/test_init_cli.py+++ b/tests/test_cli/test_init_cli.py@@ -1404,6 +1404,48 @@ def test_init_codex_writes_openai_base_url(monkeypatch, tmp_path: Path) -> None:)+def test_init_codex_provider_retags_existing_threads(monkeypatch, tmp_path: Path) -> None:+ """`headroom init` injects `model_provider = "headroom"` for Codex, which+ Codex Desktop filters its history menu by. Without retagging, existing native+ `openai` threads vanish from the sidebar/search (#961). `_ensure_codex_provider`+ must retag existing threads openai->headroom so the history stays visible —+ the same reconciliation the install and wrap paths already perform."""+ import sqlite3++ init_cli, _ = _load_init_module(monkeypatch)++ codex_home = tmp_path / ".codex"+ config_path = codex_home / "config.toml"+ # Codex Desktop reads <codex_home>/sqlite/state_5.sqlite.+ db = codex_home / "sqlite" / "state_5.sqlite"+ db.parent.mkdir(parents=True, exist_ok=True)+ conn = sqlite3.connect(str(db))+ try:+ conn.execute("CREATE TABLE threads (id TEXT PRIMARY KEY, model_provider TEXT NOT NULL)")+ conn.executemany(+ "INSERT INTO threads (id, model_provider) VALUES (?, ?)",+ [("t1", "openai"), ("t2", "openai"), ("t3", "anthropic")],+ )+ conn.commit()+ finally:+ conn.close()++ init_cli._ensure_codex_provider(config_path, 8787)++ conn = sqlite3.connect(str(db))+ try:+ counts = dict(+ conn.execute("SELECT model_provider, COUNT(*) FROM threads GROUP BY model_provider")+ )+ finally:+ conn.close()+ # Native threads now live under the active headroom provider (stay visible);+ # third-party providers are left untouched.+ assert counts.get("headroom") == 2, f"existing openai threads not retagged: {counts}"+ assert counts.get("openai", 0) == 0, f"openai threads still hidden: {counts}"+ assert counts.get("anthropic") == 1, f"third-party provider must be left alone: {counts}"++def test_init_codex_strip_removes_openai_base_url(monkeypatch, tmp_path: Path) -> None:"""_strip_codex_init_block must remove both the managed block and any orphanedopenai_base_url lines left by a crashed or partial init."""